Adversarial Patch Attacks

Ask about this topic

Overview

Adversarial patch attacks study how small, localized patterns can make vision systems misclassify objects, miss detections, or produce attacker-chosen outputs. Researchers optimize patches with gradient-based or black-box methods, often making them universal or targeted and testing robustness to changes in scale, viewpoint, lighting, and printing. Applications range from object detection in autonomous driving and infrared imaging to vision-language models and robots, where visual errors can propagate into actions. Defenses include patch detection and masking, spectral methods, adversarial training, and certification, but a central tension is whether digital robustness transfers to physical, changing scenes and prevents failures across an entire system.

Latest papers

CardsList

49 papers4 papers in the last four weeks, down 33% on the four weeks before. 0.0% of all new papers.

  1. Transferable Physical-World Adversarial Patches Against Pedestrian Detection Models

    Apr 24, 2026Shihui Yan, Ziqi Zhou, Yufei Song +3Adversarial Patch AttacksTransfer-Based Adversarial Attacks

    Huazhong University of Science and Technology China

  2. PatchPoison: Poisoning Multi-View Datasets to Degrade 3D Reconstruction

    Apr 14, 2026Prajas Wadekar, Venkata Sai Pranav Bachina, Kunal Bhosikar +2Data Poisoning AttacksAdversarial Patch Attacks

    International Institute of Information Technology, Hyderabad, India

  3. Defending against Patch-Based and Texture-Based Adversarial Attacks with Spectral Decomposition

    Apr 12, 2026Wei Zhang, Xinyu Chang, Xiao Li +2Adversarial RobustnessAdversarial Examples

    Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China. · School of Software, Tsinghua University, Beijing 100084, China. · School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, China. +2

  4. Preference Redirection via Attention Concentration: An Attack on Computer Use Agents

    Apr 9, 2026Dominik Seip, Matthias HeinAdversarial AttacksAdversarial Attacks on VLMs

    Tübingen AI Center, University of Tübingen

  5. CAAP: Capture-Aware Adversarial Patch Attacks on Palmprint Recognition Models

    Apr 8, 2026Renyang Liu, Jiale Li, Jie Zhang +6Adversarial Patch AttacksPhysical Adversarial Attacks

    Institute of Data Science, National University of Singapore, Singapore 117602, Singapore · Centre for Frontier AI Research (CFAR), A*STAR, Singapore, 138634 · School of Cyber Science and Engineering, Wuhan University, China, 430072 +2

  6. Revealing Physical-World Semantic Vulnerabilities: Universal Adversarial Patch for Infrared Vision-Language Models

    Apr 3, 2026Chengyin Hu, Yuxian Dong, Yikun Guo +8Adversarial Attacks on VLMsVLM Robustness

    China University of Petroleum-Beijing at Karamay, No. 355 Anding Road, Karamay 834000, Xinjiang, China. · the Defense Innovation Institute, Chinese Academy of Military Science, Beijing, China. · Shenzhen University, Shenzhen, China. +1

  7. Towards Physically Realizable Adversarial Attenuation Patch against SAR Object Detection

    Apr 1, 2026Yiming Zhang, Weibo Qin, Feng WangAdversarial AttacksAdversarial Patch Attacks

    Key Laboratory for Information Science of Electromagnetic Waves (MoE), School of Information Science and Technology, Fudan University, Shanghai 200433, China

  8. From Pixels to Reality: Physical-Digital Patch Attacks on Real-World Camera

    Mar 30, 2026Victoria Leonenkova, Ekaterina Shumitskaya, Dmitriy Vatolin +1Adversarial AttacksAdversarial Patch Attacks

    Lomonosov MSU, Moscow, Russia · AI Center, Lomonosov MSU, IAI MSU, Moscow, Russia

  9. TRAP: Hijacking VLA CoT-Reasoning via Adversarial Patches

    Mar 24, 2026Zhengxian Huang, Wenjun Zhu, Haoxuan Qiu +2Adversarial Attacks on VLA ModelsRobustness of VLA Models

    Zhejiang University, Hangzhou, China · Harbin Institute of Technology, Harbin, China

  10. Thermal Topology Collapse: Universal Physical Patch Attacks on Infrared Vision Systems

    Mar 23, 2026Chengyin Hu, Yikun Guo, Yuxian Dong +7Adversarial Patch AttacksPhysical Adversarial Attacks

    China University of Petroleum-Beijing at Karamay, No. 355, Anding Road, Karamay, 834000, Xinjiang, China. · Guangdong University of Technology, Guangzhou, Guangdong, China. · Tianjin University, Tianjin, China. +1

  11. OmniPatch: A Universal Adversarial Patch for ViT-CNN Cross-Architecture Transfer in Semantic Segmentation

    Mar 21, 2026Aarush Aggarwal, Akshat Tomar, Amritanshu Tiwari +1Adversarial Patch AttacksAdversarial Attacks

    Data Science Group, Indian Institute of Technology Roorkee, India

  12. AI Evasion and Impersonation Attacks on Facial Re-Identification with Activation Map Explanations

    Mar 16, 2026Noe Claudel, Weisi Guo, Yang XingAdversarial AttacksAdversarial Patch Attacks

    All authors are with the Centre for Assured and Connected Autonomy, Cranfield University, Bedford, UK.

  13. STRAP-ViT: Segregated Tokens with Randomized -- Transformations for Defense against Adversarial Patches in ViTs

    Mar 13, 2026Nandish Chattopadhyay, Anadi Goyal, Chandan Karfa +1Adversarial RobustnessVision Transformer

    Indian Institute of Technology, Guwahati, India · Nanyang Technological University, Singapore

  14. Comparative Analysis of Patch Attack on VLM-Based Autonomous Driving Architectures

    Mar 9, 2026David Fernandez, Pedram MohajerAnsari, Amir Salarpour +3Adversarial Attacks on VLMsVLM Robustness

    School of Computing, Clemson University, Clemson, SC, USA

  15. Multimodal Adversarial Quality Policy for Safe Grasping

    Mar 2, 2026Kunlin Xie, Chenghao Li, Haolan Zhang +1Safe Robot ManipulationRobotic Grasping

    The authors are with the School of Information Science, Japan Advanced Institute of Science and Technology, Nomi, Ishikawa 923-1292, Japan

  16. CaptionFool: Universal Image Captioning Model Attacks

    Feb 28, 2026Swapnil ParekhAdversarial Attacks on VLMsVLM Robustness

    Intuit

  17. Adversarial Patch Generation for Visual-Infrared Dense Prediction Tasks via Joint Position-Color Optimization

    Feb 27, 2026He Li, Wenyue He, Weihang Kong +1Adversarial Patch AttacksAdversarial Examples

    School of Artificial Intelligence (School of Software), Yanshan University, Qinhuangdao 066004, China. · Fusion Intelligence Laboratory, Department of Computer Science, University of Exeter, EX4 4RN, United Kingdom.

  18. Physical Evaluation of Naturalistic Adversarial Patches for Camera-Based Traffic-Sign Detection

    Feb 27, 2026Brianna D'Urso, Tahmid Hasan Sakib, Syed Rafay Hasan +1Traffic Sign DetectionPhysical Adversarial Attacks

    Department of Computing Sciences, University of Hartford, West Hartford, CT, USA · Department of Electrical and Computer Engineering, Tennessee Technological University, Cookeville, TN, USA · Center for Manufacturing Research, Tennessee Technological University, Cookeville, TN, USA

  19. Dynamic Deception: When Pedestrians Team Up to Fool Autonomous Cars

    Feb 20, 2026Masoud Jamshidiyan Tehrani, Marco Gabriel, Jinhan Kim +1Physical Adversarial AttacksAdversarial Patch Attacks

    Università della Svizzera italiana Lugano, Switzerland