Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift | Paper Citation Record

Observation c0c05eef-9022-48b9-bc81-2be2ba0ad8d5 · outbound

This paper cites an unresolved cited work.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:22:00.037107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6ef95d3b-167c-42da-b9bd-cc6829dec31a · outbound

This paper cites Foundational Challenges in Assuring Alignment and Safety of Large Language Models.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Foundational Challenges in Assuring Alignment and Safety of Large Language Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.728709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0476618d-1137-4ef8-bbec-acaaf3cbbfff · outbound

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

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Refusal in Language Models Is Mediated by a Single Direction

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.734558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 007f57b3-905f-4231-93e3-a9829da3619a · outbound

This paper cites an unresolved cited work.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.739712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c16cb58-1c18-4637-814f-655aa845de18 · outbound

This paper cites Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.749481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6051bc4-d415-4630-a8a8-6d1264b3241d · outbound

This paper cites Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Conference’17, July 2017, Washington, DC, USA Pappas, Florian Tramèr, Hamed Hassani, and Eric Wong.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Conference’17, July 2017, Washington, DC, USA Pappas, Florian Tramèr, Hamed Hassani, and Eric Wong

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:22:00.012051Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation de473e3f-301b-42e0-a2de-80074899320d · outbound

This paper cites Jailbreaking Black Box Large Language Models in Twenty Queries.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.759970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a1fa6dd-89a4-4691-840b-fd0d08cafc5e · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.765160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 412d3b52-7cfc-40dd-bdde-b38298ed82c0 · outbound

This paper cites Exploiting LLM Quantization.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Exploiting LLM Quantization

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.770502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6b8fbfe-074b-4a14-bc40-02564e602db2 · outbound

This paper cites Improved Large Language Model Jailbreak Detection via Pretrained Embeddings.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Improved Large Language Model Jailbreak Detection via Pretrained Embeddings

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.775054Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c91ebf5-5df8-4145-a9c1-4db7efab60e4 · outbound

This paper cites Sah, and Fathi Am- saad.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Sah, and Fathi Am- saad

Reference 11

Resolution: verified exact; raw_fallback, observed 2026-08-15T16:21:59.724359Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 21c3e0e8-c25d-43cd-992c-c96839172633 · outbound

This paper cites COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.790091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4037bb0-48ea-40e9-9565-1e8456f2da7a · outbound

This paper cites Smoothed Embeddings for Robust Language Models.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Smoothed Embeddings for Robust Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.795021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91e254e3-1138-4adc-b695-2056d4002ac1 · outbound

This paper cites Large Language Model Supply Chain: Open Problems From the Security Perspective.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Large Language Model Supply Chain: Open Problems From the Security Perspective

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.799851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 645c7d78-d786-4a06-aedc-f6852660446c · outbound

This paper cites an unresolved cited work.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.804727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bd0a1b7-d4dd-4971-bf98-d8f32c2881e0 · outbound

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

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.815294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afef8dbc-a808-4655-b771-164f40d105b6 · outbound

This paper cites Mistral 7B.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Mistral 7B

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.819852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5705883a-3555-4e6c-8ef4-f5d491cc574a · outbound

This paper cites an unresolved cited work.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:21:59.986094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0acb6bc5-0617-43f9-bc2c-0db8dbb3d004 · outbound

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

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Uncovering Logit Suppression Vulnerabilities in LLM Safety Alignment

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.835860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33adecd4-26ea-48d7-8ba7-c3e5aa51a594 · outbound

This paper cites an unresolved cited work.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.841537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bcb2cb5-11ab-4f37-bcfe-5a802068d797 · outbound

This paper cites AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.852566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c57b97dc-2c7d-41cc-9fa5-5ff5f8a1e86d · outbound

This paper cites The Llama 3 Herd of Models.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift The Llama 3 Herd of Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.857698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1badeca7-5c3a-4086-a07d-8f972f185b85 · outbound

This paper cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.863345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c0fa113-6fd8-4fec-adaf-dbaa844fbbdd · outbound

This paper cites Training language models to follow instructions with human feedback.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Training language models to follow instructions with human feedback

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.868744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd95d0fa-b4cd-4204-9979-67abe94b847e · outbound

This paper cites Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.873890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 524ab78b-ec1a-42cd-9647-33b2f93548f0 · outbound

This paper cites Direct Preference Optimization: Your Language Model is Secretly a Reward Model.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.879102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 046dffd4-09e0-4616-a220-e0e89254513e · outbound

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

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.884367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f00a2928-b60b-4059-8a47-3cf891666862 · outbound

This paper cites an unresolved cited work.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.889610Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2fb63d71-039d-43af-8ba0-f4c1c92cc05c · outbound

This paper cites Adversarial Attacks and Defenses in Large Language Models: Old and New Threats.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Adversarial Attacks and Defenses in Large Language Models: Old and New Threats

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.899446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a90ab51-7588-49ee-bb68-757c5ce8b108 · outbound

This paper cites Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.905172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61f5cc48-e92e-41a7-98fd-cd43789d5a55 · outbound

This paper cites Large Language Models Encode Clinical Knowledge.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Large Language Models Encode Clinical Knowledge

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.910428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0af96e4-467b-472e-b8a7-fea8f4cfceae · outbound

This paper cites Gemma: Open Models Based on Gemini Research and Technology.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Gemma: Open Models Based on Gemini Research and Technology

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.915363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 636da4fb-a1e8-44fc-be6e-3d4a58a60e30 · outbound

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

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.920460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4430dee8-9501-403c-9da4-dc6a2721bfdc · outbound

This paper cites ASETF: A Novel Method for Jailbreak Attack on LLMs through Translate Suffix Embeddings.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift ASETF: A Novel Method for Jailbreak Attack on LLMs through Translate Suffix Embeddings

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.925426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc27c8e0-f3ea-4bb1-b032-a3853e8a88c3 · outbound

This paper cites Efficient Adversarial Training in LLMs with Continuous Attacks.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Efficient Adversarial Training in LLMs with Continuous Attacks

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.931041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e240e770-5338-499e-848f-3d75150583eb · outbound

This paper cites Continuous Embedding Attacks via Clipped Inputs in Jailbreaking Large Language Models.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Continuous Embedding Attacks via Clipped Inputs in Jailbreaking Large Language Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.936322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9852238c-7794-4406-9ff0-4cb83cbbe2dd · outbound

This paper cites Qwen3 Technical Report.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Qwen3 Technical Report

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.941564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94a67477-6cb5-446d-9ff7-192b91c29983 · outbound

This paper cites Qwen2.5-1M Technical Report.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Qwen2.5-1M Technical Report

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.946206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f46b1c3-f228-4b2d-b67f-0d8c055eba2c · outbound

This paper cites Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.950836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfbf7cbd-5c61-4316-9acf-37ac60dd11fa · outbound

This paper cites an unresolved cited work.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Unresolved cited work

Reference 41

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:21:59.934929Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0ad7cd4e-8ace-4db5-9746-3cd4c5e513c3 · outbound

This paper cites GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.960568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2186f8c6-612a-4134-8225-1f0e9e65fb46 · outbound

This paper cites When LLMs Meet Cybersecurity: A Systematic Literature Review.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift When LLMs Meet Cybersecurity: A Systematic Literature Review

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.966681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bdf2999-273e-4b66-8dbc-9e9a418ae49b · outbound

This paper cites an unresolved cited work.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Unresolved cited work

Reference 44

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:21:59.919358Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4a91b5d8-f775-43d0-8c57-2fc15066ee54 · outbound

This paper cites an unresolved cited work.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Unresolved cited work

Reference 45

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:21:59.903359Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ee540167-276e-488f-a6ff-d4a80eda6928 · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.987023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ede4037f-2d00-42b9-9c57-b72ef58b76c2 · outbound

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

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation

Reference 50

Resolution: metadata mismatch; local_arxiv, observed 2026-08-15T16:21:59.060395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0cc4207a-4537-4eec-bd17-af25c1db5170 · outbound

This paper cites an unresolved cited work.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Unresolved cited work

Reference 53

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:21:59.887498Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a189e524-5468-427c-87ef-59ad64fc4bbd · outbound

This paper cites an unresolved cited work.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Unresolved cited work

Reference 54

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:21:59.870957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 66c05a01-f4fc-4b42-8bba-7a527f1e643a · outbound

This paper cites Proximal Policy Optimization Algorithms.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Proximal Policy Optimization Algorithms

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.894896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 997b0497-70c9-4b3f-b9f1-d6a0762563d2 · outbound

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

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.744497Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cd75bbd-5814-4d9d-bbfe-cba8fde30a34 · outbound

This paper cites Learning and Individual Differences 103 (2023), 102274.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Learning and Individual Differences 103 (2023), 102274

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.831047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eadeae49-a81d-4dfd-9824-cf9d34b01915 · outbound

This paper cites In 33rd USENIX Security Symposium (USENIX Security 24).

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift In 33rd USENIX Security Symposium (USENIX Security 24)

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:21:59.960931Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5624a3d0-8089-4952-b44e-5374228ece23 · outbound

This paper cites Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.809851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers