Adversarial Training

Ask about this topic

Overview

Adversarial training studies how to make models perform reliably when inputs, environments, or data distributions are deliberately or naturally shifted. A common approach alternates between finding difficult examples—using methods such as projected-gradient attacks, distributionally robust optimization, or learned attackers—and training the model to handle them; related methods target latent representations, domains, or interaction policies. These techniques are used in vision, language-model safety, detection, and reinforcement learning, with evaluations ranging from bounded perturbation benchmarks to adaptive attacks and shifted environments. A central tension is that robustness to trained or tested threats may not transfer to unseen attacks, while stronger training can cost accuracy, utility, or computation.

Latest papers

CardsList

187 papers31 papers in the last four weeks, up 121% on the four weeks before. 0.2% of all new papers.

  1. Latent Instruction Representation Alignment: defending against jailbreaks, backdoors and undesired knowledge in LLMs

    Apr 12, 2026Eric Easley, Sebastian FarquharBackdoor Defense in LLMsLLM Jailbreak Attacks

    ML Alignment & Theory Scholars Berkeley, CA, USA · OATML, Department of Computer Science University of Oxford, Oxford, UK

  2. Adversarial Sensor Errors for Safe and Robust Wind Turbine Fleet Control

    Apr 9, 2026Julian Quick, Marcus Binder Nilsen, Andreas Bechmann +2Robust ControlAdversarial Attacks

    Department of Wind and Energy Systems, Technical University of Denmark, Roskilde, Denmark · Department of Engineering Technology and Didactics, Technical University of Denmark, Ballerup, Denmark

  3. Adversarial Label Invariant Graph Data Augmentations for Out-of-Distribution Generalization

    Apr 9, 2026Simon Zhang, Ryan P. DeMilt, Kun Jin +1OOD GeneralizationCovariate Shift

    Department of Computer Science, Purdue University, West Lafayette, USA · Department of Computer Science and Engineering, The Ohio State University, Columbus Ohio, USA · Department of Industrial and Systems Engineering, The Ohio State University, Columbus Ohio, USA

  4. Adversarial Robustness of Time-Series Classification for Crystal Collimator Alignment

    Apr 7, 2026Xaver Fink, Borja Fernandez Adiego, Daniele Mirarchi +4Adversarial RobustnessAdversarial Attacks

    CERN, Geneva, Switzerland · RWTH Aachen University, Aachen, Germany · DESY, Hamburg, Germany

  5. The Persistent Vulnerability of Aligned AI Systems

    Mar 31, 2026Aengus LynchAI Agent SafetyAI Alignment

    Department of Computer Science, University College London

  6. Robust Multi-Agent Reinforcement Learning for Small UAS Separation Assurance under GPS Degradation and Spoofing

    Mar 30, 2026Alex Zongo, Filippos Fotiadis, Ufuk Topcu +1Robust RLCollision Avoidance

    A. Zongo and P. Wei are with the Department of Mechanical and Aerospace Engineering, George Washington University, Washington, D.C. 20052, USA. · F. Fotiadis and U. Topcu are with the Oden Institute for Computational Engineering & Sciences, University of Texas at Austin, Austin, TX 78712, USA.

  7. Statistical Guarantees for Distributionally Robust Optimization with Optimal Transport and OT-Regularized Divergences

    Mar 29, 2026Jeremiah Birrell, Xiaoxi ShenDistributionally Robust OptimizationWasserstein Distributionally Robust Optimization

    Department of Mathematics Texas State University San Marcos, TX, USA

  8. ARTA: Adversarial-Robust Multivariate Time--Series Anomaly Detection via Sparsity-Constrained Perturbations

    Mar 26, 2026Hadi Hojjati, Narges ArmanfardTime-Series Anomaly DetectionAdversarial Robustness

    McGill University, MILA - Quebec AI Institute, Montreal, Quebec, Canada

  9. Knowledge-Guided Adversarial Training for Infrared Object Detection via Thermal Radiation Modeling

    Mar 26, 2026Shiji Zhao, Shukun Xiong, Maoxun Yuan +6Infrared Object DetectionAdversarial Robustness

    Institute of Artificial Intelligence, Beihang University, No.37 Xueyuan Road, Haidian District, Beijing 100191, P.R. China. · Security Department, Alibaba Group, Hangzhou 310056, China. · School of Computer Science, Nankai University, China. +2

  10. Attack Assessment and Augmented Identity Recognition for Human Skeleton Data

    Mar 25, 2026Joseph G. Zalameda, Megan A. Witherow, Alexander M. Glandon +2Adversarial RobustnessAdversarial Training

    Dept. of ECE, Old Dominion University, Norfolk, VA, USA · Dept. of Computer Science, Amherst College, Hampshire County, MA, USA

  11. ALIGN: Adversarial Learning for Generalizable Speech Neuroprosthesis

    Mar 18, 2026Zhanqi Zhang, Shun Li, Bernardo L. Sabatini +2Brain-Computer InterfacesNeural Decoding

    Kempner Institute for the Study of Natural and Artificial Intelligence, Harvard University, Boston, Massachusetts, USA · Halıcıo˘glu Data Science Institute, Department of Electrical and Computer Engineering, Department of Computer Science and Engineering, University of California San Diego, La Jolla, California, USA

  12. ADV-0: Closed-Loop Min-Max Adversarial Training for Long-Tail Robustness in Autonomous Driving

    Mar 16, 2026Tong Nie, Yihong Tang, Junlin He +5Long-Tail Autonomous DrivingAdversarial Training

    The Hong Kong Polytechnic University, Hong Kong SAR, China · Tongji University, Shanghai, China · McGill University, Montreal, QC, Canada

  13. Taming the Adversary: A Cost-to-Disturbance Ratio Approach to Adversarial Reinforcement Learning

    Mar 12, 2026Taeho Lee, Donghwan LeeAdversarial MARLReinforcement Learning

    School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon 34141, Republic of Korea

  14. RAF: Relativistic Adversarial Feedback For Universal Speech Synthesis

    Mar 12, 2026Yongjoon Lee, Jung-Woo ChoiNeural VocodersSpeech Processing

    Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea

  15. Adversarial Latent-State Training for Robust Policies in Partially Observable Domains

    Mar 7, 2026Angad Singh AhujaRobust RLPartially Observable RL

    Constrained Image-Synthesis Lab

  16. Training for Trustworthy Saliency Maps: Adversarial Training Meets Feature-Map Smoothing

    Mar 7, 2026Dipkamal Bhusal, Md Tanvirul Alam, Nidhi RastogiGradient-Based AttributionExplanation Stability

    Rochester Institute of Technology

  17. Dual-Modality Multi-Stage Adversarial Safety Training: Robustifying Multimodal Web Agents Against Cross-Modal Attacks

    Mar 4, 2026Haoyu Liu, Dingcheng Li, Lukas Rutishauser +1Adversarial TrainingMultimodal Robustness

    UC Berkeley, IEOR & BAIR · Google · Google Deepmind

  18. Explanation-Guided Adversarial Training for Robust and Interpretable Models

    Mar 2, 2026Chao Chen, Yanhui Chen, Shanshan Lin +4Adversarial TrainingAdversarial Robustness

    Harbin Institute of Technology (Shenzhen) · Fuzhou University · NLPR, MAIS, Institute of Automation, Chinese Academy of Sciences

  19. Co-Evolutionary Multi-Modal Alignment via Structured Adversarial Evolution

    Mar 2, 2026Guoxin Shi, Haoyu Wang, Zaihui Yang +2Multimodal Multi-Turn Safety AlignmentAdversarial Training

    Nanyang Technological University · Tsinghua University

  20. S2O: Enhancing Adversarial Training with Second-Order Statistics of Weights

    Mar 1, 2026Gaojie Jin, Xinping Yi, Wei Huang +2Adversarial TrainingAdversarial Robustness

    Department of Computer Science, University of Exeter, Exeter, UK · National Mobile Communications Research Laboratory, Southeast University, Nanjing, China · Department of Computer Science, University of Liverpool, Liverpool, UK

  21. BiRQA: Bidirectional Robust Quality Assessment for Images

    Feb 23, 2026Aleksandr Gushchin, Dmitriy S. Vatolin, Anastasia AntsiferovaImage Quality AssessmentAdversarial Robustness

    ISP RAS Research Center for Trusted Artificial Intelligence, Moscow, Russia · MSU Institute for Artificial Intelligence, Moscow, Russia · Lomonosov Moscow State University, Moscow, Russia +1

  22. Decoupling Defense Strategies for Robust Image Watermarking

    Feb 23, 2026Jiahui Chen, Zehang Deng, Zeyu Zhang +3Robust WatermarkingAdversarial Robustness

    Tsinghua University · Swinburne University of Technology · The Australian National University +2

  23. Expanding the Role of Diffusion Models for Robust Classifier Training

    Feb 23, 2026Pin-Han Huang, Shang-Tse Chen, Hsuan-Tien LinAdversarial RobustnessAdversarial Training

    National Taiwan University

  24. On the Adversarial Robustness of Discrete Image Tokenizers

    Feb 20, 2026Rishika Bhagwatkar, Irina Rish, Nicolas Flammarion +1Adversarial RobustnessAdversarial Examples

    Mila - Quebec AI Institute · EPFL · ELLIS Institute Finland - Aalto University

  25. Benchmarking Adversarial Robustness and Adversarial Training Strategies for Object Detection

    Feb 18, 2026Alexis Winter, Jean-Vincent Martini, Romaric Audigier +2Adversarial Attacks on Object DetectorsAdversarial Robustness

    Universit´e Paris-Saclay, CEA, List, F-91191, Palaiseau, France.

  26. Closing the Distribution Gap in Adversarial Training for LLMs

    Feb 16, 2026Chengzhi Hu, Jonas Dornbusch, David Lüdke +2Adversarial TrainingAdversarial Robustness of Language Models

    Technical University of Munich, Germany.

  27. A swap-adversarial framework for domain generalization in pre- and post-stimulation Parkinsonian state classification

    Feb 11, 2026Seongwon Jin, Hanseul Choi, Sunggu Yang +2Adversarial TrainingData Augmentation

    Department of Computer Science and Engineering, Incheon National University, Yeonsu-gu, 22012, Incheon, Republic of Korea · Department of Nanobioengineering, Incheon National University, Yeonsu-gu, 22012, Incheon, Republic of Korea · Center for Brain-Machine Interface, Incheon National University, Yeonsu-gu, 22012, Incheon, Republic of Korea +1

  28. Adversarial Reward Auditing for Active Detection and Mitigation of Reward Hacking

    Feb 2, 2026Mohammad Beigi, Ming Jin, Junshan Zhang +2Adversarial TrainingReward Hacking

    Department of Computer Science, University of California, Davis, USA · Virginia Tech, Blacksburg, USA · Meta AI Research.

  29. 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 TrainingFake News Detection

    National Taiwan University, Taipei, Taiwan

  30. Noise-Aware and Dynamically Adaptive Federated Defense Framework for SAR Image Target Recognition

    Dec 31, 2025Yuchao Hou, Zixuan Zhang, Jie Wang +9Adversarial TrainingRemote Sensing

    Shanxi Normal University, Taiyuan, China · Guizhou University, Guiyang, China · Shanxi Key Laboratory of Cryptography and Data Security, School of Computer Science and Artificial Intelligence, Shanxi Normal University, Taiyuan 030031, China +15