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. Sparse Fine-Tuning for Parameter-Efficient Adversarial Training

    Oct 29, 2026Zhaoxin Wang, Zihang Ding, Handing WangAdversarial TrainingAdversarial Robustness

    School of Artificial Intelligence, Xidian University, Xi’an, China

  2. Adversarial Self-Distillation

    Oct 28, 2026Mohammad Sadegh Akhondzadeh, Soroush H. Zargarbashi, Aleksandar BojchevskiAdversarial Robustness of Language ModelsSafety-Preserving Fine-Tuning of Language Models

    University of Cologne · CISPA Helmholtz Center for Information Security

  3. A Separation Principle for Adversarial Attacks and Defense of Graph Neural Networks

    Oct 28, 2026Farid Mafi, Saber Jafarpour, Mohammad PiraniAdversarial AttacksGraph Neural Networks

    University of Waterloo, Waterloo, ON, Canada · University of Colorado Boulder, Boulder, CO, USA · University of Ottawa, Ottawa, ON, Canada

  4. MANTIS: Multi-Axis News Transformations for Instance-Wise Stress Testing and Worst-Case Training in Fake News Detection

    Oct 26, 2026Dexin Liu, Fan Yang, Zimu Wang +5Fake News DetectionAdversarial Robustness

    Xi’an Jiaotong-Liverpool University, Suzhou, China · University of Liverpool, Liverpool, United Kingdom · Nanjing Sibei Intelligent Technology Co., Ltd., Nanjing, China

  5. Attack logics, not outputs: Concept-based Property Attacks for Shortcut Elimination in Neural Networks

    Oct 26, 2026Raik Dankworth, Felix Mächtle, Thomas Eisenbarth +1Adversarial AttacksAdversarial Robustness

    Institute of Software Engineering and Programming Languages University of Luebeck · Institute of IT Security University of Luebeck

  6. StaX-Net: Stackelberg Interleaved Asymmetric Network for Cross-Modality Medical Image Translation

    Oct 25, 2026Amin Golnari, Saeid SaneiImage-to-Image TranslationMedical Image Synthesis

    College of Engineering & Computer Science, VinUniversity, Hanoi, Vietnam · College of Health Science, VinUniversity, Hanoi, Vietnam · Institute of Psychiatry, Psychology & Neuroscience, King’s College London, UK

  7. Augmentation-Guided Adversarial Training via Local Stability-Based Sample Selection

    Oct 23, 2026Daniel Agyei Asante, Mark Tetteh, Deborah Asamoah +2Adversarial TrainingAdversarial Robustness

    Ohio University, United States · University of Nebraska Omaha, United States · University of Toronto, Canada +1

  8. Towards Adversarially Robust Multigraph Neural Networks for Financial Crime Analysis

    Oct 22, 2026Dennis Heijmans, H. Çağrı Bilgi, Rui Wang +1Adversarial AttacksAdversarial Robustness

    Delft University of Technology Delft, The Netherlands

  9. ExGrad: Beyond Suppression - Explicit Clean-Gradient Subtraction in Adversarial Training

    Oct 21, 2026Zhiyuan Ye, Xiangyu Zhou, Ji Qi +2Adversarial TrainingAdversarial Robustness

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

  10. Adversarial Post-Training of Foundation Models for High-Frequency Trading

    Oct 19, 2026Alexandre Bismuth, Kang Li, Aramis Marti-Shahandeh +3Limit Order Book ModelingAdversarial Training

    British Open-ended Learning and Discovery Lab (BOLD), Department of Computer Science, University of Oxford, Oxford, United Kingdom · Harvard University, Cambridge, MA, United States · British Open-ended Learning and Discovery Lab (BOLD), Department of Statistics, University of Oxford, Oxford, United Kingdom +1

  11. Peer Pressure: Execution-Verified Co-Evolution of Attacker and Defender Populations for Code Security

    Oct 17, 2026Khushbu Pahwa, Yubin Ge, Daniele Bonadiman +2AI Agent SecurityAdversarial Training

    AWS AI

  12. Contrastive Adversarial Training for Robust Graph Neural Networks under Label Poisoning

    Oct 17, 2026Manshika Charvi Bissessur, Melis Ilayda Bal, Michael MuehlebachGraph Neural NetworksRobust Classification

    University of Oxford · Max Planck Institute for Intelligent Systems, Tübingen, Germany · LIONS – École Polytechnique Fédérale de Lausanne +1

  13. On the tradeoff between robustness and geometric accuracy in adversarial training

    Oct 16, 2026Rachel Morris, Ryan Murray, Kerrek StinsonAdversarial RobustnessRobust Classification

  14. CAT-alyzing Honesty: Continuous Adversarial Training for Transferable LLM Honesty

    Oct 15, 2026Yuan-Chen Chang, Niklas Herbster, Gauthier Gidel +1LLM HonestyLLM Alignment

    Tara Research · Mila – Quebec AI Institute · Technical University of Munich

  15. Bias Mitigation in Audio-Enabled LLMs through Adversarial Training and Distillation Methods

    Oct 15, 2026Adnan Al Ali, Jindřich Libovický, Anne LauscherAdversarial DebiasingLanguage Model Debiasing

    Charles University, Faculty of Mathematics and Physics, Czech Republic · Trustworthy AI Lab, University of Hamburg, Germany

  16. Personalized Projected Ascent for Federated Stackelberg Optimization

    Oct 15, 2026M Yashwanth, Sharannya Ghosh, Saikiran Bulusu +1Federated LearningStochastic Gradient Descent

    Indian Institute of Science, Bangalore · CISPA, Germany · IIIT-Hyderabad

  17. AgentSafeEvo: Adversarial Co-Evolution for LLM Agent Safety

    Oct 14, 2026Chenxu Wang, Xiaoyu Wen, Han Qi +4LLM Agent SafetyAdversarial Training

    Shanghai Artificial Intelligence Laboratory · Fudan University · Shanghai Jiaotong University +1

  18. TRACER: Trace-Regularized Training Against Indirect Prompt Injection

    Oct 13, 2026Kshitij Mishra, Salem Lahlou, Nils LukasIndirect Prompt InjectionPrompt Injection Defense

    Mohamed bin Zayed University of Artificial Intelligence Abu Dhabi, United Arab Emirates

  19. Adaptive Compression and Targeted Perturbation: A Unified Framework for Generalized Audio Deepfake Detection

    Oct 12, 2026Jianqiao Cui, Haoxian Zhu, Hanbiao Meng +1Audio Deepfake DetectionAudio Deepfake Detection Robustness

    Imperial College London, London, UK · Taiyuan University of Technology, Taiyuan, China

  20. [Re] Boosting the Visual Interpretability of CLIP via Adversarial Fine-Tuning

    Oct 10, 2026Anton Nuzhdin, Andrei Gruzitski, Balázs Egyed +1VLM InterpretabilitySaliency Map Evaluation

    University of Amsterdam

  21. Adversarial Gradient Forcing for Robust Few-Step Autoregressive Video Generation

    Oct 10, 2026Chenxi Xia, Yixuan Xu, Shan Liu +7Autoregressive Video GenerationLong-Horizon Video Generation

    Zhejiang University · Alibaba Group · Nanjing University

  22. When Listening Becomes Easier: Scrubbing Visual Cues for Shortcut-Free VLAs

    Oct 7, 2026Jasper Gerigk, Kenzo Aspuru-Takata, Chin-Hsuan Wu +3Vision-Language-Action ModelsRobustness of VLA Models

    University of Toronto, Toronto, ON M5S 3H5, Canada · Vector Institute, Toronto, ON M5G 0C6, Canada

  23. Explaining the Saliency Map Sparsity of Adversarially-Trained Neural Networks

    Oct 7, 2026Yannick Lunk, Atell Yehor Krasnopolsky, Damien Garreau +1Adversarial TrainingGradient-Based Attribution

    Institute of Mathematics University of Würzburg, Germany · Technical University of Munich, Germany · Institute of Computer Science, CAIDAS University of Würzburg, Germany +1

  24. Breaking Adversarial Transferability in Fine-Tuned Speech Recognition

    Oct 6, 2026Mojtaba Nafez, Aref Mousavi, Mohammad Ebrahim Mahdavi +3Adversarial TransferabilityAutomatic Speech Recognition

    Department of Computer Engineering Sharif University of Technology · Department of Computer Engineering University of Isfahan

  25. AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model

    Oct 6, 2026Sarim Hashmi, Mukul Ranjan, Kshitij Mishra +3Adversarial TrainingSim-to-Real Transfer

    Mohamed bin Zayed University of Artificial Intelligence · Amazon · Massachusetts Institute of Technology

  26. Adversarially Trained Linear Transformers Are Optimal Robust In-Context Learners for Gaussian Mixtures

    Oct 6, 2026Soichiro KumanoAdversarial TrainingTransformer

    LY Corporation

  27. Improving Synthetic Data Generation for Argument Mining via Adversarial Reinforcement Learning

    Oct 6, 2026Zhijun Zhang, Qianlong Wang, Keyang Ding +5Adversarial TrainingArgument Mining

    College of Applied Science, Shenzhen University, Shenzhen, China · School of Artificial Intelligence, Shenzhen Technology University, Shenzhen, China · Harbin Institute of Technology (Shenzhen), Shenzhen, China +2

  28. Adversarial Training for Deep Hedging in Nonstationary Markets

    Oct 5, 2026Philipp J. Schneider, Lukas Looser, Antoine Garin +2Adversarial TrainingQuantitative Finance

    Risk Analytics and Optimization Chair, EPFL, Lausanne, Switzerland · University of Waterloo, Waterloo, Canada

  29. Online AutoML: Evaluating Poisoning Attacks on Cost-Utility Adversarial Training Defence Strategy for IoT Networks

    Oct 5, 2026Chukwunonso Henry Nwokoye, Khalil El-Khatib, Li YangAdversarial TrainingInternet of Things

    Faculty of Business and Information Technology, Ontario Tech University, Oshawa, Ontario, Canada · Department of Computer Science, Alex Ekwueme Federal University, Nigeria

  30. Target-free Latent Safety Alignment

    Oct 3, 2026Luoyu Chen, Weiqi Wang, Chenhan Zhang +3LLM Safety AlignmentAdversarial Robustness of Language Models

    University of Technology Sydney, Sydney, NSW, Australia · Xi’an Jiaotong University, Xi’an, Shaanxi, China · Southeast University, Nanjing, Jiangsu, China +1