Adversarial Text Attacks

Follow this topic Ask about this topic

Momentum

1 paper in the last four weeks, down 67% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 49

All topics

EASE: Entropy-Adaptive Distribution Shaping for Evading AI-generated Text Detectors
Oct 7, 2026Jicheng Zhou, Kahim Wong, Jialong Wang +1Adversarial Text Attacks Robustness of Machine-Generated Text Detection
Department of Artificial Intelligence, Faculty of Information Science and Computing State Key Laboratory of Internet of Things for Smart City University of Macau, Macau, China
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
OASIS: Optimizing Attacker Sequences for Hard-Label Black-Box Text Attacks
Aug 30, 2026Qian Chen, Shiliang Xiao, Yuzhi LiangAdversarial Attacks Black-Box Adversarial Attacks
School of Information Science and Technology Guangdong University of Foreign Studies, China
Refusing Everything Looks Safe: Restoring the Benign Arm to Encoded-Prompt Evaluation
Aug 12, 2026Haoyu Zhang, Haowen Xu, Xiao Luo +7LLM Safety Benchmarks Language Model Safety Evaluation
Northeastern 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
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.
Occluded Oculus: Operationalizing Stylistic Obscurement
Jul 27, 2026Robert DilworthStylometry Adversarial Text Attacks
Department of Computer Science and Engineering, Mississippi State University, Mississippi State, Mississippi, USA
Adversarial Robustness of Phishing Email Detection: A Comparative Study of TF-IDF + Logistic Regression and Fine-Tuned DistilBERT
Jul 20, 2026Tanveer Ahmed, Seyedali PourmoafilAdversarial Robustness Cybersecurity
School of Physics, Engineering and Computer Science, University of Hertfordshire, Hatfield, Herts AL10 9AB, United Kingdom
UTS at ELOQUENT 2026 Voight-Kampff: structural shifts in AI writing bypass state-of-the-art detectors
Jul 15, 2026Dima Galat, Marian-Andrei RizoiuAdversarial Training AI-Generated Text Detection
University of Technology Sydney, Australia
Out of Sight: Compression-Aware Content Protection against Agentic Crawlers
Jul 9, 2026Xuefei WangLLM Agent Security Black-Box Adversarial Attacks
Beihang University
Seduced by the Narrative: Assessing Rule Adherence in Semi-Open Textual Sandboxes
Jul 2, 2026Weiying Chen, Junlong Shen, Zhanyuan Guo +1LLM Safety Benchmarks Adversarial Prompt Generation
University of Alberta, Edmonton, AB, Canada · N-Dice Association · Qilu University of Technology, Shandong, China
Triospect: A Three-Dimensional Framework for Robust Statistical AI-Generated Text Detection Against Diverse Attacks
Jun 30, 2026Guangsheng Bao, Lihua Rong, Yanbin Zhao +3AI-Generated Text Detection Robustness of Machine-Generated Text Detection
Zhejiang University · Zhejiang University of Technology · Shanghai Polytechnic University +2
Vulnerability of Natural Language Classifiers to Evolutionary Generated Adversarial Text
Jun 25, 2026Manjinder Singh, Alexander E. I. Brownlee, Mohamed ElawadyAdversarial Attacks Black-Box Adversarial Attacks
Computing Science & Mathematics University of Stirling, Stirling, UK · Computer and Information Sciences University of Strathclyde, Glasgow, UK
Generalised Eigenvalue Geometry of Semantic Adversarial Attacks
Jun 17, 2026Martin Anthony, Kaveh Salehzadeh NobariAdversarial Robustness Adversarial Text Attacks
Data Science Institute, London School of Economics and Political Science. · Department of Mathematics, London School of Economics and Political Science. · The Inclusion Initiative, London School of Economics and Political Science.
GAS-Leak-LLM: Genetic Algorithm-Based Suffix Optimization for Black-Box LLM Jailbreaking
Jun 14, 2026Aman Anifer, Vignesh Kumar Kembu, Vishnu M +4Adversarial Prompt Generation LLM Safety
Department of Computer Applications, Cochin University of Science and Technology, Kerala, India. · Department of Electrical, Computer and Biomedical Engineering, University of Pavia, A. Ferrata, 5, Pavia, 27100, Italy.
Greedy Coordinate Diffusion: Effective and Semantically Coherent Adversarial Attacks via Diffusion Guidance
Jun 14, 2026Bohdan Turbal, Blossom Metevier, Max Springer +1Adversarial Prompt Generation Adversarial Attacks
Princeton University, Princeton, NJ, USA.
S-GBT: Smooth Growth Bound Tensor for Certified Robustness Against Word Substitution Attacks in NLP
Jun 11, 2026Mohammed Bouri, Mohammed Erradi, Adnane SaoudAdversarial Training Certified Robustness
College of Computing, Mohammed VI Polytechnic University, Morocco · CID Development, Morocco · ENSIAS, University Mohamed V of Rabat, Morocco
No Hidden Prompts Needed! You Can Game AI Peer Review with Presentation-Only Revisions
Jun 11, 2026Xu Yang, Zhizhou Sha, Junbo Li +10Adversarial Attacks Automated Peer Review
University of Texas at Austin · University of Illinois Urbana-Champaign · University of Texas at Dallas +1
What the Eyes See, the LLMs Miss: Exploiting Human Perception for Adversarial Text Attacks
Jun 8, 2026Qin Yang, Lu Malloy, Joshua Lee +4Language Model Safety Evaluation Black-Box Adversarial Attacks
University of Connecticut · University of Tennessee · University of California, Santa Barbara +1
Detector-Evasive LLM Paraphrasing via Constrained Policy Optimization
May 29, 2026Mingyi Wang, Zhuoer Shen, Yuheng Bu +1Constrained RL Text Generation
School of ECEE, Arizona State University · Department of Computer Science, University of California, Santa Barbara
GEO-Bench: Benchmarking Ranking Manipulation in Generative Engine Optimization
May 27, 2026Ojas Nimase, Zhe Chen, Gengpei Qi +2Generative Engine Optimization Adversarial Attacks
University of Southern California · Arizona State University
SilentRetrieval: Hijacking Retrieval-Augmented Generation via Semantically-Preserving Adversarial Data Poisoning
May 27, 2026Jiachen QianRetrieval-Augmented Generation RAG Poisoning Attacks
City University of Hong Kong · Hong Kong, Hong Kong
Unveiling the Fragility of Vision-Language Models: Multi-Modal Adversarial Synergy via Texture-Constrained Perturbations and Cross-Modal Optimization
May 26, 2026Xiang Fang, Wanlong Fang, Changshuo WangVLM Robustness Adversarial Attacks on VLMs
School of Software Engineering, Huazhong University of Science and Technology · Nanyang Technological University, Singapore · University College London
SEP-Attack: A Simple and Effective Paradigm for Transfer-Based Textual Adversarial Attack
May 24, 2026Han Liu, Zhi Xu, Xiaotong Zhang +5Determinantal Point Process Transfer-Based Adversarial Attacks
Dalian University of Technology Dalian, China · Peking University Beijing, China · Macao Polytechnic University Macao, China +1
Turning Bias into Bugs: Bandit-Guided Style Manipulation Attacks on LLM Judges
May 24, 2026Xianglin Yang, Bryan Hooi, Gelei Deng +2LLM Evaluation LLM-as-a-Judge
School of Computing, National University of Singapore, Singapore · Nanyang Technological University, Singapore
Harder to Defend: Towards Chinese Toxicity Attacks via Implicit Enhancement and Obfuscation Rewriting
May 21, 2026Jingyi Kang, Junyu Lu, Bo Xu +4Language Model Safety Evaluation Toxicity Detection
1Dalian University of Technology · 2The University of Tokyo · 3Singapore University of Technology and Design
SCI-Defense: Defending Manipulation Attacks from Generative Engine Optimization
May 21, 2026Xucheng Yu, Haibo Jin, Huimin Zeng +1LLM Reranking Adversarial Example Detection
Siebel School of Computing and Data Science, University of Illinois Urbana-Champaign · School of Information Sciences, University of Illinois Urbana-Champaign · Amazon
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
Universal Adversarial Triggers
May 18, 2026Benedict Florance Arockiaraj, Alexander Feng, Jianxiong Cai +1Adversarial Attacks Adversarial Text Attacks
The Capability Paradox: How Smarter Auditors Make Multi-Agent Systems Less Secure
May 17, 2026Qiqi Liu, Thorsten Holz, Shilin Ye +1Multi-Agent LLM Systems Multi-Agent System Security
University of Chinese Academy of Sciences · Max Planck Institute for Security and Privacy · Henan Yinzhu Safety Technology Co., Ltd. +1

Oct 7, 2026, cs.CLJ/K move · Enter open · S save

EASE: Entropy-Adaptive Distribution Shaping for Evading AI-generated Text Detectors

Jicheng Zhou, Kahim Wong, Jialong Wang, Jiantao Zhou

Department of Artificial Intelligence, Faculty of Information Science and Computing State Key Laboratory of Internet of Things for Smart City University of Macau, Macau, China

Adversarial Text Attacks Robustness of Machine-Generated Text Detection

Open paper AskPDF arXiv

AI-generated text (AIGT) detection can be sensitive to the decoding choices of the source large language model (LLM). We observe that perturbing next-token logits or adjusting sampling temperature can reduce detection performance, providing a clear signal of detector vulnerability to decoding-time distribution changes. Building on this observation, we propose EASE (Entropy-Adaptive Distribution Shaping for Evasion), a training-free and detector-agnostic framework for evading AIGT detectors. EASE computes predictive entropy directly from the source LLM's next-token distribution and uses it to adapt both logit perturbation and sampling temperature, without detector feedback or model fine-tuning. Experiments across three source LLMs and multiple detectors demonstrate consistent reductions in detection performance, with negligible degradation in text quality and negligible inference overhead.

Momentum

Related topics

Latest papers 49