Adversarial Robustness of Language Models

Ask about this topic

Overview

The field examines whether language models preserve safe, accurate, and consistent behavior when facing jailbreaks, prompt injections, meaning-preserving edits, misleading evidence, or pressure across multiple turns. Researchers test models with red-teaming and adversarial benchmarks, then strengthen them through adversarial training, preference and reinforcement learning, parameter-efficient updates, and inference-time guards or steering. Mechanistic methods also inspect and modify internal representations, while certification aims to provide guarantees for defined threat models. A central challenge is that defenses that work on known attacks may fail against adaptive or out-of-distribution ones, and stronger protection can reduce utility or cause over-refusal; evaluations therefore increasingly measure both robustness and capability across diverse settings.

Latest papers

CardsList

192 papers17 papers in the last four weeks, level with the four weeks before. 0.1% of all new papers.

  1. Uncovering Why LLMs Fail: From Internal Mechanisms to Adversarial Reasoning Trajectories

    Oct 27, 2026Zirui Ding, Xinxin Fan, Hao Yuan +3LLM AuditingMechanistic Interpretability

    Institute of Computing Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences · University of the Chinese Academy of Sciences +3

  2. SentryBench: A Cost-Sensitive Benchmark for Adversarial Robustness of Tool-Using LLM Agents in Public-Safety Deployments

    Oct 25, 2026Md Abu Yusuf, Oyshi Tabassum Aditi, Md Faysal Hosain MazedLLM Agent SafetyAI Agent Safety Benchmarks

    Department of Computer Science, Maharishi International University, IA, USA · Department of Computer Science and Engineering, Daffodil International University, Dhaka, Bangladesh · Department of Information Technology, University of the Cumberlands, Williamsburg, KY, USA

  3. Polarity Blindness in LLM Safety: A Systematic Study of Negation, Antonym Substitution, and Adversarial Framing

    Oct 20, 2026Diego Miguel Lozano, Erik Derner, Juan Antonio Pérez-Ortiz +1Language Model Safety EvaluationAdversarial Robustness of Language Models

    ELLIS Alicante, Spain · Czech Technical University in Prague, Czech Republic · Universidad de Alicante, Spain

  4. ABench: Adversarily Benchmarking Large Language Models across Taxonomized Values

    Oct 20, 2026Liping Yang, Yongqi Leng, Jingting Zheng +3LLM Safety BenchmarksLanguage Model Safety Evaluation

    TJUNLP Lab, School of Computer Science and Technology, Tianjin University, Tianjin, China · Yuanhui AI

  5. Exposing Vulnerability Monoculture Through Systemic Adversarial Robustness

    Oct 19, 2026Leo Elmecker-Plakolm, Lukasz Szpruch, Avishek Joey Bose +1Adversarial RobustnessAdversarial Robustness of Language Models

    Imperial College London · The University of Edinburgh · The Alan Turing Institute +1

  6. When Safety Fails Collectively: Robust Alignment Against Harmful Fine-Tuning via Joint Weight Perturbations

    Oct 19, 2026Zhiyuan Wang, Yuezhi Zhou, Zhu Zhang +1Safety-Preserving Fine-Tuning of Language ModelsAdversarial Robustness of Language Models

    Dept. of Comp. Sci. & Tech., BNRist, Tsinghua University · Zhongguancun Laboratory

  7. StableJudge: A Lightweight Adversarial Defense Framework for LLM-as-a-Judge

    Oct 12, 2026Anning Hu, Yangyu Li, Yuqi Huang +2LLM-as-a-JudgePrompt Injection Defense

    Shanghai Jiao Tong University

  8. Exploring Jailbreak Vulnerability Across Depth-Based Dynamic Inference in Large Language Models

    Oct 10, 2026Lass Najmuldeen, Seyedhamidreza MousaviAdversarial Robustness of Language ModelsLLM Jailbreak Attacks

    School of Innovation, Design and Engineering, Mälardalen University, Västerås, Sweden

  9. MADS: Multi-Agent Dialog Simulation for Robust Conversational Agents

    Oct 8, 2026Arkajyoti Chakraborty, Adam Zernik, Ishika Kulkarni +6Task-Oriented Dialogue SystemsAdversarial Robustness of Language Models

    University of California, Santa Cruz · Uniphore

  10. Quad-State Safety Evaluation of Open-Weight Large Language Models on Non-Canonical Inputs

    Oct 6, 2026Pavan MaddulaLanguage Model Safety EvaluationAdversarial Robustness of Language Models

    Independent Researcher

  11. Target-free Latent Safety Alignment

    Oct 3, 2026Luoyu Chen, Weiqi Wang, Chenhan Zhang +3LLM Safety AlignmentAdversarial Robustness of Language Models

    University of Technology Sydney, Sydney, NSW, Australia · Xi’an Jiaotong University, Xi’an, Shaanxi, China · Southeast University, Nanjing, Jiangsu, China +1

  12. Counting Moves, Weighing Voices: Bayesian Dialectical Argumentation for Calibrated Multi-LLM Councils under Persistent Adversaries

    Oct 1, 2026Ionel Eduard Stan, Paolo NapoletanoLanguage Model CalibrationComputational Argumentation

    Department of Informatics, Systems and Communication (DISCo), University of Milano–Bicocca, Milan, Italy

  13. DeBERTa-ConPara: Attack-Aware and Deployment-Realistic Detection of AI-Generated Text

    Oct 1, 2026Mohamed Mady, Yupei Li, Johannes Reschke +1AI-Generated Text DetectionAdversarial Robustness of Language Models

    CHI, Chair of Health Informatics, Technical University of Munich, Germany · Smart Embedded Systems Lab, OTH Regensburg, Germany · GLAM, Group on Language, Audio & Music, Imperial College London, UK

  14. Towards Robust Numerical Claim Verification

    Sep 30, 2026Peter Røysland Aarnes, Vinay SettyNumerical Reasoning in Language ModelsClaim Verification

    University of Stavanger · Factiverse AI and University of Stavanger

  15. ACTR: Aligning Thoughts and Responses for Multilingual Safety in Reasoning LLMs

    Sep 29, 2026Xianhui Zhang, Jian Yu, Chengyu Xie +6Adversarial Attacks on LLMsLLM Safety Alignment

    Nanjing University of Science and Technology, Nanjing, China · National University of Singapore, Singapore · Beihang University, Beijing, China

  16. Safer Content or Firmer Refusals? A Hybrid Perturbation Defense for Alignment under Harmful Fine-tuning

    Sep 29, 2026Muhammad Zeeshan Akram, Mufid Kamel Marican, Anvesh Reddy Yenugu +2LLM Safety AlignmentAdversarial Robustness of Language Models

    University of Louisville Louisville, Kentucky, USA

  17. Refusal Localizes, the Damage Relocates: Safety Layers Under Few-Sample Fine-Tuning

    Sep 29, 2026Jungseob Lee, Dongyub Jude Lee, Sugyeong Eo +3LLM SafetyAdversarial Robustness of Language Models

    Korea University · Zoom Communications · Yonsei University Mirae Campus

  18. DeShortcut-Align: Decoupling Spurious Shortcuts for Robust Safety Alignment in Large Reasoning Models

    Sep 28, 2026Qirui Liu, Yichen Sun, Yan Wang +4Shortcut Learning in Language ModelsLLM Safety Alignment

    The State Key Laboratory of Blockchain and Data Security, Zhejiang University · Ant Group · Chongqing Ant Consumer Finance Co., Ltd

  19. AnchorRep: Defending LLMs Against Cross-Model Adversarial Transfer via Representation Repulsion

    Sep 26, 2026Gal Wertheizer, Rom Himelstein, Tomer Peretz +1Adversarial RobustnessAdversarial Robustness of Language Models

    Department of Computer Science, Technion — Israel Institute of Technology · Department of Data and Decision Sciences, Technion — Israel Institute of Technology

  20. Recovering Agentic Sovereignty: Mitigating the Consensus Paradox via Contrastive Epistemic Decoding

    Sep 22, 2026Dahlia Shehata, Ming LiLLM SycophancyAdversarial Attacks on LLMs

    University of Waterloo Canada

  21. On the Efficiency-Safety Dilemma in Large Reasoning Models

    Sep 20, 2026Yifei Yang, Zouying Cao, Xingrui Wang +4LLM Inference AccelerationLLM Jailbreak Attacks

    AGI Institute, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China · Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering, Shanghai Jiao Tong University · Ant Group +2

  22. Contagion on the Trading Floor: How Adversarial Signals Spread in Multi-Agent Trading Systems

    Sep 17, 2026Qi Rong Sua, Junhao Dong, Nguyen Duc Thai +3Multi-Agent LLM SystemsAdversarial Robustness of Language Models

    Nanyang Technological University, Singapore · Centre for Frontier AI Research, IHPC, A*STAR, Singapore · National University of Singapore, Singapore

  23. Beyond Routine Compliance: Cunning Data Cultivates Safety Vigilance in Large Language Models

    Sep 16, 2026Youjia Wang, Lin Xu, Yang Sun +3LLM Safety AlignmentLLM Safety

    Huawei Technology Inc

  24. Market Signal Injection: Adversarial Context Manipulation of LLM Pricing Agents

    Sep 16, 2026Dohun Lee, Hyunwoo ParkAdversarial Attacks on LLMsAI Agent Security

    Graduate School of Data Science, Seoul National University

  25. BENCHCOMPASS: From Scores to Signals for Training and Harness Decisions in Payment-Domain LLMs

    Sep 16, 2026Sijie Dong, Wei Ren, Xuanwei Hu +9Financial ServicesLLM Evaluation

    Ant International

  26. A Three-Axis Stress Test of LLM vs Classical ML for Network Intrusion Detection under Distribution Shift and Adversarial Evasion

    Sep 11, 2026Muhammad Ebad Atif, Muhammad Haider AliNetwork Intrusion DetectionLLMs for Cybersecurity

    Dhanani School of Science and Engineering Habib University Karachi, Pakistan · Faculty of Computer Sciences and Engineering Ghulam Ishaq Khan Institute of Engineering Sciences Swabi, Pakistan

  27. Active Adaptation, Not Static Defense: Temporal Dynamics of Preventative Steering in Adversarial Fine-Tuning

    Sep 9, 2026Jing Guan, Yachao Yang, Zhaoliang Liu +3LLM Fine-TuningAdversarial Attacks on LLMs

    JIUTIAN Research, Beijing, China · Beijing University of Posts and Telecommunications, Beijing, China

  28. Understanding In-Context Multimodal Jailbreaks via Posterior Reweighting

    Sep 8, 2026Xu Zhang, Dev Mistry, Xiang Xu +1Multimodal Jailbreak AttacksAdversarial Robustness of Language Models

  29. Style Over Substance: Content-Invariant Wrappers Flip LLM Safety-Judge Verdicts

    Sep 8, 2026Yongxi Zhou, Wenbo Ye, Yuanzhe Liu +3LLM GuardrailsLLM-as-a-Judge

    Northeastern University, Massachusetts, USA · University of Southern California, California, USA · Georgia Institute of Technology, Georgia, USA

  30. The Geometry of Refusal: Why Post-Hoc Safety Is Fragile and Pretraining-Time Safety Persists

    Sep 7, 2026Srikanth Malla, Chiho Choi, Joon Hee ChoiLLM SafetyRefusal Behavior in Language Models

    Samsung Semiconductor US