Adversarial Example Detection

Ask about this topic

Overview

Adversarial example detection studies how to distinguish deliberately perturbed inputs from benign ones when small changes can cause a model to make errors. Methods look for signals such as unusual input frequencies, shifts in internal representations, prediction instability under transformations, or disagreement across layers and tasks; some use uncertainty estimates or formal certification. These approaches are studied in image, speech, language, and multimodal systems, with detectors ranging from training-free checks to learned classifiers calibrated on benign data. A central challenge is detecting adaptive and previously unseen attacks while keeping false alarms and computational costs low, and empirical success does not always provide a formal guarantee.

Latest papers

CardsList

49 papers12 papers in the last four weeks, against 1 the four weeks before. 0.1% of all new papers.

  1. When Guidance Becomes a Guard: Early Interception of Unsafe Inputs in Text-to-Image Generation

    Oct 19, 2026Yanchun Li, Yujin Wu, Gangkai Shen +5Safe T2I GenerationT2I Diffusion Models

    Xiangtan University · Changsha University of Science and Technology · City University of Hong Kong +1

  2. Provable Adversarial Detection: Prime Quantization meets Gromov--Wasserstein

    Oct 19, 2026Manohar Kaul, Sadbhavana Babar, Aditya Ramesh +4Adversarial Example Detection

  3. Feature-Context Consistency: Unsupervised Adversarial Detection with Drift Stability on Attributed Graphs

    Oct 12, 2026Firas Bayram, Maxime CordyGraph-Based Anomaly DetectionAnomaly Detection

    SnT, University of Luxembourg Luxembourg

  4. Robust Detection of Directional Adversarial Attacks in Deep Neural Networks for Radiological Imaging

    Oct 11, 2026Tristan Malatyński, Joanna Jaworek-KorjakowskaAdversarial Example DetectionAdversarial Attacks

    AGH University of Kraków, Poland Center of Excellence in Artificial Intelligence

  5. Adversarial Detection for Pre-trained Classifiers via Lipschitz-Margin Analysis with Certification

    Oct 11, 2026Rui Zhang, Xinle Cao, Huazhen Yu +2Adversarial Example DetectionAdversarial Robustness

    Nanjing University of Aeronautics and Astronautics · The State Key Laboratory of Blockchain and Data Security, Zhejiang University · Nanjing University of Information Science and Technology

  6. Detection-Guided Adaptive Purification with Diffusion Models for Robust Audio Deepfake Detection

    Oct 7, 2026Muhammed Salih Kayhan, Qiben YanAudio Deepfake Detection RobustnessAudio Deepfake Detection

    Michigan State University, East Lansing, MI, USA

  7. Detecting Adversarial Images through Response Profiles of Vision-Language Models

    Oct 7, 2026Arash Vashagh, Roozbeh Razavi-FarAdversarial Example DetectionVLM Robustness

    Trustworthy and Secure AI (TSAI) Lab, Faculty of Computer Science, University of New Brunswick, Canada

  8. GraphRectify: Graph-Based Transfer of Adversarial Example Detectors Across Neural Networks

    Oct 7, 2026Arash Vashagh, Roozbeh Razavi-FarAdversarial Example DetectionAdversarial Attacks

    Trustworthy and Secure AI (TSAI) Lab, Faculty of Computer Science, University of New Brunswick, Canada

  9. Detect and Suppress: A Mechanistic Defense against Adversarial Patches in VLA Models

    Oct 2, 2026Yukiya Horiba, Koshiro Aoki, Shunsuke Yasuki +2Robustness of VLA ModelsAdversarial Patch Attacks

    Keio University · Waseda University · The University of Tokyo

  10. Robust Evidential Learning Through Latent Consistency

    Oct 1, 2026Charmaine Barker, Daniel Bethell, Simos GerasimouEvidential Deep LearningAdversarial Robustness

    Department of Computer Science, University of York, UK · Department of Elect. Eng., and Computer Science and Eng., Cyprus University of Technology, Cyprus

  11. Detection of Adversarial Attacks on Super-Resolvers Using Spectral Features

    Sep 28, 2026Emma J. Reid, Haley Duba-Sullivan, Tony G. AllenAdversarial Example DetectionImage Super-Resolution

    Human Analysis and Biometrics Oak Ridge Laboratory Oak Ridge, TN, USA · Radar and Computational Imaging Oak Ridge Laboratory Oak Ridge, TN, USA

  12. Backdoor as Probe: Test-Time Adversarial Defense for CLIP

    Sep 28, 2026Zhongqi Wang, Jie Zhang, Nie Sen +3VLM RobustnessBackdoor Defense

    Key Laboratory of AI Safety of CAS, Institute of Computing Technology, Chinese Academy of Sciences (CAS), Beijing, China · University of Chinese Academy of Sciences, Beijing, China · Xuzhou University of Technology, China

  13. Preprocessing Failure and Adversarial Detection in Depthwise-Separable Edge Vision Systems

    Sep 3, 2026Jannatul Masruk Mukta, Rifa Sanjida, Adrita Rahman Tory +2Edge InferenceAdversarial Robustness

    Bangladesh University of Business and Technology (BUBT), Mirpur-2, Dhaka-1216, Bangladesh · University of New South Wales (UNSW), ACT 2601, Australia

  14. A Convolutional Layer Activation Dimensionality Reduction for Out-of-Distribution and Adversarial Attack Detection Methods

    Aug 10, 2026Leandro de Souza Rosa, Lorenzo Capelli, Clara Nunes Barrancos +2Convolutional Neural NetworksDimensionality Reduction

    Dipartimento di Ingegneria dell’Energia Elettrica e dell’Informazione “Guglielmo Marconi” (DEI) - Alma Mater Studiorum Università di Bologna, Bologna, Italy · Advanced Research Center on Electronic Systems “Ercole De Castro” (ARCES) - Alma Mater Studiorum Università di Bologna, Bologna, Italy

  15. Multi-Task Consistency-based Detection of Adversarial Attacks

    Aug 7, 2026Cong Chen, Jean-Philippe Monteuuis, Jonathan PetitAdversarial Example Detection

    Qualcomm Technologies, Inc. San Diego, CA 92121, USA

  16. Revisiting the Adversarial Robustness of Graph-Based Traffic Forecasting

    Jul 30, 2026Qingzhao ZhangAdversarial AttacksAdversarial Robustness

    The University of Arizoan

  17. Adversarial Deepfake Generation and an Investigation of Purification-Based Adversarial Detection

    Jul 28, 2026Junghyun Kim, Seunghyun Kim, Jiyoung WooDeepfake DetectionAI-Generated Image Detection

    Department of AI and Big Data Engineering, Soonchunhyang University, Asan, South Korea

  18. GeoDetect: Geometric Adversarial Detection for VLPs

    Jul 16, 2026Afsaneh Hasanebrahimi, Hanxun Huang, Christopher Leckie +2VLM RobustnessAdversarial Attacks on VLMs

    The University of Melbourne, Melbourne, Australia · Monash University, Melbourne, Australia

  19. A Unified Detection Framework for AI-Related Content and Artifacts

    Jul 8, 2026Xifeng Zhang, Tao Hu, Yijie Peng +1AI-Generated Text DetectionLLM Hallucination Detection

    School of Mathematical Sciences, Capital Normal University, Beijing 100048, China · School of Management and Engineering, Nanjing University, Nanjing 210008, China · Advanced Institute of Information Technology, Peking University +1

  20. A Classifier-Agnostic Zero-Shot Adversarial Attack Detection via CLIP

    Jun 29, 2026Hodaya Krakover, Meir Yossef Levi, Eyal Gofer +1Adversarial Example Detection

    Technion - Israel Institute of Technology, Haifa, Israel

  21. USAD: Uncertainty-aware Statistical Adversarial Detection

    Jun 26, 2026Zhijian Zhou, Xunye Tian, Jiacheng Zhang +5Two-Sample TestingAdversarial Example Detection

    The University of Melbourne

  22. What Was That Again? Certified Robustness for Automatic Speech Recognition

    Jun 26, 2026Andrew C. Cullen, Neil G. Marchant, Jiani Xie +2ASR EvaluationNeural Network Robustness

    University of Melbourne · DST Group, Adelaide

  23. AEGIS: A Semantic GAN and Evidential Learning Frameworkfor Robust Adversarial Detection in Vision Sensors

    Jun 25, 2026Maher Boughdiri, Mounira Msahli, Albert BifetAdversarial Example DetectionImage Classification

    LTCI, Département Informatique et Réseaux, Télécom Paris, Institut Polytechnique de Paris, France

  24. DE-FIVE: Detecting Malicious Image Prompts via Fourier Features and Image Vector Embeddings

    Jun 22, 2026Xingwei Zhong, Varun Sharma, Kar Wai Fok +1VLM RobustnessIndirect Prompt Injection

  25. Online Shift Detection and Conformal Adaptation for Deployed Safety Classifiers

    Jun 10, 2026Jun Wen LeongDistribution ShiftConformal Prediction

  26. Adversarial Attack and Disturbance Detection by Hadamard-Coded Output Representations for Object Detection and Semantic Segmentation

    Jun 8, 2026Lucas Görnhardt, Timo Bartels, Niklas Schwarz +1Adversarial PerturbationsObject Detection

    Technische Universität Braunschweig, Germany

  27. Securing Self-supervised Data Curation for Foundation Models Robustness

    Jun 8, 2026Sandeep Gupta, Roberto PasseroneTraining Data CurationAdversarial Example Detection

    Centre for Secure Information Technologies (CSIT), Queen’s University Belfast, UK. · Department of Information Engineering and Computer Science, University of Trento, Italy.

  28. SCI-Defense: Detecting Persuasion-Structured Manipulation of LLM-Based Ranking in Generative Engines

    May 21, 2026Xucheng Yu, Haibo Jin, Huimin Zeng +1LLM RerankingAdversarial Example Detection

    Siebel School of Computing and Data Science, University of Illinois Urbana-Champaign · School of Information Sciences, University of Illinois Urbana-Champaign · Amazon

  29. Detecting Fluent Optimization-Based Adversarial Prompts via Sequential Entropy Changes

    May 19, 2026Mohammed Alshaalan, Miguel R. D. RodriguesAdversarial Attacks on LLMsJailbreak Detection

    Department of Electronic and Electrical Engineering, University College London, London, United Kingdom.

  30. Enabling Adversarial Robustness in AI Models through Kubeflow MLOps

    May 14, 2026Stavros Bouras, Ioannis Korontanis, Antonios Makris +1Adversarial AttacksAdversarial Robustness

    School of Electrical and Computer Engineering, National Technical University of Athens, Greece · Department of Informatics and Telematics, Harokopio University of Athens, Greece