Adversarial Robustness of Language Models

Follow this topic Ask about this topic

Momentum

14 papers in the last four weeks, up 133% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 123

All topics

Quad-State Safety Evaluation of Open-Weight Large Language Models on Non-Canonical Inputs
Oct 6, 2026Pavan MaddulaLanguage Model Safety Evaluation Adversarial Robustness of Language Models
Independent Researcher
Counting Moves, Weighing Voices: Bayesian Dialectical Argumentation for Calibrated Multi-LLM Councils under Persistent Adversaries
Oct 1, 2026Ionel Eduard Stan, Paolo NapoletanoLanguage Model Calibration Computational Argumentation
Department of Informatics, Systems and Communication (DISCo), University of Milano–Bicocca, Milan, Italy
DeBERTa-ConPara: Attack-Aware and Deployment-Realistic Detection of AI-Generated Text
Oct 1, 2026Mohamed Mady, Yupei Li, Johannes Reschke +1AI-Generated Text Detection Adversarial 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
Towards Robust Numerical Claim Verification
Sep 30, 2026Peter Røysland Aarnes, Vinay SettyNumerical Reasoning in Language Models Claim Verification
University of Stavanger · Factiverse AI and University of Stavanger
ACTR: Aligning Thoughts and Responses for Multilingual Safety in Reasoning LLMs
Sep 29, 2026Xianhui Zhang, Jian Yu, Chengyu Xie +6Adversarial Attacks on LLMs LLM Safety Alignment
Nanjing University of Science and Technology, Nanjing, China · National University of Singapore, Singapore · Beihang University, Beijing, China
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 Alignment Adversarial Robustness of Language Models
University of Louisville Louisville, Kentucky, USA
DeShortcut-Align: Decoupling Spurious Shortcuts for Robust Safety Alignment in Large Reasoning Models
Sep 28, 2026Qirui Liu, Yichen Sun, Yan Wang +4LLM Safety Alignment Adversarial Robustness of Language Models
The State Key Laboratory of Blockchain and Data Security, Zhejiang University · Ant Group · Chongqing Ant Consumer Finance Co., Ltd
Recovering Agentic Sovereignty: Mitigating the Consensus Paradox via Contrastive Epistemic Decoding
Sep 22, 2026Dahlia Shehata, Ming LiLLM Sycophancy Adversarial Attacks on LLMs
University of Waterloo Canada
On the Efficiency-Safety Dilemma in Large Reasoning Models
Sep 20, 2026Yifei Yang, Zouying Cao, Xingrui Wang +4LLM Inference Acceleration LLM 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
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 Systems Adversarial Robustness of Language Models
Nanyang Technological University, Singapore · Centre for Frontier AI Research, IHPC, A*STAR, Singapore · National University of Singapore, Singapore
Beyond Routine Compliance: Cunning Data Cultivates Safety Vigilance in Large Language Models
Sep 16, 2026Youjia Wang, Lin Xu, Yang Sun +3LLM Safety Alignment LLM Safety
Huawei Technology Inc
Market Signal Injection: Adversarial Context Manipulation of LLM Pricing Agents
Sep 16, 2026Dohun Lee, Hyunwoo ParkAdversarial Attacks on LLMs AI Agent Security
Graduate School of Data Science, Seoul National University
BENCHCOMPASS: From Scores to Signals for Training and Harness Decisions in Payment-Domain LLMs
Sep 16, 2026Sijie Dong, Wei Ren, Xuanwei Hu +9Financial Services LLM Evaluation
Ant International
Active Adaptation, Not Static Defense: Temporal Dynamics of Preventative Steering in Adversarial Fine-Tuning
Sep 9, 2026Jing Guan, Yachao Yang, Zhaoliang Liu +3LLM Fine-Tuning Adversarial Attacks on LLMs
JIUTIAN Research, Beijing, China · Beijing University of Posts and Telecommunications, Beijing, China
Style Over Substance: Content-Invariant Wrappers Flip LLM Safety-Judge Verdicts
Sep 8, 2026Yongxi Zhou, Wenbo Ye, Yuanzhe Liu +2LLM Safety Benchmarks LLM-as-a-Judge
Northeastern University, Massachusetts, USA · University of Southern California, California, USA · Georgia Institute of Technology, Georgia, USA
Representational alignment yields generalizable safety in language models
Sep 3, 2026Lingyu Li, Yan Teng, Yingchun Wang +1Moral Reasoning in Language Models LLM Safety Alignment
Shanghai Artiﬁcial Intelligence Laboratory, Shanghai, China
HiveTraceGuard-Pro: A Compact Generative Guardrail for Prompt Injection, Jailbreaks, and Adversarial Obfuscation
Sep 1, 2026Nikita Oblakov, Sabrina Sadiekh, Evgeniy KokuykinLanguage Model Safety Evaluation LLM Guardrails
HiveTraceLab
Refusal geometry reflects refusal training: diverse refusal prefixes can raise stable rank and weaken refusal vector ablation attacks
Aug 26, 2026Andrey LabunetsAdversarial Attacks on LLMs Adversarial Robustness of Language Models
UC San Diego
Learning to Persuade Exposes How Easily LLMs Abandon Correct Beliefs
Aug 12, 2026Nimet Beyza Bozdag, Emre Can Acikgoz, Gokhan Tur +1Deception in Language Models Adversarial Attacks on LLMs
University of Illinois Urbana-Champaign
Dual-Adversarial Safety Alignment: Cultivating Intrinsic Threat Comprehension in LRMs
Aug 10, 2026Hongli Shen, Shaopeng Fu, Qinbo Zhang +2Adversarial Training Adversarial Attacks on LLMs
1King Abdullah University of Science and Technology · 2Stony Brook University
Build it, Break it, Repeat: Benchmarking and improving LLM-manipulated disinformation detection in social media posts
Aug 10, 2026Kevin Thomas, Milosz Kasprzyk, Reuel C Igbokwe Onuigbo +5AI-Generated Text Detection Adversarial Robustness of Language Models
University of Sheffield, Department of Computer Science, Regent Court, 211 Portobello Street, Sheffield, S1 4DP, United Kingdom
Mood Matters: How Syntactic Sensitivity Undermines Safety Alignment
Aug 5, 2026Alina Klerings, Jannik Brinkmann, Heiner Stuckenschmidt +1Adversarial Attacks on LLMs LLM Safety Alignment
University of Mannheim · Technical University Clausthal
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation
Aug 5, 2026Victor Akinwande, J. Zico Kolter, Aran NayebiScalable Oversight LLM Evaluation
School of Computer Science 2Neuroscience Institute Carnegie Mellon University
Eliciting Intrinsic Hallucinations in LLMs via Semantically Equivalent Adversarial Attacks
Aug 4, 2026Atri Vivek Sharma, Brian Formento, Alessio LomuscioRetrieval-Augmented Generation Adversarial Attacks
Imperial College London · Safe Intelligence
Sensitivity, Causality, and Repair Dissociate: A Layer-Wise Analysis of Perturbation Robustness and Its Scaling
Aug 4, 2026Nathan Labiosa, David Buff, Ena Nayak +1LLM Interpretability Adversarial Robustness of Language Models
University of Southern California
Moving the Safety Barrier: Dynamic Routing Adaptive Alignment Against White-Box Attacks
Aug 2, 2026Shangze Li, Chuancheng Shi, Simiao Xie +6Adversarial Attacks on LLMs LLM Safety Alignment
1Nanjing University of Science and Technology · 2The University of Sydney · 5NExT++ Research Centre, National University of Singapore +2
On-Policy Distillation for LLM Safety: A Routing Approach to Template-Robust Realignment
Jul 29, 2026Yongjian Guo, Wanlun Ma, Lingyu Shen +2LLM Safety Alignment Adversarial Robustness of Language Models
Tsinghua University · Swinburne University of Technology · EPFL
Evaluation of Adversarial Robustness in Arabic Language Models
Jul 28, 2026Anwar Alajmi, Ayed Salman, Imtiaz AhmadAdversarial Training Arabic NLP
Department of Computer Engineering, Kuwait University, Kuwait. · Department of Computer Science, College of Business Studies, Public Authority of Applied Education and Training, Kuwait.
Distribution-Specific Curvature Control with Finite-Sample Guarantees for Open-Weight Safety
Jul 24, 2026Domenic Rosati, Ali Dadsetan, Hong Huang +5Adversarial Robustness LLM Safety Alignment
1Dalhousie University · 2Vector Institute for Artificial Intelligence · 3Indian Institute of Management Bangalore
Trustworthiness Costs of Domain Adaptation in Small Language Models:A Cross-Architecture Empirical Study
Jul 23, 2026Ramesh B. ParamkushamLanguage Model Safety Evaluation Domain Adaptation
Independent Researcher; Adjunct Faculty, University of the Cumberlands, Williamsburg, KY, USA

Oct 6, 2026, cs.CLJ/K move · Enter open · S save

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

Pavan Maddula

Independent Researcher

Language Model Safety Evaluation Adversarial Robustness of Language Models LLM Safety Benchmarks Adversarial Attacks on LLMs

Open paper AskPDF arXiv

Standard safety evaluations of large language models assess harmful requests written in canonical plain text, while models in real-world deployment routinely receive inputs containing emojis, altered spellings, encoded strings, and character-level variations. This work introduces the Adversarial Surface-Form Robustness Dataset (ASRD), comprising 2,100 prompts across seven distinct surface-form families. Five open-weight language models are evaluated across these prompts, producing 10,500 responses. The Quad-State Evaluation Rubric classifies each response into one of four outcomes: harmful compliance, safe response, comprehension failure, or indeterminate. Emoji and invisible Unicode variations cause almost no comprehension failure, with pooled harmful compliance of 20.27% and 17.20% against a 22.87% baseline that is driven mainly by Mistral 7B, whereas leetspeak, encoded wrappers, and hybrid transformations score 2.40%, 0.13%, and 2.40% while comprehension failure rises to 36.47%, 65.60%, and 34.47%. Inspection of raw model outputs reveals three response behaviors: hallucinated benignity, structural collapse, and language drift. Project page: www.pavanmaddula.com/quadstate

Momentum

Related topics

Latest papers 123