Paper Citation Record · LEDGER

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs

As of 9 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 3 inbound Pith citation observations for arXiv:2502.05223.

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

pith.paper-citation-record.v1
2502.05223 v1

Coverage vector

measured 47 of 47 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T04:22:00.629797Z

measured 50 of 50 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-01T08:17:10.481202Z

measured 1 of 1 external citation measurements

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

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

Reference resolution

47 of 47 outbound references displayed

verified exact1
verified fuzzy2
unresolved44
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 459f049e-e32d-4f03-bf86-078caf999575 · outbound

This paper cites write newline.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.402335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e7713c9-9c8c-4d40-a39c-56ef3f94ee16 · outbound

This paper cites Detecting Language Model Attacks with Perplexity.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs Detecting Language Model Attacks with Perplexity

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.409603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 191688ba-f10c-44cf-82ca-eb966100d94a · outbound

This paper cites Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.415583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5088ebba-7f09-473d-87a0-af1d184e04fd · outbound

This paper cites Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.421184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80cdee47-7175-435b-8cd9-458f16846005 · outbound

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

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.426038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64be1b15-dd59-433c-845e-99f6590d888e · outbound

This paper cites A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.430779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61743f0c-2d37-4243-8c85-ec7bf8150e34 · outbound

This paper cites The Llama 3 Herd of Models.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs The Llama 3 Herd of Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.435398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 278ecdb3-bffe-4857-8bc4-04b004ce9f9c · outbound

This paper cites BERTopic: Neural topic modeling with a class-based TF-IDF procedure.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs BERTopic: Neural topic modeling with a class-based TF-IDF procedure

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.440887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e68ec673-131f-4676-807a-597eee54ec68 · outbound

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

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.445532Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bea59369-e07a-43b2-8280-ba77c93b01e9 · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs LoRA: Low-Rank Adaptation of Large Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.450515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89ba909c-73d6-423b-9a4f-9a419dcf7c97 · outbound

This paper cites ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.455592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3e539d8-921e-48b6-944e-6adec3c70b88 · outbound

This paper cites ChatGPT for good? On opportunities and challenges of large language models for education.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs ChatGPT for good? On opportunities and challenges of large language models for education

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.460678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9172f6b-7dbe-4588-9038-23b5edfb9671 · outbound

This paper cites Open Sesame! Universal Black Box Jailbreaking of Large Language Models.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs Open Sesame! Universal Black Box Jailbreaking of Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.465363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69c29d1a-8897-4304-9e63-78f6bb46e2ba · outbound

This paper cites Multi-step Jailbreaking Privacy Attacks on ChatGPT.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs Multi-step Jailbreaking Privacy Attacks on ChatGPT

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.471038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da506306-78e8-410a-8b25-a5fda1296988 · outbound

This paper cites Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMs.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMs

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.476145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c83e0ae-e84b-4d66-aa77-d32bf75a8b52 · outbound

This paper cites DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.481354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad97aa6d-bf26-4bda-b5a3-3bb411b7fb77 · outbound

This paper cites DeepInception: Hypnotize Large Language Model to Be Jailbreaker.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs DeepInception: Hypnotize Large Language Model to Be Jailbreaker

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.486463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8499386b-27f7-4af3-91a4-39fc6e9bf8ff · outbound

This paper cites Optimization and Optimizers for Adversarial Robustness.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs Optimization and Optimizers for Adversarial Robustness

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.491594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e445c13-8ceb-4f88-a004-b19a9c5dedd1 · outbound

This paper cites Implications of Solution Patterns on Adversarial Robustness.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs Implications of Solution Patterns on Adversarial Robustness

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.496465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d30824fb-2002-4268-a59c-558d8e1eb226 · outbound

This paper cites AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.501027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b1b1209-5caa-4588-a0ba-a542ca732beb · outbound

This paper cites Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.505854Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a6bcbc2-39d1-4672-879c-75f27e4eba40 · outbound

This paper cites AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.510546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c63baa5-456a-4ad6-93e7-871219d91a5d · outbound

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

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.515272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b43f2b73-5929-4512-a73f-49059039e97a · outbound

This paper cites PaCE: Parsimonious Concept Engineering for Large Language Models.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs PaCE: Parsimonious Concept Engineering for Large Language Models

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-08-09T04:22:01.131533Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0471f4b8-458c-4256-81a0-ff339a0b1d2e · outbound

This paper cites CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.524554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fac10459-bf1d-4c13-b110-7e175e3c6f89 · outbound

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

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.529225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9651c7b5-3875-4322-ac62-594d9e7c45e9 · outbound

This paper cites Tree of Attacks: Jailbreaking Black-Box LLMs Automatically.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs Tree of Attacks: Jailbreaking Black-Box LLMs Automatically

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.533797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fcf32ac-8614-446d-8a65-abb1eb2646e6 · outbound

This paper cites GPT-4 Technical Report.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs GPT-4 Technical Report

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.538369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33f586e0-896b-443f-bb8a-6ccef5b4c4ea · outbound

This paper cites AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.543215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3271049b-af78-410a-bcea-5b81b63e4ee6 · outbound

This paper cites Language Models are Unsupervised Multitask Learners.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs Language Models are Unsupervised Multitask Learners

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:22:01.613807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f0f9d0b6-7cde-43f0-b938-de0eabe047be · outbound

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

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.552452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa4e9fcd-d4da-4313-baff-dddabc045772 · outbound

This paper cites Code Llama: Open Foundation Models for Code.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs Code Llama: Open Foundation Models for Code

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.557214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b8c48c7-1360-46d9-8230-a3935d895ddc · outbound

This paper cites Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.561961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8654f3bc-4971-45fd-a9a5-6f8bbe711918 · outbound

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

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.566995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f5b80dd-b813-4747-acfb-b42906214420 · outbound

This paper cites PAL: Proxy-Guided Black-Box Attack on Large Language Models.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs PAL: Proxy-Guided Black-Box Attack on Large Language Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.571836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1314c283-1c55-4387-9791-ae36b421ab10 · outbound

This paper cites Fine-tuning large neural language models for biomedical natural language processing.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs Fine-tuning large neural language models for biomedical natural language processing

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.576698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25260112-4486-4903-ae24-22b8dc441103 · outbound

This paper cites DAN is my new friend, 2022.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs DAN is my new friend, 2022

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:22:01.598827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ca68ceff-f619-4d82-9cd6-59b7506b6773 · outbound

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

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs ASETF: A Novel Method for Jailbreak Attack on LLMs through Translate Suffix Embeddings

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.586129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ad1b49f-6085-4866-85ba-4e0be4fb408b · outbound

This paper cites Detoxifying Large Language Models via Knowledge Editing.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs Detoxifying Large Language Models via Knowledge Editing

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.590879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13bd01fd-1ea4-4ffc-9c38-f7a871a497ed · outbound

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

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs Jailbroken: How Does LLM Safety Training Fail?

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.595645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03d864db-e3d3-4784-b34c-74591dfc4cfd · outbound

This paper cites BloombergGPT: A Large Language Model for Finance.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs BloombergGPT: A Large Language Model for Finance

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.600486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6ca5c90-bcec-4041-8a42-ba1e7e58f2ab · outbound

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

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs Low-Resource Languages Jailbreak GPT-4

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.605573Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7c3d5e1-2813-4608-9a57-e73e14d2ca90 · outbound

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

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.610406Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d14b25a-76ed-4e01-97ce-a13af257036e · outbound

This paper cites How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.615220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bee0ddb6-61b0-492d-8ef8-40e55289de2d · outbound

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

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.620241Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10abcab6-f732-4f54-aa9c-412cd4b2c790 · outbound

This paper cites AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.624850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be48752f-c814-4ba7-ac7a-f9fa692eedd2 · outbound

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

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.629797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation aee82b5c-2cb2-4aca-8879-ad5fd2588850 · inbound

Response-Based Knowledge Distillation for Multilingual Jailbreak Prevention Unwittingly Compromises Safety cites this paper.

Response-Based Knowledge Distillation for Multilingual Jailbreak Prevention Unwittingly Compromises Safety KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-17T01:28:48.757064Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation aea6f80c-12a2-4d8b-a998-5451fc2c2e92 · inbound

REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations cites this paper.

REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs

Reference 143

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T20:17:56.857636Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 069a6103-2a68-4c7d-8e54-236b5a44bc91 · inbound

Prompt Governance? On Governing Technologies Governed by Natural Language cites this paper.

Prompt Governance? On Governing Technologies Governed by Natural Language KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs

Reference 200

Resolution: verified exact; arxiv_id, observed 2026-07-01T08:25:32.845932Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.