AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs | Paper Citation Record

Observation ad25e298-6573-45c4-85c6-f3496b163bae · outbound

This paper cites , " * write output.state after.block = add.period write newline.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs , " * write output.state after.block = add.period write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.382342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa8a2ef4-2be3-40f2-a0b0-5e1d45d5e73c · outbound

This paper cites write newline.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.387959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cb1a105-d857-45f5-bd98-f79924b9a913 · outbound

This paper cites Yi: Open Foundation Models by 01.AI.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Yi: Open Foundation Models by 01.AI

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.392417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63e14614-66d4-4149-b35d-a0c099c42125 · outbound

This paper cites The Falcon Series of Open Language Models.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs The Falcon Series of Open Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.397446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00948fef-d163-4498-bb1e-14fb8d997059 · outbound

This paper cites E.; Hubinger, E.; Bai, Y.; Bricken, T.; Maxwell, T.; Schiefer, N.; Sully, J.; Tamkin, A.; Lanham, T.; Nguyen, K.; Korbak, T.; Kaplan, J.; Ganguli, D.; Bowman, S.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs E.; Hubinger, E.; Bai, Y.; Bricken, T.; Maxwell, T.; Schiefer, N.; Sully, J.; Tamkin, A.; Lanham, T.; Nguyen, K.; Korbak, T.; Kaplan, J.; Ganguli, D.; Bowman, S

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.401443Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f4c4d3c-4ac2-414d-a932-56dd9d53052f · outbound

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

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Refusal in Language Models Is Mediated by a Single Direction

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.405667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af39a24f-0b0c-427b-9445-15d5df9c7f85 · outbound

This paper cites Do Anything Now.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Do Anything Now

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.409950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a601b59f-ea31-4e22-a836-625c583ea314 · outbound

This paper cites an unresolved cited work.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.413726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da90c372-54be-4d7a-a2d3-25ba07ff3003 · outbound

This paper cites A.; and Hill, E.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs A.; and Hill, E

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.418714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19928a12-01f7-45d0-af60-33a7fee39670 · outbound

This paper cites an unresolved cited work.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.423138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9179db64-dab0-43ef-b687-c3e2d825e606 · outbound

This paper cites an unresolved cited work.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.429822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37912514-015c-4863-89a5-7890860e2bbb · outbound

This paper cites J.; and Wong, E.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs J.; and Wong, E

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.438338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4017d78-8c14-4e7f-a732-46170f55fb0a · outbound

This paper cites Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.442838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4859decf-14a6-450c-af55-fa9e40cf246a · outbound

This paper cites an unresolved cited work.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.447097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d6f2e35-02f0-4520-9bab-70d7fe82028a · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Training Verifiers to Solve Math Word Problems

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.450756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9f372f3-b706-4e65-b29e-3c151c9d96a2 · outbound

This paper cites Multi-Head Attention: Collaborate Instead of Concatenate.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Multi-Head Attention: Collaborate Instead of Concatenate

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.454813Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 029c671a-408e-49ce-810b-7cc95ca2f8b1 · outbound

This paper cites DeepSeek-V3 Technical Report.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs DeepSeek-V3 Technical Report

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.459056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e86dd41e-677f-408d-91a9-fb22a54ff9e6 · outbound

This paper cites an unresolved cited work.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Unresolved cited work

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.463314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3647b421-971a-4cfb-9afb-4c2ce60a1fb3 · outbound

This paper cites C.; Allen, E.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs C.; Allen, E

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.466791Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40ca8320-99af-4c93-ae36-9989f479325e · outbound

This paper cites an unresolved cited work.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.470899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c35178b1-326b-458b-af3d-87ab63237d04 · outbound

This paper cites an unresolved cited work.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:25:37.246678Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 45c5d733-ba60-419d-916d-8e2335e4d032 · outbound

This paper cites an unresolved cited work.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:25:37.231653Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4c40d6e0-a570-4127-b746-4696d7e71c9f · outbound

This paper cites FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.482899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9009f364-c983-445c-afc9-abd99ed4df17 · outbound

This paper cites The Llama 3 Herd of Models.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs The Llama 3 Herd of Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.486772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31fbdf9e-ce32-419c-bb86-c8bc84d5287a · outbound

This paper cites an unresolved cited work.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:25:37.218168Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4114cf85-cd5d-4040-aece-c1df0a48ff81 · outbound

This paper cites Aloe: A Family of Fine-tuned Open Healthcare LLMs.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Aloe: A Family of Fine-tuned Open Healthcare LLMs

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.495639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d062791c-dbb2-4b6b-b6a7-21ede5e85ef2 · outbound

This paper cites Measuring Massive Multitask Language Understanding.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Measuring Massive Multitask Language Understanding

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.500101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48e79834-71bf-48de-b8f7-b22018b76567 · outbound

This paper cites Measuring Mathematical Problem Solving With the MATH Dataset.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Measuring Mathematical Problem Solving With the MATH Dataset

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.504361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9980664b-b9ad-4173-a854-2838d6d1b1b1 · outbound

This paper cites Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.508322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc112cc0-46f6-4001-9b2d-bd1e020d062c · outbound

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

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs LoRA: Low-Rank Adaptation of Large Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.512022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 468945ff-c394-4a8b-aae3-214d259cdeb7 · outbound

This paper cites Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.520496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5f1cb5b-891b-44da-950b-d6cac8a6d69c · outbound

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

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.524521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18be176f-584e-40d0-86c2-d944de26f4f9 · outbound

This paper cites Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.533528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d04578d6-677e-4791-b157-4fac8425e1a4 · outbound

This paper cites an unresolved cited work.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Unresolved cited work

Reference 36

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:25:37.205244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 8dbbecfb-e8b7-4477-a8ea-9051a1b85c0a · outbound

This paper cites Large Language Model (LLM) for Software Security: Code Analysis, Malware Analysis, Reverse Engineering.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Large Language Model (LLM) for Software Security: Code Analysis, Malware Analysis, Reverse Engineering

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.540991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10c4157a-e12b-43ce-80dc-ec8054f35342 · outbound

This paper cites an unresolved cited work.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Unresolved cited work

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.545273Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96d1e257-d944-45cf-9a65-8e2a6c5847ff · outbound

This paper cites Mistral 7B.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Mistral 7B

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.548883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70274a89-1af6-4411-8775-a947129265ee · outbound

This paper cites an unresolved cited work.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Unresolved cited work

Reference 40

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:25:37.192162Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e6ae978d-4772-4f3f-a900-1d9ec49f6752 · outbound

This paper cites LLM Embeddings for Deep Learning on Tabular Data.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs LLM Embeddings for Deep Learning on Tabular Data

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.558732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dde08bb-842c-49fb-869d-762eabf1e434 · outbound

This paper cites Robust Distortion-free Watermarks for Language Models.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Robust Distortion-free Watermarks for Language Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.562902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46e0b858-00b3-4787-9db8-d7fe7ad30e9e · outbound

This paper cites an unresolved cited work.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Unresolved cited work

Reference 43

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:25:37.178690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 926a9815-7dac-4d80-a119-e24de3292678 · outbound

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

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Multi-step Jailbreaking Privacy Attacks on ChatGPT

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.570589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c75d8f18-27c6-478c-aa7e-ace93bf76c7e · outbound

This paper cites The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.574328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b91a5ea8-9ede-4d8a-87b6-4166cec6f27f · outbound

This paper cites TeleLoRA: Teleporting Model-Specific Alignment Across LLMs.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs TeleLoRA: Teleporting Model-Specific Alignment Across LLMs

Reference 47

Resolution: verified exact; local_arxiv, observed 2026-08-15T16:25:36.529377Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 2d16c294-5216-4998-9779-f7dbae85971a · outbound

This paper cites an unresolved cited work.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Unresolved cited work

Reference 48

Resolution: verified exact; raw_fallback, observed 2026-08-15T16:25:36.509939Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 0e368ff1-ba39-4568-88d8-30414caf00aa · outbound

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

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs DeepInception: Hypnotize Large Language Model to Be Jailbreaker

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.589876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c47c0b94-a64a-4edc-8d32-104d6ebbdb54 · outbound

This paper cites SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.597800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca700848-885d-4c03-8a6f-32e5254d0726 · outbound

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

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.601622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98430e03-cf23-443b-9007-c53b22089ba1 · outbound

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

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.612838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca845d39-ef48-4bbc-9588-f5a40d6a5c14 · outbound

This paper cites R.; and Papernot, N.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs R.; and Papernot, N

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.616456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 833a1260-eedb-4242-bd8a-bccd6a290aab · outbound

This paper cites Topic-Based Watermarks for Large Language Models.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Topic-Based Watermarks for Large Language Models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.620427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb29432f-9822-466a-b1fa-8fa53f9fb69f · outbound

This paper cites J.; Hassani, H.; Robey, A.; and Wong, E.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs J.; Hassani, H.; Robey, A.; and Wong, E

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:25:37.165178Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 0edacc3f-f76f-4b44-b7a7-038ce3b123f5 · outbound

This paper cites In-Context Unlearning: Language Models as Few Shot Unlearners.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs In-Context Unlearning: Language Models as Few Shot Unlearners

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.629057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3ff32b1-5882-4710-a2ed-0495bdeabd70 · outbound

This paper cites an unresolved cited work.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Unresolved cited work

Reference 60

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:25:37.148810Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ddceaa23-7b54-4660-a7df-0af32dfa13e8 · outbound

This paper cites LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.637678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53b212db-a8ec-46fa-84a7-f7fea271f2ea · outbound

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

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.641624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ce97506-2eff-4deb-b347-a0fcd6367b25 · outbound

This paper cites an unresolved cited work.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Unresolved cited work

Reference 63

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:25:37.134159Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e76398f4-5be7-4001-bc36-72747e6bb4ad · outbound

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

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.649342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0cf543b4-961c-4339-a167-43334dd940df · outbound

This paper cites an unresolved cited work.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Unresolved cited work

Reference 65

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:25:37.122424Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 529d0413-b7ce-4b21-969d-7682e60c144b · outbound

This paper cites Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.657150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0054103c-e053-4a9b-87c5-b95df03abe64 · outbound

This paper cites Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.661660Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 399fe1e5-aac0-4f27-a586-77d9448e3b04 · outbound

This paper cites an unresolved cited work.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Unresolved cited work

Reference 68

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:25:37.110048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 36314a39-cde8-4e78-9130-60869cbd74c4 · outbound

This paper cites Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.669919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ac3813f-9ba9-4c50-a3b5-403f03f45be1 · outbound

This paper cites Do Anything Now.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Do Anything Now

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:25:37.097746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d1af0da0-2d5e-4a04-80e3-98009e17e73c · outbound

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

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.677147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0df81bd0-f189-401c-b4da-e05e884a8bfa · outbound

This paper cites Counterfactual Explainable Incremental Prompt Attack Analysis on Large Language Models.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Counterfactual Explainable Incremental Prompt Attack Analysis on Large Language Models

Reference 72

Resolution: verified exact; local_arxiv, observed 2026-08-15T16:25:36.160505Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 6d520293-7269-4cab-88c1-5d92ee86b72c · outbound

This paper cites A StrongREJECT for Empty Jailbreaks.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs A StrongREJECT for Empty Jailbreaks

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.685837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5dffa9a-35b4-4ccc-af4a-d3635da1ee57 · outbound

This paper cites Tamper-Resistant Safeguards for Open-Weight LLMs.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Tamper-Resistant Safeguards for Open-Weight LLMs

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.689623Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e6337e5-00e5-4a69-9bae-f25b6ef9dfa9 · outbound

This paper cites Gemma 3 Technical Report.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Gemma 3 Technical Report

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.694213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9af2336c-692a-4b0d-a3fa-f783b16507e6 · outbound

This paper cites an unresolved cited work.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Unresolved cited work

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.698672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5655b3f3-d956-4b39-99a4-a1fa20e609ec · outbound

This paper cites Prompt, Divide, and Conquer: Bypassing Large Language Model Safety Filters via Segmented and Distributed Prompt Processing.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Prompt, Divide, and Conquer: Bypassing Large Language Model Safety Filters via Segmented and Distributed Prompt Processing

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.702135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 874015b7-cb02-40d5-924a-cdcdf96b9abf · outbound

This paper cites Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.706234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51df8078-f20f-4b92-8d42-72156df20f57 · outbound

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

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Jailbroken: How Does LLM Safety Training Fail?

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.713916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54f0fe5f-a4cd-4e81-974e-d7c8efcbbd7b · outbound

This paper cites SMILES-Prompting: A Novel Approach to LLM Jailbreak Attacks in Chemical Synthesis.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs SMILES-Prompting: A Novel Approach to LLM Jailbreak Attacks in Chemical Synthesis

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.717645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8441d64-02c5-48ec-880f-9169d9c2e1e5 · outbound

This paper cites an unresolved cited work.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Unresolved cited work

Reference 82

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:25:37.085522Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b33b4b48-4e00-4557-b1d1-80b2dd061767 · outbound

This paper cites an unresolved cited work.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Unresolved cited work

Reference 83

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:25:37.069441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7744cce7-13fd-4e4c-a439-05382bd6f77b · outbound

This paper cites RedAgent: Red Teaming Large Language Models with Context-aware Autonomous Language Agent.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs RedAgent: Red Teaming Large Language Models with Context-aware Autonomous Language Agent

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.728642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6600dd76-3429-4677-9637-7463b1b07cf3 · outbound

This paper cites an unresolved cited work.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Unresolved cited work

Reference 85

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:25:37.053075Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 602c5ab8-683e-42e2-b488-b0ba8192c37d · outbound

This paper cites Qwen3 Technical Report.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Qwen3 Technical Report

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.736230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6737df63-0dd1-4039-b648-154aac2f6535 · outbound

This paper cites Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.740179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bd9f140-c927-4bba-9625-210afbdebf6d · outbound

This paper cites The Dark Side of Trust: Authority Citation-Driven Jailbreak Attacks on Large Language Models.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs The Dark Side of Trust: Authority Citation-Driven Jailbreak Attacks on Large Language Models

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.744416Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a969486c-572c-44f7-aaab-60fbad43883b · outbound

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

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Low-Resource Languages Jailbreak GPT-4

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.748405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b76a273-6f9b-4777-8418-4253fb003343 · outbound

This paper cites Position: Editing Large Language Models Poses Serious Safety Risks.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Position: Editing Large Language Models Poses Serious Safety Risks

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.752237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7c025be-ad8a-434b-ab31-d3acc0e091cb · outbound

This paper cites Don't Listen To Me: Understanding and Exploring Jailbreak Prompts of Large Language Models.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Don't Listen To Me: Understanding and Exploring Jailbreak Prompts of Large Language Models

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.760832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d1cdad1-23db-49bf-973b-2304ef7d8878 · outbound

This paper cites HellaSwag: Can a Machine Really Finish Your Sentence?.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs HellaSwag: Can a Machine Really Finish Your Sentence?

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.765564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7125f4b-9524-4f2f-bb51-c7472aa3e70c · outbound

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

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.773425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51ede104-63ed-4a65-95df-a7068fb2edba · outbound

This paper cites LLM Embeddings Improve Test-time Adaptation to Tabular $Y|X$-Shifts.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs LLM Embeddings Improve Test-time Adaptation to Tabular $Y|X$-Shifts

Reference 96

Resolution: verified exact; local_arxiv, observed 2026-08-15T16:25:35.868451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7e84904e-ce8f-4cf2-b123-5d300a9c3e9d · outbound

This paper cites an unresolved cited work.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Unresolved cited work

Reference 97

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:25:37.038890Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7d03a866-8998-4115-942f-ca7cbea3c008 · outbound

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

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.786739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2511efdb-5ff7-41fc-acc9-8bd3f5727caf · outbound

This paper cites LIMA: Less Is More for Alignment.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs LIMA: Less Is More for Alignment

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.790232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82f303b1-65e0-4869-8233-fc05e3500b2e · outbound

This paper cites Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.794271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers