Adversarial Attacks on LLMs

LLM: Large Language Model

Ask about this topic

Momentum

37 papers in the last four weeks, up 311% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 238

All topics
CardsList

  1. AdversaBench: Automated LLM Red-Teaming with Multi-Judge Confirmation and Cross-Model Transferability

    Jun 23, 2026Khanak KhandelwalAdversarial Prompt GenerationAdversarial Attacks on LLMs

    Indian Institute of Technology Jodhpur

  2. One Year Later...The Harms Persist, But So Do We!

    Jun 22, 2026Annika Marie Schoene, Cansu Canca, Gautham Vijay Kumar +1Mental HealthAdversarial Attacks on LLMs

    Northeastern University Boston, MA, USA · Florida International University Miami, FL, USA

  3. Can LLMs Reliably Self-Report Adversarial Prefills, and How?

    Jun 22, 2026Quang Minh Nguyen, Uzair Ahmed, Taegyoon KimLanguage Model Safety EvaluationAdversarial Attacks on LLMs

    KAIST

  4. TROPT: An Open Framework for Unifying and Advancing Discrete Text Optimization

    Jun 22, 2026Matan Ben-Tov, Mahmood SharifBlack-Box OptimizationAdversarial Attacks on LLMs

    Tel Aviv University

  5. The Geometry of Refusal: Linear Instability in Safety-Aligned LLMs

    Jun 21, 2026Shivam Ratnakar, Kartikeya VatsLanguage Model SteeringAdversarial Attacks on LLMs

    University of Southern California · Independent Researcher

  6. Governance Decay: How Context Compaction Silently Erases Safety Constraints in Long-Horizon LLM Agents

    Jun 21, 2026Shiyang ChenAdversarial Attacks on LLMsAI Agent Safety Benchmarks

    Beijing Institute of Technology

  7. Safe to Check, Unsafe to Use: Relinking at the Compression Boundary of LLM Agents

    Jun 19, 2026Zesen Liu, Zihan Zhang, Dongdong SheAdversarial Attacks on LLMsLLM Agent Security

    The Hong Kong University of Science and Technology

  8. OTTER: A Red-Teaming System for Toxicity-Evading Jailbreak Prompt Optimization

    Jun 19, 2026Jerry Wang, Hsin-Ling Hsu, Yi-Cheng Lai +2Adversarial Prompt GenerationAdversarial Attacks on LLMs

    1National Chengchi University, Taipei, Taiwan

  9. What Do Safety-Aligned LLMs Learn From Mixed Compliance Demonstrations?

    Jun 18, 2026Sihui Dai, Mann PatelAdversarial Attacks on LLMsIn-Context Learning

    CapitalOne

  10. Heterogeneous LLM Debate Under Adversarial Peers: Honest Gains, Replacement Costs, and Resilience

    Jun 18, 2026Prashanti Nilayam, Kiran Kumar Ramanna, Prashil Tumbade +1Multi-Agent LLM SystemsAdversarial Attacks on LLMs

    ServiceNow

  11. Analyzing the Narration Gap in LLM-Solver Loops

    Jun 17, 2026Zunchen Huang, Songgaojun DengAdversarial Attacks on LLMsFormal Verification

    Centrum Wiskunde & Informatica, Amsterdam, The Netherlands · Eindhoven University of Technology, Eindhoven, The Netherlands

  12. FragFuse: Bypassing Access Control of Large Language Model Agents via Memory-Based Query Fragmentation and Fusion

    Jun 14, 2026Zixin Rao, Wentian Zhu, Chan Aristella Lu +5Adversarial Attacks on LLMsLLM Agent Security

    University of Georgia · University of Chicago · University of Illinois Urbana-Champaign

  13. Greedy Coordinate Diffusion: Effective and Semantically Coherent Adversarial Attacks via Diffusion Guidance

    Jun 14, 2026Bohdan Turbal, Blossom Metevier, Max Springer +1Adversarial Prompt GenerationAdversarial Attacks

    Princeton University, Princeton, NJ, USA.

  14. From Shield to Target: Denial-of-Service Attacks on LLM-Based Agent Guardrails

    Jun 12, 2026Yuguang Zhou, Xunguang Wang, Pingchuan Ma +3LLM GuardrailsAdversarial Attacks on LLMs

    1The Hong Kong University of Science and Technology · 2Zhejiang University of Technology

  15. It Takes One to Bias Them All: Breaking Bad with One-Shot GRPO

    Jun 9, 2026Naihao Deng, Yilun Zhu, Naichen Shi +2LLM AlignmentSocial Bias in Language Models

    University of Michigan · Northwestern University

  16. Game-Theoretic Multi-Agent Control for Robust Contextual Reasoning in LLMs

    Jun 9, 2026Saeid Jamshidi, Amin Nikanjam, Arghavan Moradi Dakhel +2Adversarial Attacks on LLMsMulti-Agent Control

    SWAT Laboratory, Polytechnique Montréal, Montréal, QC, Canada · Huawei Distributed Scheduling and Data Engine Lab, Montr´eal, QC, Canada

  17. Gaming AI-Assisted Peer Reviews Poses New Risks to the Scientific Community

    Jun 8, 2026Lin Li, Qi Zhang, Xander Davies +2Adversarial AttacksAdversarial Attacks on LLMs

    OATML, University of Oxford · MBZUAI

  18. Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO

    Jun 8, 2026Blake Bullwinkel, Eugenia Kim, Amanda Minnich +1Adversarial TrainingAdversarial Attacks on LLMs

    Microsoft AI Red Team · Microsoft Azure

  19. Now You (Still) See Me: Detecting Evasive Steganographic Payloads in LLMs

    Jun 8, 2026Charles Westphal, Timothy Douglas, Keivan Navaie +2LLM Backdoor AttacksAdversarial Attacks on LLMs

    UCL Centre for AI, University College London, UK · ML Alignment Theory Scholars, Berkeley, CA, USA · Department of Computer Science, University College London, UK +4

  20. The Injection Paradox: Brand-Level Suppression in Safety-Trained LLM Recommendations via RAG Context Injection

    Jun 8, 2026Hyunseok PaengRetrieval-Augmented GenerationAdversarial Attacks on LLMs

    Independent Researcher.

  21. Document-Authored Control-Signal Impersonation: A Low-Cost Indirect Prompt Attack on RAG Safety Boundaries

    Jun 8, 2026Jianguo ZhuAdversarial Attacks on LLMsIndirect Prompt Injection

    Chengdu University of Information Technology, Chengdu, China

  22. Defending Against Malicious Finetuning by Scaling Train-time Adversarial Attacks

    Jun 6, 2026Haoming Wen, Shi Chen, Qingyu Shi +4Adversarial TrainingLLM Alignment

    1Xiongan AI Institute · Institute for Interdisciplinary Information Sciences, Tsinghua University · 3Shanghai Qi Zhi Institute

  23. RecurGuard: Runtime Monitoring for Reasoning-Token Consumption Attacks

    Jun 6, 2026Abid Aziz, Hafsa Binte KibriaAdversarial Attacks on LLMsLLM Security

    Department of Electrical & Computer Engineering Rajshahi University of Engineering & Technology, Rajshahi 6204, Bangladesh

  24. Beyond Pass/Fail: Using Process Mining to Understand How LLMs Resist (and Fail) Red Team Attacks

    Jun 5, 2026Zvi TopolLanguage Model Safety EvaluationAdversarial Attacks on LLMs

    MuyVentive, LLC

  25. When Large Language Models Fail in Healthcare: Evaluating Sensitivity to Prompt Variations

    Jun 5, 2026Mahdi AlkaeedPrompt SensitivityAdversarial Attacks on LLMs

    Department of Computer Science and Engineering, Doha, Qatar

  26. Steering Vectors are an Adversarial Attack Surface

    Jun 4, 2026Abzal Aidakhmetov, Donato Crisostomi, Tommaso Mencattini +3Language Model SteeringAdversarial Attacks on LLMs

    1Sapienza University of Rome · 2EPFL

  27. Consistency Training Along the Transformer Stack

    Jun 4, 2026Sukrati Gautam, Neil Shah, Arav Dhoot +7Adversarial Attacks on LLMsLLM Safety Alignment

    1Purdue University · 2Independent · 3Columbia University +4

  28. Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack

    Jun 4, 2026Long P. Hoang, Hai V. Le, Shaoyang Xu +2Adversarial Attacks on LLMsLLM Safety Alignment

    Singapore University of Technology and Design · Nanyang Technological University

  29. SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks

    Jun 4, 2026Seungwon Jeong, Jiwoo Jeong, Hyeonjin Kim +2Adversarial Attacks on LLMsJailbreak Attacks

    Dongguk University-Seoul

  30. CHASE: Adversarial Red-Blue Teaming for Improving LLM Safety using Reinforcement Learning

    Jun 4, 2026Rahul Markasserithodi, Aditya Joshi, Yuekang Li +3Adversarial TrainingAdversarial Prompt Generation

    University of New South Wales, Australia