Adversarial Text Attacks

Follow this topic Ask about this topic

Adversarial text attacks study how changes to wording, spelling, typography, style, or prompt structure can alter a model’s predictions or bypass safeguards. Common approaches include synonym and character substitutions, paraphrasing and style rewriting, black-box search guided by model feedback, and adversarial suffixes; defenses include adversarial training, input normalization, detection, and certified robustness methods. Evaluations span text classification, content moderation, AI-generated-text detection, retrieval and ranking, and LLM safety, with growing attention to multilingual and multimodal settings. A central challenge is making attacks effective while preserving meaning and readability, and ensuring that defenses generalize to adaptive attacks without rejecting benign inputs.

Latest papers

78 papers9 papers in the last four weeks, up 80% on the four weeks before. 0.1% of all new papers.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models
Apr 14, 2026Han Liu, Jiaqi Li, Zhi Xu +5Adversarial Attacks on VLMs Black-Box Adversarial Attacks
Dalian University of Technology, Dalian, China · The Pennsylvania State University, Pennsylvania, USA · Shenzhen University, Shenzhen, China
Reading Between the Pixels: Linking Text-Image Embedding Alignment to Typographic Attack Success on Vision-Language Models
Apr 14, 2026Ravikumar Balakrishnan, Sanket Mendapara, Ankit GargAdversarial Attacks on VLMs VLM Robustness
Cisco Systems
Homoglyph-based Adversarial Perturbation of Introductory Computer Science Theory Problems
Apr 13, 2026Aidan Alexander, Chitrangada Juneja, Napaluck Tontrasathien +4Adversarial Text Attacks Adversarial Attacks on LLMs
Hijacking Text Heritage: Hiding the Human Signature through Homoglyphic Substitution
Apr 11, 2026Robert DilworthStylometry Authorship Attribution
Department of Computer Science and Engineering, Mississippi State University, Mississippi State, Mississippi, USA
AtomEval: Validity-Aware Atomic Evaluation of Adversarial Claim Rewriting in Fact Verification
Apr 9, 2026Hongyi Cen, Mingxin Wang, Yule Liu +3Adversarial Text Attacks Automated Fact-Checking
Zhejiang University · The Hong Kong University of Science and Technology (Guangzhou)
Content Fuzzing for Escaping Information Cocoons on Digital Social Media
Apr 7, 2026Yifeng He, Ziye Tang, Hao ChenSocial Media Analysis Adversarial Text Attacks
Department of Computer Science, University of California, Davis · Department of Communication, University of California, Davis · University of Hong Kong
Beyond Semantic Manipulation: Token-Space Attacks on Reward Models
Apr 3, 2026Yuheng Zhang, Mingyue Huo, Minghao Zhu +2Adversarial Attacks Adversarial Text Attacks
UIUC · Independent Researcher · University of Massachusetts Amherst
Can LLMs Fool Graph Learning? Exploring Universal Adversarial Attacks on Text-Attributed Graphs
Mar 22, 2026Zihui Chen, Yuling Wang, Pengfei Jiao +4Adversarial Text Attacks Text-Attributed Graph Learning
School of Cyberspace, Hangzhou Dianzi University, Hangzhou, China · Hangzhou Dianzi University, Hangzhou, China · Beihang University, Beijing, China +1
RTD-Guard: A Black-Box Textual Adversarial Detection Framework via Replacement Token Detection
Mar 13, 2026He Zhu, Yanshu Li, Wen Liu +1Adversarial Example Detection Adversarial Text Attacks
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China · School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China
PivotAttack: Rethinking the Search Trajectory in Hard-Label Text Attacks via Pivot Words
Mar 11, 2026Yuzhi Liang, Shiliang Xiao, Jingsong Wei +2Adversarial Text Attacks Black-Box Adversarial Attacks
Guangdong University of Foreign Studies, China
Two Frames Matter: A Temporal Attack for Text-to-Video Model Jailbreaking
Mar 7, 2026Moyang Chen, Zonghao Ying, Wenzhuo Xu +4T2V Generation Adversarial Text Attacks
College of Science, Mathematics and Technology, Wenzhou-Kean University · AI Security Lab · State Key Laboratory of Complex & Critical Software Environment, Beihang University
Intent Laundering: AI Safety Datasets Are Not What They Seem
Feb 17, 2026Shahriar Golchin, Marc WetterLLM Safety Evaluation LLM Safety Benchmarks
Applied Machine Learning Research
StealthRL: Reinforcement Learning Paraphrase Attacks for Multi-Detector Evasion of AI-Text Detectors
Feb 9, 2026Suraj Ranganath, Atharv RameshRobustness of Machine-Generated Text Detection Adversarial Text Attacks
University of California, San Diego
RADAR: Retrieval-Augmented Detector with Adversarial Refinement for Adaptive LLM-Generated Fake News Detection
Jan 7, 2026Song-Duo Ma, Yi-Hung Liu, Hsin-Yu Lin +4Adversarial Training Fake News Detection
National Taiwan University, Taipei, Taiwan
destroR: A Benchmark and Adversarial-Training Defense for Bangla Transfer Models under Meaning-Preserving Attacks
Nov 13, 2025Saadat Rafid Ahmed, Rubayet Shareen, Radoan Sharkar +3Adversarial Text Attacks Adversarial Robustness of Language Models
Dept. of Computer Science and Engineering, BRAC University
Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content
Sep 16, 2025Shaz Furniturewala, Arkaitz ZubiagaMechanistic Interpretability Toxicity Detection
Center for Data Science, New York University · Queen Mary University of London
TSCheater: Generating High-Quality Tibetan Adversarial Texts via Visual Similarity
Dec 3, 2024Xi Cao, Quzong Gesang, Yuan Sun +2Adversarial Robustness of Language Models Adversarial Text Attacks
Minzu University of China, Beijing, China · National Language Resource Monitoring & Research Center Minority Languages Branch, Beijing, China · Tibet University, Lhasa, China +1
Perturbation Effects on Robustness and Individual Fairness
Apr 1, 2024Xuran Li, Hao Xue, Peng Wu +4Neural Network Robustness Algorithmic Fairness
University of New South Wales Sydney, Australia · The Hong Kong University of Science and Technology Guangzhou, China · Key Laboratory of System Software, Institute of Software, Chinese Academy of Sciences Beijing, China +3

Apr 14, 2026J/K move · Enter open · S save

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models

Han Liu, Jiaqi Li, Zhi Xu, Xiaotong Zhang+4

Dalian University of Technology, Dalian, China · The Pennsylvania State University, Pennsylvania, USA · Shenzhen University, Shenzhen, China

Adversarial Attacks on VLMs Black-Box Adversarial Attacks Adversarial Text Attacks

Open paper AskPDF arXiv

Black-box adversarial attack on vision-language pre-trained models is a practical and challenging task, as text and image perturbations need to be considered simultaneously, and only the predicted results are accessible. Research on this problem is in its infancy, and only a handful of methods are available. Nevertheless, existing methods either rely on a complex iterative cross-search strategy, which inevitably consumes numerous queries, or only consider reducing the similarity of positive image-text pairs but ignore that of negative ones, which will also be implicitly diminished, thus inevitably affecting the attack performance. To alleviate the above issues, we propose a simple yet effective framework to generate high-quality adversarial examples on vision-language pre-trained models, named HQA-VLAttack, which consists of text and image attack stages. For text perturbation generation, it leverages the counter-fitting word vector to generate the substitute word set, thus guaranteeing the semantic consistency between the substitute word and the original word. For image perturbation generation, it first initializes the image adversarial example via the layer-importance guided strategy, and then utilizes contrastive learning to optimize the image adversarial perturbation, which ensures that the similarity of positive image-text pairs is decreased while that of negative image-text pairs is increased. In this way, the optimized adversarial images and texts are more likely to retrieve negative examples, thereby enhancing the attack success rate. Experimental results on three benchmark datasets demonstrate that HQA-VLAttack significantly outperforms strong baselines in terms of attack success rate.