Paper Citation Record · LEDGER

Universal and Transferable Adversarial Attacks on Aligned Language Models

As of 6 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 100 inbound Pith citation observations for arXiv:2307.15043.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2307.15043 v2

Coverage vector

measured 29 of 29 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-24T07:42:09.112946Z

measured 129 of 129 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00

measured 100 of 723 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T19:26:13.774858Z

measured 1 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-08-05T02:28:24.338817Z

Reference resolution

29 of 29 outbound references displayed

verified exact23
verified fuzzy2
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch4

External citation measurements

187
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation ca4e928a-9d59-41b2-b973-a170c0b100b1 · outbound

This paper cites Generating Natural Language Adversarial Examples.

Universal and Transferable Adversarial Attacks on Aligned Language Models Generating Natural Language Adversarial Examples

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-05-24T07:44:08.458367Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b2f5e9bd-290b-470c-9202-5eb960eee6c9 · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Universal and Transferable Adversarial Attacks on Aligned Language Models Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-24T07:44:08.438344Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6a9e9bee-8dd3-4138-a99f-f2f458f35de7 · outbound

This paper cites Evasion attacks against machine learning at test time.

Universal and Transferable Adversarial Attacks on Aligned Language Models Evasion attacks against machine learning at test time

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-24T07:44:08.931997Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 70b52c00-5d1e-4019-8c6b-dbede855f858 · outbound

This paper cites Are aligned neural networks adversarially aligned?.

Universal and Transferable Adversarial Attacks on Aligned Language Models Are aligned neural networks adversarially aligned?

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-24T07:44:08.583092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4a777885-6e35-43da-8749-bb209fb2e591 · outbound

This paper cites QLoRA: Efficient Finetuning of Quantized LLMs.

Universal and Transferable Adversarial Attacks on Aligned Language Models QLoRA: Efficient Finetuning of Quantized LLMs

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-24T07:44:08.576786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 97d41f36-9e04-4305-898e-8d65624e5c6f · outbound

This paper cites HotFlip: White-Box Adversarial Examples for Text Classification.

Universal and Transferable Adversarial Attacks on Aligned Language Models HotFlip: White-Box Adversarial Examples for Text Classification

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-24T07:44:08.570834Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d5dc8f3f-5cae-44a5-9567-4dfa8e5f5e6e · outbound

This paper cites Improving alignment of dialogue agents via targeted human judgements.

Universal and Transferable Adversarial Attacks on Aligned Language Models Improving alignment of dialogue agents via targeted human judgements

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-24T07:44:08.427372Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f7530c69-8ed4-4384-bf38-f51aeeed4585 · outbound

This paper cites Explaining and Harnessing Adversarial Examples.

Universal and Transferable Adversarial Attacks on Aligned Language Models Explaining and Harnessing Adversarial Examples

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-24T07:44:08.565407Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d85c7d76-6cfc-4435-86f8-85b94843a510 · outbound

This paper cites Gradient-based Adversarial Attacks against Text Transformers.

Universal and Transferable Adversarial Attacks on Aligned Language Models Gradient-based Adversarial Attacks against Text Transformers

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-24T07:44:08.560184Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e297ad03-7c85-42a5-bc48-d7e4bd71d09e · outbound

This paper cites Adversarial Examples for Evaluating Reading Comprehension Systems.

Universal and Transferable Adversarial Attacks on Aligned Language Models Adversarial Examples for Evaluating Reading Comprehension Systems

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-24T07:44:08.553572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2057dccc-700a-4cf2-9f2f-cc98e76fe724 · outbound

This paper cites Automatically Auditing Large Language Models via Discrete Optimization.

Universal and Transferable Adversarial Attacks on Aligned Language Models Automatically Auditing Large Language Models via Discrete Optimization

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-24T07:44:08.444210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 321cb681-049f-486e-96dc-72cd871218ab · outbound

This paper cites Scalable agent alignment via reward modeling: a research direction.

Universal and Transferable Adversarial Attacks on Aligned Language Models Scalable agent alignment via reward modeling: a research direction

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-24T07:44:08.548111Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 0f77806a-b0a6-430c-a32d-59bb0a883152 · outbound

This paper cites The Power of Scale for Parameter-Efficient Prompt Tuning.

Universal and Transferable Adversarial Attacks on Aligned Language Models The Power of Scale for Parameter-Efficient Prompt Tuning

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-24T07:44:08.432848Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1ecd6f6f-ef44-4f02-8e17-ff3599895285 · outbound

This paper cites Sok: Certified robustness for deep neural networks.

Universal and Transferable Adversarial Attacks on Aligned Language Models Sok: Certified robustness for deep neural networks

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-24T07:44:08.935695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b979029f-6eec-4452-a10f-2985c4c8fd37 · outbound

This paper cites Exploring Targeted Universal Adversarial Perturbations to End-to-end ASR Models.

Universal and Transferable Adversarial Attacks on Aligned Language Models Exploring Targeted Universal Adversarial Perturbations to End-to-end ASR Models

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-24T07:44:08.543081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d76ba06f-d1c6-48a0-b92b-75a91a292791 · outbound

This paper cites Black Box Adversarial Prompting for Foundation Models.

Universal and Transferable Adversarial Attacks on Aligned Language Models Black Box Adversarial Prompting for Foundation Models

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-24T07:44:08.537226Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ac6388fc-d75b-4f5b-a80b-472482296aca · outbound

This paper cites Universal Adversarial Perturbations for Speech Recognition Systems.

Universal and Transferable Adversarial Attacks on Aligned Language Models Universal Adversarial Perturbations for Speech Recognition Systems

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-24T07:44:08.531019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d83fd42c-7ee9-4e4a-9ba9-b8cea034257a · outbound

This paper cites Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples.

Universal and Transferable Adversarial Attacks on Aligned Language Models Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-05-24T07:44:08.523743Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c0389a04-54c2-4631-9fdd-c8aa7ef0fd9c · outbound

This paper cites The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only.

Universal and Transferable Adversarial Attacks on Aligned Language Models The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only

Reference 19

Resolution: metadata mismatch; local_arxiv, observed 2026-05-24T07:44:08.464630Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1045f988-1058-450c-9c07-c2c184a9cd74 · outbound

This paper cites AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts.

Universal and Transferable Adversarial Attacks on Aligned Language Models AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts

Reference 20

Resolution: metadata mismatch; arxiv_id, observed 2026-05-24T07:44:08.517831Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3831fdf3-9c73-4317-93af-53f49c229acb · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Universal and Transferable Adversarial Attacks on Aligned Language Models Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 21

Resolution: metadata mismatch; local_arxiv, observed 2026-05-24T07:44:08.512307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 023b5a70-651b-4c14-b264-82fadcd3dcd6 · outbound

This paper cites The Space of Transferable Adversarial Examples.

Universal and Transferable Adversarial Attacks on Aligned Language Models The Space of Transferable Adversarial Examples

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-05-24T07:44:08.506484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 51751e4c-a6b8-468f-8be4-42ff42147cec · outbound

This paper cites Universal Adversarial Triggers for Attacking and Analyzing NLP.

Universal and Transferable Adversarial Attacks on Aligned Language Models Universal Adversarial Triggers for Attacking and Analyzing NLP

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-24T07:44:08.501178Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 299597fc-8011-4ba3-900f-bd62627e7964 · outbound

This paper cites Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models.

Universal and Transferable Adversarial Attacks on Aligned Language Models Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-24T07:44:08.495253Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3bd9b335-1537-4360-a4d6-67d4c015a45d · outbound

This paper cites Jailbroken: How Does LLM Safety Training Fail?.

Universal and Transferable Adversarial Attacks on Aligned Language Models Jailbroken: How Does LLM Safety Training Fail?

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-05-24T07:44:08.488843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e62e4a33-f511-4137-b300-e7a0247455d2 · outbound

This paper cites Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery.

Universal and Transferable Adversarial Attacks on Aligned Language Models Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-24T07:44:08.477006Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3efae1f4-54d7-4687-aafa-7b082e8c0467 · outbound

This paper cites Fundamental Limitations of Alignment in Large Language Models.

Universal and Transferable Adversarial Attacks on Aligned Language Models Fundamental Limitations of Alignment in Large Language Models

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-24T07:44:08.470910Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation cebe60e5-147d-4845-8fa1-b8dd4a3d0d07 · outbound

This paper cites Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena.

Universal and Transferable Adversarial Attacks on Aligned Language Models Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-05-24T07:44:08.450809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2b2e6116-13c7-4016-8e76-f738ee64014d · outbound

This paper cites PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts.

Universal and Transferable Adversarial Attacks on Aligned Language Models PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-24T07:44:08.483210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Pith citing papers

Observation 689f133a-5324-4b83-8b9e-c4eea52b2441 · inbound

XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models cites this paper.

XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 5

Resolution: metadata mismatch; local_arxiv, observed 2026-05-15T06:51:50.807968Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7ec25416-37d4-4a6f-826e-2f9e0880554d · inbound

"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models cites this paper.

"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 95

Resolution: metadata mismatch; local_arxiv, observed 2026-05-17T08:39:28.195931Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation acaf8eee-4c15-4042-b03f-d453f71624a3 · inbound

Baseline Defenses for Adversarial Attacks Against Aligned Language Models cites this paper.

Baseline Defenses for Adversarial Attacks Against Aligned Language Models Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 67

Resolution: metadata mismatch; local_arxiv, observed 2026-05-13T23:24:39.984464Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation cfc55ff5-8613-4f87-b8a0-da5af497d12f · inbound

GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts cites this paper.

GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 78

Resolution: metadata mismatch; local_arxiv, observed 2026-05-15T06:25:21.174508Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8bc99e31-5022-4f5d-8b1b-659d0ef8fd2e · inbound

Low-Resource Languages Jailbreak GPT-4 cites this paper.

Low-Resource Languages Jailbreak GPT-4 Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 57

Resolution: verified exact; local_arxiv, observed 2026-05-17T09:24:14.046876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9f633d5a-b017-40db-b951-b5cc550752bf · inbound

SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks cites this paper.

SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-05-14T17:11:00.729569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation cb3c49d1-813d-41b1-94d9-da2e6c6bff3e · inbound

Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation cites this paper.

Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-05-16T22:00:51.530893Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9079ed20-f698-4c86-9b07-489d1b1d3578 · inbound

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting cites this paper.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 59

Resolution: metadata mismatch; local_arxiv, observed 2026-05-17T01:59:51.414513Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 19f7b153-cf69-4d84-a46e-93245620482a · inbound

AI Alignment: A Comprehensive Survey cites this paper.

AI Alignment: A Comprehensive Survey Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-05-17T14:28:49.032977Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 58a9aa42-db13-4505-a043-5befa3274470 · inbound

Scalable Extraction of Training Data from (Production) Language Models cites this paper.

Scalable Extraction of Training Data from (Production) Language Models Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 56

Resolution: metadata mismatch; local_arxiv, observed 2026-05-15T19:00:46.810082Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8e84bd5f-8736-41af-9961-f9f71ab2b41a · inbound

TOFU: A Task of Fictitious Unlearning for LLMs cites this paper.

TOFU: A Task of Fictitious Unlearning for LLMs Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 44

Resolution: verified exact; local_arxiv, observed 2026-05-16T11:07:39.246388Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 072c6e2a-0719-4282-b7aa-32e4992998ac · inbound

Whispers in the Machine: Confidentiality in Agentic Systems cites this paper.

Whispers in the Machine: Confidentiality in Agentic Systems Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-05-24T04:03:53.912178Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7f8da37b-d73a-46ac-acc8-04760c41a286 · inbound

A StrongREJECT for Empty Jailbreaks cites this paper.

A StrongREJECT for Empty Jailbreaks Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 44

Resolution: verified exact; local_arxiv, observed 2026-05-16T21:28:02.900691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4df00ab4-ea88-47ed-a0bc-0df4844ba04d · inbound

Defending Against Indirect Prompt Injection Attacks With Spotlighting cites this paper.

Defending Against Indirect Prompt Injection Attacks With Spotlighting Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-05-14T22:28:55.503509Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7149086c-43aa-441f-a801-7da49abfc2b1 · inbound

JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models cites this paper.

JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 64

Resolution: verified exact; local_arxiv, observed 2026-05-15T06:08:05.564496Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8350874e-ad20-47ca-ac27-48037e9179b5 · inbound

Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack cites this paper.

Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 36

Resolution: metadata mismatch; local_arxiv, observed 2026-05-18T02:12:41.520873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6370596a-fdd9-4567-b76b-1ba428927731 · inbound

LLM Agents can Autonomously Exploit One-day Vulnerabilities cites this paper.

LLM Agents can Autonomously Exploit One-day Vulnerabilities Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-05-18T04:18:27.680738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1b2eada1-26ce-4905-a0c5-23380fb12b90 · inbound

The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions cites this paper.

The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 15

Resolution: metadata mismatch; local_arxiv, observed 2026-05-12T10:59:30.811638Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f70dc3f4-852e-49b1-8029-357de2a01387 · inbound

Uncovering Logit Suppression Vulnerabilities in LLM Safety Alignment cites this paper.

Uncovering Logit Suppression Vulnerabilities in LLM Safety Alignment Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-05-24T00:38:39.800763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8990ca77-8e46-4295-973c-6fa1cb724aab · inbound

Refusal in Language Models Is Mediated by a Single Direction cites this paper.

Refusal in Language Models Is Mediated by a Single Direction Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 208

Resolution: verified exact; local_arxiv, observed 2026-05-13T10:47:56.181588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d9c4eff1-78e4-4d0c-af2c-c8aeac3843c4 · inbound

AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents cites this paper.

AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 73

Resolution: metadata mismatch; local_arxiv, observed 2026-05-13T06:35:13.539981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 78e3adc0-7411-4d4b-96d4-4c86ceeeba18 · inbound

WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs cites this paper.

WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 44

Resolution: verified exact; local_arxiv, observed 2026-05-17T16:25:14.923012Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9ba9306c-28a8-4616-8a2c-4fd7c64240d0 · inbound

Jailbreak Attacks and Defenses Against Large Language Models: A Survey cites this paper.

Jailbreak Attacks and Defenses Against Large Language Models: A Survey Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 125

Resolution: metadata mismatch; local_arxiv, observed 2026-05-15T02:20:44.537423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 0e127a1a-06d7-4776-95b0-0087710317ac · inbound

Guidance for twisted particle filter: a continuous-time perspective cites this paper.

Guidance for twisted particle filter: a continuous-time perspective Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 70

Resolution: verified exact; local_arxiv, observed 2026-05-23T21:08:26.084514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation df5667e5-d446-46e4-a88d-0a5a584f919b · inbound

Training Language Models to Self-Correct via Reinforcement Learning cites this paper.

Training Language Models to Self-Correct via Reinforcement Learning Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 138

Resolution: metadata mismatch; local_arxiv, observed 2026-05-17T12:04:10.681068Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 979b9f49-bfce-45ca-8377-e8ad995d6700 · inbound

Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey cites this paper.

Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 184

Resolution: metadata mismatch; local_arxiv, observed 2026-05-23T20:58:25.850959Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5a53c659-fa35-4dea-8ff0-6632e7ba4b1e · inbound

Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems cites this paper.

Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 98

Resolution: metadata mismatch; local_arxiv, observed 2026-05-15T19:32:19.876030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6b640dcf-4154-4191-95c9-4adfb30dd792 · inbound

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents cites this paper.

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 37

Resolution: metadata mismatch; local_arxiv, observed 2026-05-14T01:35:51.188032Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 61bec995-990b-4a62-b57d-70cfcaa12970 · inbound

Faster-GCG: Efficient Discrete Optimization Jailbreak Attacks against Aligned Large Language Models cites this paper.

Faster-GCG: Efficient Discrete Optimization Jailbreak Attacks against Aligned Large Language Models Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 14

Resolution: metadata mismatch; local_arxiv, observed 2026-05-23T19:03:21.394452Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ce3bce45-f4b3-47b5-884f-7d52f467af29 · inbound

VoiceBench: Benchmarking LLM-Based Voice Assistants cites this paper.

VoiceBench: Benchmarking LLM-Based Voice Assistants Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 111

Resolution: verified exact; local_arxiv, observed 2026-05-17T00:50:13.931900Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3438c2bd-479c-41be-aa06-dd13c4777f2a · inbound

Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference cites this paper.

Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 25

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T17:46:47.014121Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b7cc975b-4979-4e18-82c7-854a94d69f03 · inbound

Adversarial Hubness in Multi-Modal Retrieval cites this paper.

Adversarial Hubness in Multi-Modal Retrieval Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 93

Resolution: verified exact; local_arxiv, observed 2026-05-23T06:42:39.776660Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ccaf8640-23cc-4605-9a3a-18bca850bbc6 · inbound

Improving LLM Unlearning Robustness via Random Perturbations cites this paper.

Improving LLM Unlearning Robustness via Random Perturbations Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 39

Resolution: verified exact; local_arxiv, observed 2026-05-23T04:42:33.408884Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation cbb29ad8-3885-4d94-aeda-1032d8eb6078 · inbound

Peering Behind the Shield: Guardrail Identification in Large Language Models cites this paper.

Peering Behind the Shield: Guardrail Identification in Large Language Models Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 45

Resolution: metadata mismatch; local_arxiv, observed 2026-05-23T03:45:21.382565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 637f526e-2929-40eb-97d3-90a660c36cc2 · inbound

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety cites this paper.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 93

Resolution: verified exact; local_arxiv, observed 2026-05-23T04:42:33.773359Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 894a831f-546e-4e02-93cb-64991a8715a0 · inbound

Responsible Federated LLMs via Safety Filtering and Constitutional AI cites this paper.

Responsible Federated LLMs via Safety Filtering and Constitutional AI Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 43

Resolution: verified exact; local_arxiv, observed 2026-05-23T02:22:25.163571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation af241a98-56db-4f1d-94c4-6c9679ab0378 · inbound

Towards an AI co-scientist cites this paper.

Towards an AI co-scientist Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 18

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T13:02:44.377608Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation bc488420-641c-4c77-88b8-04b63f9be930 · inbound

Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction cites this paper.

Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-05-22T19:11:58.054185Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 24a4adc1-99d1-4f51-8574-5635935e58ac · inbound

Phonetic Perturbations Reveal Tokenizer-Rooted Safety Gaps in LLMs cites this paper.

Phonetic Perturbations Reveal Tokenizer-Rooted Safety Gaps in LLMs Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-05-22T14:41:41.452731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f02a76a8-8b5c-4f40-89c5-fab83ff4e166 · inbound

Improving LLM First-Token Predictions in Multiple-Choice Question Answering via Output Prefilling cites this paper.

Improving LLM First-Token Predictions in Multiple-Choice Question Answering via Output Prefilling Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 51

Resolution: malformed identifier; local_arxiv, observed 2026-05-22T14:21:39.607873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b76efd75-d0d9-46ea-ad2a-d362a8bce8f4 · inbound

Secure LLM Fine-Tuning via Safety-Aware Probing cites this paper.

Secure LLM Fine-Tuning via Safety-Aware Probing Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 44

Resolution: verified exact; local_arxiv, observed 2026-05-22T13:11:35.797307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b7c82321-6650-484a-962c-968250b0b367 · inbound

Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs cites this paper.

Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 46

Resolution: malformed identifier; local_arxiv, observed 2026-05-22T13:31:36.614411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8f9b1d36-ed45-4d04-bae2-971bb6b06b23 · inbound

ReGA: Model-Based Safeguard for LLMs via Representation-Guided Abstraction cites this paper.

ReGA: Model-Based Safeguard for LLMs via Representation-Guided Abstraction Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-05-19T11:37:16.011602Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9376c1d2-219c-4e2e-b956-503d17ea8e7d · inbound

Through the Stealth Lens: Attention-Aware Defenses Against Poisoning in RAG cites this paper.

Through the Stealth Lens: Attention-Aware Defenses Against Poisoning in RAG Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 47

Resolution: verified exact; local_arxiv, observed 2026-05-25T08:15:34.183042Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 511005a8-5dd7-4be7-8719-e9692af9ad39 · inbound

Benchmarking Misuse Mitigation Against Covert Adversaries cites this paper.

Benchmarking Misuse Mitigation Against Covert Adversaries Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 31

Resolution: metadata mismatch; local_arxiv, observed 2026-05-19T10:32:14.672975Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a5c26d1f-29f0-4915-ae9d-f3845d336592 · inbound

Enhancing the Safety of Medical Vision-Language Models by Synthetic Demonstrations cites this paper.

Enhancing the Safety of Medical Vision-Language Models by Synthetic Demonstrations Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 41

Resolution: verified exact; local_arxiv, observed 2026-05-19T10:57:16.516818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 80df81ac-fe22-4c21-b861-2c9cf89ea567 · inbound

Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems cites this paper.

Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 80

Resolution: metadata mismatch; local_arxiv, observed 2026-05-19T09:22:15.935221Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a1907dc4-5f4e-4c17-ae41-e158b954d2f3 · inbound

Exploring the Secondary Risks of Large Language Models cites this paper.

Exploring the Secondary Risks of Large Language Models Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 57

Resolution: verified exact; local_arxiv, observed 2026-05-19T09:42:13.917686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation da4f7547-1716-48ad-a6b2-97c30866c39b · inbound

Toward Principled LLM Safety Testing: Solving the Jailbreak Oracle Problem cites this paper.

Toward Principled LLM Safety Testing: Solving the Jailbreak Oracle Problem Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-19T08:42:12.809508Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a8a01a32-cf18-4ac8-aa00-4f59739f1c6d · inbound

Optimus: A Robust Defense Framework for Mitigating Toxicity while Fine-Tuning Conversational AI cites this paper.

Optimus: A Robust Defense Framework for Mitigating Toxicity while Fine-Tuning Conversational AI Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 88

Resolution: verified exact; local_arxiv, observed 2026-05-22T12:21:31.168880Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 822a0e55-2997-4ae1-8622-df97a4992f59 · inbound

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations cites this paper.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:47.094379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 509b5c76-8874-43d0-a16c-ce5ef743af98 · inbound

Data Compressibility Quantifies LLM Memorization cites this paper.

Data Compressibility Quantifies LLM Memorization Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 49

Resolution: verified exact; local_arxiv, observed 2026-05-19T06:02:07.677164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 05f8fcb2-eb3f-441e-99f1-8a526aa9d2fe · inbound

The bitter lesson of misuse detection cites this paper.

The bitter lesson of misuse detection Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:40.283148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81543be5-060c-4908-a8f5-81c9cc76f904 · inbound

Bridging AI and Software Security: A Comparative Vulnerability Assessment of LLM Agent Deployment Paradigms cites this paper.

Bridging AI and Software Security: A Comparative Vulnerability Assessment of LLM Agent Deployment Paradigms Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T19:12:22.950253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f682a274-4437-454e-9094-6f3cd42927a9 · inbound

A Mathematical Theory of Discursive Networks cites this paper.

A Mathematical Theory of Discursive Networks Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:18.041331Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3038363-73c7-4391-9fea-9f2d75a9285f · inbound

Mitigating Watermark Forgery in Generative Models via Randomized Key Selection cites this paper.

Mitigating Watermark Forgery in Generative Models via Randomized Key Selection Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 51

Resolution: metadata mismatch; local_arxiv, observed 2026-05-19T05:27:05.474981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation aad169b6-04a0-46ca-8be5-38d353ad6935 · inbound

Defending Against Prompt Injection With a Few DefensiveTokens cites this paper.

Defending Against Prompt Injection With a Few DefensiveTokens Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:44.285307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a23e8d93-7f7b-4d19-8c45-61b2b66b355d · inbound

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation cites this paper.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.774858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55d16c82-124c-46f0-820c-40016709b7f5 · inbound

SEALGuard: Safeguarding the Multilingual Conversations in Southeast Asian Languages for LLM Software Systems cites this paper.

SEALGuard: Safeguarding the Multilingual Conversations in Southeast Asian Languages for LLM Software Systems Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:46.576684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dda1b033-61d2-4105-9240-05780f8dee01 · inbound

Explicit Vulnerability Generation with LLMs: An Investigation Beyond Adversarial Attacks cites this paper.

Explicit Vulnerability Generation with LLMs: An Investigation Beyond Adversarial Attacks Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T17:45:58.756338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4777db18-432d-4d4b-b08a-62bbc6266ced · inbound

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models cites this paper.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:27.669576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 182fc9f9-0577-4c67-9158-41413fef0fbf · inbound

Scaling laws for activation steering with Llama 2 models and refusal mechanisms cites this paper.

Scaling laws for activation steering with Llama 2 models and refusal mechanisms Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T17:05:04.749036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1612cb63-f7b3-4493-b43e-c44ffd16bb53 · inbound

Watch, Listen, Understand, Mislead: Tri-modal Adversarial Attacks on Short Videos for Content Appropriateness Evaluation cites this paper.

Watch, Listen, Understand, Mislead: Tri-modal Adversarial Attacks on Short Videos for Content Appropriateness Evaluation Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T17:09:24.884191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c71ef73d-e629-4829-bd77-79b456a154dc · inbound

DEMONSTRATE: Zero-shot Language to Robotic Control via Multi-task Demonstration Learning cites this paper.

DEMONSTRATE: Zero-shot Language to Robotic Control via Multi-task Demonstration Learning Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T16:42:30.788941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b688f2f-1418-4268-8b2c-054e0d455c8b · inbound

Paper Summary Attack: Jailbreaking LLMs through LLM Safety Papers cites this paper.

Paper Summary Attack: Jailbreaking LLMs through LLM Safety Papers Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-06T16:28:54.067424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b34dbed-1ad6-4c8e-a379-7265076398a4 · inbound

Large Language Models in Cybersecurity: Applications, Vulnerabilities, and Defense Techniques cites this paper.

Large Language Models in Cybersecurity: Applications, Vulnerabilities, and Defense Techniques Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 165

Resolution: unresolved; no resolver link, observed 2026-08-06T16:24:30.380334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa31761e-3949-45f7-ae22-ae12307ef775 · inbound

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models cites this paper.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:54.883404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bba77999-6c87-41b9-bf16-cc2d7c3a81ad · inbound

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training cites this paper.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.626472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72567c5b-b766-408c-84bc-fbb1cad14ede · inbound

Manipulating LLM Web Agents with Indirect Prompt Injection Attack via HTML Accessibility Tree cites this paper.

Manipulating LLM Web Agents with Indirect Prompt Injection Attack via HTML Accessibility Tree Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T15:52:56.837539Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05a11772-9b8d-4347-87ad-2ea278f2011e · inbound

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning cites this paper.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.441397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5fd10a6-b584-415e-a924-c1a1834b7ae5 · inbound

PromptArmor: Simple yet Effective Prompt Injection Defenses cites this paper.

PromptArmor: Simple yet Effective Prompt Injection Defenses Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-06T15:42:01.109613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46896952-598c-46e0-835f-975c032324c5 · inbound

Scaling Decentralized Learning with FLock cites this paper.

Scaling Decentralized Learning with FLock Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T15:40:19.586657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4109fe61-1555-4a87-afec-b2619bbd29d4 · inbound

Multi-Stage Prompt Inference Attacks on Enterprise LLM Systems cites this paper.

Multi-Stage Prompt Inference Attacks on Enterprise LLM Systems Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T15:32:52.962454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2fc7540c-8fa6-4f35-9582-0abde34b4e65 · inbound

When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning LLMs cites this paper.

When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning LLMs Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T15:07:29.257814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d7e05da-9a35-4c94-9b5d-ee9effd20baf · inbound

Agent Identity Evals: Measuring Agentic Identity cites this paper.

Agent Identity Evals: Measuring Agentic Identity Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T14:57:06.710356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ef33d82-3afb-4942-8a18-8c3bbd3e0cd9 · inbound

An Uncertainty-Driven Adaptive Self-Alignment Framework for Large Language Models cites this paper.

An Uncertainty-Driven Adaptive Self-Alignment Framework for Large Language Models Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T14:51:53.952177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67231121-8a7e-4839-b5ad-4050d547ecd5 · inbound

From Seed to Harvest: Augmenting Human Creativity with AI for Red-teaming Text-to-Image Models cites this paper.

From Seed to Harvest: Augmenting Human Creativity with AI for Red-teaming Text-to-Image Models Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:20.584079Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44dd8d47-a542-4d88-b2d7-e04cd9399c11 · inbound

Understanding the Supply Chain and Risks of Large Language Model Applications cites this paper.

Understanding the Supply Chain and Risks of Large Language Model Applications Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:42.918332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39d40f62-47b1-4f12-a3ce-39c1cd4c782c · inbound

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection cites this paper.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-06T14:42:08.218547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 258945a3-61a4-4d26-ad7a-a680973cd1d1 · inbound

MOCHA: Are Code Language Models Robust Against Multi-Turn Malicious Coding Prompts? cites this paper.

MOCHA: Are Code Language Models Robust Against Multi-Turn Malicious Coding Prompts? Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:34.222274Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7824e3b7-baaa-4e5c-b1d7-1e519ffd28b0 · inbound

Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges cites this paper.

Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-06T14:13:06.203975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0689a87f-add5-4750-9a33-7b636a5c79eb · inbound

A Survey on Generative Model Unlearning: Fundamentals, Taxonomy, Evaluation, and Future Direction cites this paper.

A Survey on Generative Model Unlearning: Fundamentals, Taxonomy, Evaluation, and Future Direction Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 271

Resolution: unresolved; no resolver link, observed 2026-08-06T13:54:40.584133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c3fa86f-39a3-4e81-aef5-217f6cfced5e · inbound

Analysis of Threat-Based Manipulation in Large Language Models: A Dual Perspective on Vulnerabilities and Performance Enhancement Opportunities cites this paper.

Analysis of Threat-Based Manipulation in Large Language Models: A Dual Perspective on Vulnerabilities and Performance Enhancement Opportunities Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T15:10:29.544536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee54552d-dc47-4001-9de5-3984dec23f87 · inbound

TRIDENT: Benchmarking LLM Safety in Finance, Medicine, and Law cites this paper.

TRIDENT: Benchmarking LLM Safety in Finance, Medicine, and Law Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-06T15:04:21.377383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b19ed04-201d-49af-ac45-199cae965ab4 · inbound

PRISM: Programmatic Reasoning with Image Sequence Manipulation for LVLM Jailbreaking cites this paper.

PRISM: Programmatic Reasoning with Image Sequence Manipulation for LVLM Jailbreaking Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 50

Resolution: metadata mismatch; local_arxiv, observed 2026-05-19T03:37:01.111600Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c4fdc14f-445e-4781-9f32-f9361afa7df3 · inbound

Training language models to be warm and empathetic makes them less reliable and more sycophantic cites this paper.

Training language models to be warm and empathetic makes them less reliable and more sycophantic Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T12:18:37.932831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ab8a4e0-999b-4b93-a1ca-820f02528e21 · inbound

Strategic Deflection: Defending LLMs from Logit Manipulation cites this paper.

Strategic Deflection: Defending LLMs from Logit Manipulation Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T12:05:44.471626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7e21a6a-5c9e-4963-b3b2-45149780c19b · inbound

ProbGuard: Proactive Runtime Monitoring for LLM Agent Safety via Probabilistic Prediction cites this paper.

ProbGuard: Proactive Runtime Monitoring for LLM Agent Safety via Probabilistic Prediction Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-06T10:13:24.003904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63eef6ee-9127-41be-a63b-b15d1a0cda18 · inbound

Adaptive Content Restriction for Large Language Models via Suffix Optimization cites this paper.

Adaptive Content Restriction for Large Language Models via Suffix Optimization Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T05:53:58.417889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d008524b-2600-43f7-aabf-d8db455af81e · inbound

PUZZLED: Jailbreaking LLMs through Word-Based Puzzles cites this paper.

PUZZLED: Jailbreaking LLMs through Word-Based Puzzles Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T05:43:40.073275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 554aa273-f8f3-4e03-88a6-cfc38ee93423 · inbound

A comprehensive taxonomy of hallucinations in Large Language Models cites this paper.

A comprehensive taxonomy of hallucinations in Large Language Models Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 108

Resolution: unresolved; no resolver link, observed 2026-08-06T05:29:20.984433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04d16a38-0f21-415b-a5ff-0d1c0fc63bcc · inbound

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning cites this paper.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:22.349778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc60518b-deb8-4fc3-88a7-a602e4919a1c · inbound

ReasoningGuard: Safeguarding Large Reasoning Models with Inference-time Safety Aha Moments cites this paper.

ReasoningGuard: Safeguarding Large Reasoning Models with Inference-time Safety Aha Moments Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 34

Resolution: metadata mismatch; local_arxiv, observed 2026-05-19T01:02:54.791365Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation fe9819de-170b-47b6-b817-f4b5472bb3f3 · inbound

Automatic LLM Red Teaming cites this paper.

Automatic LLM Red Teaming Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T00:04:25.509141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4660857-0f0c-4709-959c-2603ffaed132 · inbound

Quantifying Conversation Drift in MCP via Latent Polytope cites this paper.

Quantifying Conversation Drift in MCP via Latent Polytope Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-05T22:51:28.192282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9154070-1a34-4e73-923e-6ee24ea89336 · inbound

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection cites this paper.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T22:24:23.367757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e05cc146-80ba-4697-b710-292789aa3a39 · inbound

From Hard Refusals to Safe-Completions: Toward Output-Centric Safety Training cites this paper.

From Hard Refusals to Safe-Completions: Toward Output-Centric Safety Training Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-05T21:35:34.616461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a38a564c-74ba-4d95-803e-320d6bbb4945 · inbound

NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs cites this paper.

NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-05T21:08:06.140982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ae6274f-493e-4d41-9408-b6a083ff8ea8 · inbound

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation cites this paper.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:31.913269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a2bac1f-2a01-4ccd-bdec-c3257360aa44 · inbound

ORFuzz: Fuzzing the "Other Side" of LLM Safety -- Testing Over-Refusal cites this paper.

ORFuzz: Fuzzing the "Other Side" of LLM Safety -- Testing Over-Refusal Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-05-18T23:31:54.549906Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.