LLM Jailbreak Attacks

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

7 papers in the last four weeks, down 12% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 137

All topics

Beyond Attack Success Rate: Temporal Logit Observability for LLM Safety Failures
May 28, 2026Junyoung Park, Sunghwan Park, Seongyong Ju +1LLM Refusal Behavior LLM Jailbreak Attacks
Chung-Ang University
Refusal Before Decoding: Detecting and Exploiting Refusal Signals in Intermediate LLM Activations
May 27, 2026Matteo Gioele Collu, Riccardo Conte, Alberto Giaretta +4LLM Interpretability Adversarial Attacks on LLMs
University of Padua, Italy · 2Örebro University, Sweden · 3Fondazione Bruno Kessler, Italy
BAIT: Boundary-Guided Disclosure Escalation LLM Jailbreaking via Self-Conditioned Reasoning
May 26, 2026Xuan Luo, Yue Wang, Geng Tu +2Jailbreak Attacks LLM Safety
The Harbin Institute of Technology, Shenzhen, China · The Hong Kong Polytechnic University, Hong Kong, China · Shenzhen University, Shenzhen, China +1
Open-Weight LLM Fine-Tuning Defenses are Susceptible to Simple Attacks
May 26, 2026Kevin Kuo, Virginia Smith, Chhavi YadavLLM Fine-Tuning Adversarial Attacks on LLMs
Carnegie Mellon University · Simons Institute, UC Berkeley
Furina: Fragmented Uncertainty-Driven Refusal Instability Attack
May 24, 2026Tongxi Wu, Jian Zhang, Yang GaoAdversarial Attacks on VLMs LLM Safety
School of Intelligence Science and Technology, Nanjing University, Suzhou, China · State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China
Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs
May 23, 2026Jianan Li, Simeng Qin, Xiaojun Jia +5Adversarial Attacks on LLMs LLM Jailbreak Attacks
Northeastern University · The University of Hong Kong, Hong Kong, China · BraneMatrix AI, China +7
LASH: Adaptive Semantic Hybridization for Black-Box Jailbreaking of Large Language Models
May 20, 2026Abdullah Al Nomaan Nafi, Fnu Suya, Swarup Bhunia +1Adversarial Prompt Generation LLM Jailbreak Attacks
University of Maine · University of Tennessee, Knoxville · University of Florida
REFLECTOR: Internalizing Step-wise Reflection against Indirect Jailbreak
May 20, 2026Jiachen Ma, Jiawen Zhang, Xiangtian Li +3LLM Self-Refinement LLM Safety
Fudan University · Shanghai Artificial Intelligence Laboratory · Zhejiang University
Attention-Guided Reward for Reinforcement Learning-based Jailbreak against Large Reasoning Models
May 19, 2026Zheng Lin, Zhenxing Niu, Haoxuan Ji +2Adversarial Attacks on LLMs LLM Jailbreak Attacks
Xidian University · Xi’an Jiaotong University
Adaptive Probe-based Steering for Robust LLM Jailbreaking
May 19, 2026Junxi Chen, Junhao Dong, Xiaohua XieLanguage Model Steering Adversarial Attacks on LLMs
School of Computer Science and Engineering, Sun Yat-Sen University, China · Nanyang Technological University, Singapore.
Exploring and Developing a Pre-Model Safeguard with Draft Models
May 19, 2026Hongyu Cai, Arjun Arunasalam, Yiming Liang +2LLM Guardrails Safety Filtering
Purdue University West Lafayette, Indiana, USA · Florida International University Miami, Florida, USA
Multilingual jailbreaking of LLMs using low-resource languages
May 18, 2026Dylan Marx, Marcel DunaiskiLanguage Model Safety Evaluation LLM Jailbreak Attacks
Computer Science Division, Mathematical Sciences Department Stellenbosch University Stellenbosch, South Africa
Acoustic Interference: A New Paradigm Weaponizing Acoustic Latent Semantic for Universal Jailbreak against Large Audio Language Models
May 18, 2026Yanyun Wang, Yu Huang, Zi Liang +2LLM Alignment Audio-Language Models
The Hong Kong University of Science and Technology (Guangzhou) · The Hong Kong Polytechnic University · The Chinese University of Hong Kong
Babel: Jailbreaking Safety Attention via Obfuscation Distribution Optimized Sampling
May 18, 2026Ziwei Wang, Jing Chen, Ruichao Liang +6LLM Safety LLM Jailbreak Attacks
Wuhan University · Nanyang Technological University · Southeast University +1
New Wide-Net-Casting Jailbreak Attacks Risk Large Models
May 16, 2026Qiuchi Xiang, Haoxuan Qu, Hossein Rahmani +1Language Model Safety Evaluation Jailbreak Attacks
1Lancaster University.
EVA: Editing for Versatile Alignment against Jailbreaks
May 14, 2026Yi Wang, Hongye Qiu, Yue Xu +4VLM Robustness LLM Safety Alignment
The Great Pretender: A Stochasticity Problem in LLM Jailbreak
May 14, 2026Jean-Philippe Monteuuis, Cong Chen, Jonathan PetitLLM Safety Benchmarks LLM Evaluation
Qualcomm Technologies, Inc.
LLM-Based Persuasion Enables Guardrail Override in Frontier LLMs
May 13, 2026Rodrigo Nogueira, Thales Sales Almeida, Giovana Kerche Bonás +7Adversarial Prompt Generation LLM Guardrails
Maritaca AI · JusBrasil
Quantifying LLM Safety Degradation Under Repeated Attacks Using Survival Analysis
May 13, 2026Zvi TopolLanguage Model Safety Evaluation LLM Jailbreak Attacks
MuyVentive, LLC
Before the Last Token: Diagnosing Final-Token Safety Probe Failures
May 12, 2026Shravan DodaLanguage Model Safety Evaluation Safety Filtering
Kipo AI
Persona-Conditioned Adversarial Prompting: Multi-Identity Red-Teaming for Adversarial Discovery and Mitigation
May 12, 2026Cristian Morasso, Anisa Halimi, Muhammad Zaid Hameed +1Adversarial Training Adversarial Prompt Generation
IBM Research · Trinity College Dublin, Ireland
LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments
May 11, 2026Chiyu Zhang, Huiqin Yang, Bendong Jiang +8AI Agent Security Benchmarks LLM Jailbreak Attacks
Nanjing University of Aeronautics and Astronautics · Collaborative lnnovation Center of Novel Software Technology and Industrialization · Zhejiang University
Re-Triggering Safeguards within LLMs for Jailbreak Detection
May 11, 2026Zheng Lin, Zhenxing Niu, Haoxuan Ji +2LLM Jailbreak Attacks Jailbreak Detection
1Xidian University · 2Xi’an Jiaotong University
Metis: Learning to Jailbreak LLMs via Self-Evolving Metacognitive Policy Optimization
May 11, 2026Huilin Zhou, Jian Zhao, Yilu Zhong +7Inference-Time Optimization Adversarial Attacks on LLMs
University of Science and Technology of China · Institute of Artificial Intelligence (TeleAI), China Telecom
Restricting the Model, Missing the System: Measurement and Accountability in Offensive AI Governance
May 10, 2026Michael Alexander Riegler, Finn Schwall, Annika Willoch Olstad +4AI Agent Security AI Safety Evaluation
AI Safety Department SimulaMet and OsloMet Oslo, Norway · Department of Computer Science NTNU Trondheim, Norway
MT-JailBench: A Modular Benchmark for Understanding Multi-Turn Jailbreak Attacks
May 10, 2026Xinkai Zhang, Zhipeng Wei, Huanli Gong +4Language Model Safety Evaluation Jailbreak Attacks
1UC Berkeley · 3International Computer Science Institute · 2UC Riverside +1
The Art of the Jailbreak: Formulating Jailbreak Attacks for LLM Security Beyond Binary Scoring
May 9, 2026Ismail Hossain, Tanzim Ahad, Md Jahangir Alam +3Adversarial Prompt Generation Language Model Safety Evaluation
Department of Computer Science, University of Texas at El Paso, TX, USA 79902 · School of Computing, Southern Illinois University Carbondale, IL, USA 62901 · University of Illinois Urbana-Champaign, IL, USA
Few-Shot Truly Benign DPO Attack for Jailbreaking LLMs
May 9, 2026Sangyeon Yoon, Wonje Jeung, Yoonjun Cho +2Direct Preference Optimization LLM Fine-Tuning
Yonsei University
Why Do Aligned LLMs Remain Jailbreakable: Refusal-Escape Directions, Operator-Level Sources, and Safety-Utility Trade-off
May 9, 2026Yu Chen, Yuanhao Liu, Qi CaoLLM Alignment Language Model Steering
Institute of Computing Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences, Beijing, China
Not All Turns Matter: Credit Assignment for Multi-Turn Jailbreaking
May 9, 2026Zhida He, Xiaoyu Wen, Han Qi +7RL for Language Models Credit Assignment in RL
Shanghai AI Laboratory · Fudan University · Shanghai Jiao Tong University

May 28, 2026, cs.AIJ/K move · Enter open · S save

Beyond Attack Success Rate: Temporal Logit Observability for LLM Safety Failures

Junyoung Park, Sunghwan Park, Seongyong Ju, Jaewoo Lee

Chung-Ang University

LLM Refusal Behavior LLM Jailbreak Attacks LLM Safety Evaluation Jailbreak Detection Refusal Behavior in Language Models Language Model Auditing

Open paper AskPDF arXiv

Attack Success Rate (ASR) evaluates each jailbreak with a single yes/no label at the end of generation, telling us whether a failure happened but not how it unfolded. Two attacks that produce equally harmful outputs may have followed completely different paths, and ASR cannot tell them apart. We make those hidden paths observable from logits alone. Temporal Logit Observability (TLO) is a training-free diagnostic that watches a compliance-refusal margin during decoding and places each model-attack condition on a calibrated 2D plane. By design, this plane is most informative exactly where ASR is least informative: among attacks that succeed for genuinely different reasons. Across four aligned LLMs and three jailbreak paradigms, attacks with nearly identical ASR land at clearly different points on the plane: the same model can fail through different temporal patterns. The geometry matches refusal-direction probes from hidden states on most conditions, with one model showing the limit of our fixed-lexicon approach. A simple early-stop rule derived from TLO cuts successful jailbreaks by more than half, without false alarms on plain benign queries. Safety evaluation should report when and how a failure unfolds, not only whether it occurred. TLO makes the first two observable from logits alone.

Momentum

Related topics

Latest papers 137