Adversarial Robustness

Ask about this topic

Overview

Adversarial robustness asks whether a model still predicts or acts reliably when an attacker makes small, strategic changes to its inputs, training data, or operating environment. Common approaches include adversarial training, which exposes models to attacks during learning; randomized smoothing and other certification methods, which provide conditional guarantees; and input purification, representation regularization, and test-time adaptation. Evaluations span image classifiers and detectors, language and multimodal models, graphs, time series, and safety-critical systems, using both empirical attacks and formal bounds. A central tension is that gains can depend on the attack, data, and deployment setting, while stronger robustness may cost clean accuracy or compute; adaptive, realistic evaluation and guarantees that match real threats remain open challenges.

Latest papers

CardsList

481 papers49 papers in the last four weeks, up 26% on the four weeks before. 0.3% of all new papers.

  1. On the Adversarial Robustness of Multimodal LLM Judges

    Jun 14, 2026Zihan Wang, Guansong Pang, Zelin Liu +3LLM-as-a-JudgeAdversarial Robustness

    School of Computer Science and Engineering, Beihang University, Beijing, China · School of Computing and Information Systems, Singapore Management University, Singapore · State Key Laboratory of Virtual Reality Technology and System, Beihang University, Beijing, China +1

  2. Securing Multi-Agent GIS Systems: Risk Evaluation and Prompt Hardening Optimization

    Jun 13, 2026Kyle Gao, Pranavi Kotta, Linlin Xu +2Adversarial RobustnessLLM Red Teaming

    Department of Systems Design Engineering, University of Waterloo, Waterloo, ON, Canada · Department of Mechatronics Engineering, University of Waterloo, Waterloo, ON, Canada · Department of Geomatics Engineering, University of Calgary, Calgary, AB, Canada +1

  3. GRAPE: Guided Parameter-Space Evolution for Compact Adversarial Robustness

    Jun 12, 2026Zhiyuan Ye, Xiangyu Zhou, Ji Qi +2Adversarial TrainingNeural Network Robustness

    University of Science and Technology of China · China Mobile · 2China Mobile (Suzhou) Software Technology Co., Ltd.

  4. Giving AI a Headache: Acoustic Adversarial Attacks to Computer Vision Applications

    Jun 12, 2026Nicole Villavicencio-Garduño, Maksim Ekin Eren, Milo Prisbrey +2Adversarial AttacksAdversarial Robustness

    Carnegie Mellon University, Pittsburgh, USA · Los Alamos National Laboratory, Los Alamos, USA

  5. Robust Auto-associative Memory via Convolutional Restricted Hopfield Networks

    Jun 11, 2026Ci Lin, Tet Yeap, Iluju KiringaAdversarial RobustnessHopfield Networks

    Electrical Engineering and Computer Science University of Ottawa

  6. Neural Variability Enhances Artificial Network Robustness

    Jun 11, 2026Robin Preble, Praveen Venkatesh, Stefan Mihalas +1Distribution Shift RobustnessNeural Network Robustness

    Department of Computer Science, Western Washington University, Bellingham, WA 98225 · Allen Institute, Seattle, WA 98195

  7. Shielded Analysis: Certification and Characterization of Defensibility in Systems under Adversarial Interaction

    Jun 11, 2026Achraf Hsain, Sultan AlmuhammadiAutonomous Cyber DefenseAdversarial Robustness

    Information and Computer Science Department King Fahd University of Petroleum and Minerals Dhahran, Saudi Arabia

  8. ERTS: Adversarial Robustness Testing of Ethical AI via Semantic Perturbation in a Bounded Consequence Space

    Jun 11, 2026Pratyush ChaudhariMoral Reasoning in Language ModelsLanguage Model Safety Evaluation

    Independent Researcher

  9. Quality-Preserving Imperceptible Adversarial Attack on Skeleton-based Human Action Recognition

    Jun 11, 2026Ziyi Chang, Kanglei Zhou, Xiaohui Liang +1Skeleton-Based Action RecognitionAdversarial Attacks

    Department of Computer Science, Durham University, Durham, DH1 4FL, UK · Department of Psychology and Cognitive Science, Tsinghua University, Beijing 100084, China · State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing 100191, China +1

  10. Reinforcement Learning Disrupts Gradient-Based Adversarial Optimization

    Jun 10, 2026Xinhai Zou, Chang Zhao, Alireza Aghabagherloo +3Adversarial TrainingAdversarial Attacks

    COSIC, KU Leuven · Leuven, Belgium · Imec +1

  11. Categorical Robustness Assessment for Machine Learning based Network Intrusion Detection Systems

    Jun 10, 2026Mayank Raj, Nathaniel D. Bastian, Lance Fiondella +1IoT Intrusion DetectionAdversarial Attacks

    University of Massachusetts Dartmouth, Dartmouth, MA 02747 USA · United States Military Academy, West Point, NY 10996 USA

  12. Toward Trustworthy AI: Multi-Target Adversarial Attacks and Robust Defenses for Continuous Data Summarization

    Jun 10, 2026Yuefang Lian, Longkun Guo, Zhongrui Zhao +5Submodular OptimizationAdversarial Attacks

    Nankai University · James Cook University · Western Sydney University +5

  13. Risk Under Pressure: Compute-Aware Evaluation of Adversarial Robustness in Language Models

    Jun 9, 2026Malikeh Ehghaghi, Boglárka Ecsedi, Marsha Chechik +1LLM AlignmentNeural Network Robustness

    University of Toronto · Vector Institute · Hugging Face

  14. Hybrid Robustness Verification for Spatio-Temporal Neural Networks

    Jun 8, 2026Sherwin Varghese, Matthew Wicker, Alessio LomuscioNeural Network VerificationNeural Network Robustness

    Imperial College London, United Kingdom

  15. Stain-Aware Wavelet Regularization for Instant Adversarial Purification in Histopathology

    Jun 7, 2026Zhe Li, Bernhard KainzComputational PathologyAdversarial Robustness

    FAU Erlangen-Nürnberg Erlangen, Germany · Imperial College London London, UK

  16. SHIELD-IDS: Structurally Heterogeneous Ensemble with Integrated Layered Defense for Intrusion Detection Systems

    Jun 5, 2026Maryam Zaman, Muhammad Khuram ShahzadEnsemble LearningNetwork Intrusion Detection

    School of Electrical Engineering and Computing(SEECS) · 2National University of Sciences and Technology, Islamabad, Pakistan

  17. SS-TPT: Stability and Suitability-Guided Test-Time Prompt Tuning for Adversarially Robust Vision-Language Models

    Jun 5, 2026Sunoh Kim, Daeho UmVLM RobustnessVLM Adaptation

    Dankook University, Yongin, South Korea · University of Seoul, Seoul, South Korea

  18. When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness

    Jun 5, 2026Sunoh Kim, Daeho UmVLM RobustnessAdversarial Attacks

    Dankook University Yongin, South Korea · University of Seoul Seoul, South Korea

  19. PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis

    Jun 4, 2026Ziling Liang, Xinping Yi, Qingsong Wen +1PAC-Bayesian Generalization BoundsAdversarial Robustness

    School of Information Science and Engineering, Southeast University, Nanjing 210096, China · Squirrel Ai Learning, Bellevue, WA, 98004 USA

  20. FoeGlass: Simple In-Context Learning Is Enough for Red Teaming Audio Deepfake Detectors

    Jun 3, 2026Sepehr Dehdashtian, Jacob H Seidman, Vishnu N Boddeti +1Audio Deepfake DetectionAdversarial Robustness

    Michigan State University · Reality Defender

  21. Measuring Model Robustness via Fisher Information: Spectral Bounds, Theoretical Guarantees, and Practical Algorithms

    Jun 3, 2026Chong Zhang, Xiang Li, Jia Wang +3Neural Network RobustnessAdversarial Robustness

    1Xi’an Jiaotong-Liverpool University · 2The Chinese University of Hong Kong.

  22. Toward a Generalized Defense Across Sparse, Continuous, and Structured Parameter Attacks

    Jun 3, 2026Bin Duan, Zeyu Bai, Guowei YangAdversarial AttacksAdversarial Robustness

    School of Electrical Engineering and Computer Science, The University of Queensland, Australia

  23. Adaptive Causal Alignment for High-Confidence Adversarial Training

    Jun 2, 2026Zhiming Luo, Kejia Zhang, Yingxin Lai +3Adversarial TrainingAdversarial Robustness

    Department of Artificial Intelligence, Xiamen University, Xiamen, China · Department of Computer Science, Emory University, GA, USA · College of Information Science and Technology, Jinan University, Guangzhou, China

  24. Beyond False Stability: High-Noise Drift Gating for Test-Time Adversarial Defenses in Vision-Language Models

    Jun 2, 2026Hashmat Shadab Malik, Muzammal Naseer, Salman KhanVLM RobustnessAdversarial Robustness

    Mohamed Bin Zayed University of AI, UAE · Khalifa University, UAE · Australian National University, Australia

  25. Investigating Adversarial Robustness of Multi-modal Large Language Models

    Jun 2, 2026Hashmat Shadab Malik, Muzammal Naseer, Salman KhanAdversarial TrainingVLM Robustness

    Mohamed Bin Zayed University of AI, UAE · Khalifa University, UAE · Australian National University, Australia

  26. Post-Hoc Robustness for Model-Based Reinforcement Learning

    Jun 2, 2026Siemen Herremans, Ali Anwar, Siegfried MercelisAdversarial RobustnessRobust RL

    1IDLab - University of Antwerp, imec

  27. ATLAS: A Large-Scale Evaluation Benchmark for Adversarial LiDAR Perception

    Jun 1, 2026Mellon M. Zhang, Siddhant Panse, Zimo Fan +3Lidar-Based 3D Object DetectionAdversarial Attacks

    Georgia Institute of Technology

  28. A combination of noise and bilateral filters achieve supralinear and scalable adversarial robustness in CNNs

    Jun 1, 2026Nicolas Stalder, Benjamin F. Grewe, Matteo Saponati +1Neural Network RobustnessAdversarial Robustness

    Institute of Neuroinformatics

  29. Sensitivity as a Double-Edged Sword: A Trade-off Between Discriminability and Adversarial Robustness

    Jun 1, 2026Kai WangPrototype-Based ClassificationNeural Network Robustness

  30. GJDNet: Robust Graph Neural Networks via Joint Disentangled Learning Against Adversarial Attacks

    Jun 1, 2026Canyixing Cui, Tao Wu, Xingping Xian +3Disentangled Representation LearningGraph Neural Networks

    School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, China · School of Cyber Security and Information Law, Chongqing University of Posts and Telecommunications, Chongqing, China · Computational Communication Research Center, Beijing Normal University, Zhuhai, China +2