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. QuISE: Defense against Typographic Attacks on VLMs via Query-Irrelevant Semantic Editing

    Aug 13, 2026Shubin Lu, Jiaqi Yin, Yihao HuangVLM RobustnessAdversarial Attacks on VLMs

    School of Software, Northwestern Polytechnical University, Xi’an, China · Software Engineering Institute, East China Normal University, Shanghai, China

  2. SeFaR: Semantic Feature-aware Robustness Testing of Deep Neural Networks

    Aug 10, 2026Nusrat Jahan Mozumder, Divya Gopinath, Corina Pasareanu +1Neural Network VerificationNeural Network Robustness

    University of Virginia · USA · KBR Inc., NASA Ames +1

  3. Agentic Harnesses: LLM-Driven Verification Layers for Robot Autonomy

    Aug 10, 2026Rohan Bhagra, Mahantesh Halapannavar, Uddhav BhattaraiLarge Language Model-Based Robot PlanningAdversarial Robustness

    Carnegie Mellon University, Department of Information Systems

  4. Confusion-Geometry Rebalancing for Long-Tailed Adversarial Training

    Aug 10, 2026Mengnan Zhao, Geyong Min, Lihe Zhang +2Adversarial TrainingLong-Tailed Classification

    School of Computer Science, Anhui University, China · Department of Computer Science, University of Exeter, UK · School of Information and Communication Engineering, Dalian University of Technology, China +1

  5. Distilling Vision-Language Models for Robust Traffic Sign Perception in Autonomous Vehicles

    Aug 9, 2026Pedram MohajerAnsari, Amir Salarpour, Mert D. PeséAdversarial RobustnessVLM Distillation

    Clemson University, Clemson, SC, USA

  6. TOFD: Target-Oriented Feature Decoupling against Poisoning Attacks in Split Federated Learning

    Aug 7, 2026Yuhan Xie, Jingrong Huang, Chen LyuAdversarial RobustnessSplit Federated Learning

    Shanghai University of Finance and Economics MoE Key Laboratory of Interdisciplinary Research of Computation and Economics Shanghai, China

  7. Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers

    Aug 7, 2026Ridma Jayasundara, Shaheer Mohamed, Tharindu Fernando +6Adversarial AttacksAdversarial Robustness

    Signal Processing, Artificial Intelligence and Vision Technologies Group (SAIVT), Queensland University of Technology · Institute of High-Performance Computing, Agency for Science, Technology and Research, Singapore · School of Computing, National University of Singapore +1

  8. Universal Concept Disruption for SAM3 Image Segmentation

    Aug 6, 2026Hao Wang, Yuxuan Zhang, Wei YangPromptable Image SegmentationAdversarial Robustness

    School of Computer Science and Technology, University of Science and Technology of China, Hefei, China · School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China · Suzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou, China +1

  9. CohortHijack: Robustness of Single Cell Annotation to Companion Cell Removal

    Aug 6, 2026Arash Vashagh, Yasmin VashaghAdversarial RobustnessSingle-Cell Transcriptomics

    Faculty of Computer Science, University of New Brunswick, Fredericton, New Brunswick E3B 5A3, Canada · Farzanegan Amin 2 High School, Isfahan, Iran

  10. MOAT: Model-Agnostic Randomized Transformations for preventing Efficiency Degradation Attacks on ViTs

    Aug 5, 2026Anadi Goyal, Nandish Chattopadhyay, Chandan Karfa +2Adversarial AttacksVision Transformer

    Indian Institute of Technology Guwahati, India · Nanyang Technological University, Singapore · Prince of Songkla University, Phuket Campus

  11. Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecycle

    Aug 5, 2026Jiaming Zhang, Boyang Chen, Zherui Li +14Data ProvenanceAdversarial Robustness

    College of Computing and Data Science, Nanyang Technological University, Singapore · School of Computing and Information Systems, University of Melbourne, Australia · School of Computing and Information Systems, Singapore Management University, Singapore +3

  12. Adversarially Robust Abductive Fusion of Pre-trained Transformer-based Perception Models

    Aug 4, 2026Mario Leiva, Yue Ma, Qinru Qiu +2Distribution ShiftAbductive Reasoning

    1DCIC, Universidad Nacional del Sur (UNS) & ICIC (UNS-CONICET), Bahía Blanca, Argentina · 2Syracuse University, Syracuse, NY USA

  13. Understanding Fault Tolerance of Adversarially Robust Pruned Models

    Aug 4, 2026Manali Dangarikar, Cory MerkelAdversarial TrainingNeural Network Robustness

    Brain Lab Rochester Institute of Technology Rochester, NY, USA

  14. Double Down on Defense: Strengthening Deep Perceptual Hashes against Evasion Attacks without Retraining

    Aug 4, 2026Bangjie Sun, Nayoung Kim, Mun Choon Chan +1Image MatchingAdversarial Robustness

    National University of Singapore (NUS) · Korea Advanced Institute of Science and Technology (KAIST)

  15. Does the Competitive Component of Adversarial Self-Play Improve Legal Reasoning? A Controlled Negative Result

    Aug 3, 2026Miseog Shawn KimAdversarial RobustnessReinforcement Learning with Verifiable Rewards

    Preprint, 2026-08-02

  16. No Single Neuron of Failure: Distributed Safety Alignment Against White-Box Attacks

    Aug 2, 2026Simiao Xie, Chuancheng Shi, Shangze Li +5LLM AlignmentAdversarial Attacks on LLMs

    The University of Sydney · NExT++ Research Centre, National University of Singapore

  17. ZAPs: A Reward Attribution Framework for DeFi Ecosystems with Adversarial-Robust Scoring via Parallel Anomaly Ensemble Detection

    Jul 30, 2026Girish G N, Ashutosh Sahoo, Ajay Bhat +4Adversarial RobustnessFinancial Fraud Detection

    Zeru Finance · The Ohio State University, USA

  18. Improving the Robustness/Accuracy Tradeoff Against Adversarial Attacks Using Information Bottleneck Distillation Through Dual Teachers

    Jul 30, 2026Vincent Ryusuke Takahashi, Yoshinari Takeishi, Jun'ichi Takeuchi +1Adversarial TrainingNeural Network Robustness

    Joint Graduate School of Mathematics for Innovation Kyushu University · Faculty of Information Science and Electrical Engineering Kyushu University · Université Savoie Mont Blanc

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

    Jul 30, 2026Qingzhao ZhangAdversarial AttacksAdversarial Robustness

    The University of Arizoan

  20. EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability

    Jul 27, 2026Andrea Ponte, Daniel Gibert, Matous Kozak +5Efficient InferenceAdversarial Robustness

    Department of Informatics, Bioengineering, Robotics and Systems Engineering, University of Genova, Italy · Artificial Intelligence Research Institute (IIIA-CSIC), Spain · Department of Information Security at Faculty of Information Technology, CTU in Prague, Czech Republic +2

  21. Distribution-Specific Curvature Control with Finite-Sample Guarantees for Open-Weight Safety

    Jul 24, 2026Domenic Rosati, Ali Dadsetan, Hong Huang +5Adversarial RobustnessLLM Safety Alignment

    1Dalhousie University · 2Vector Institute for Artificial Intelligence · 3Indian Institute of Management Bangalore

  22. Detectors Learn the Wrong Thing: Shortcut-Resistant Adversarial Training Against Physically Realizable Attacks

    Jul 23, 2026Yuanhao Huang, Yilong Ren, Jinlei Wang +3Adversarial TrainingAdversarial Robustness

    School of Transportation Science and Engineering, Beihang University, 100191, Beijing, P.R China · Zhongguancun Laboratory, 100191, Beijing, P.R China · School of Systems Science and Engineering, Sun Yat-Sen University, 510006, Guangzhou, P.R China +2

  23. Adversarial Frontiers: Minimum-Norm Attack Ensembles for Robustness Evaluation

    Jul 22, 2026Luca Scionis, Luca Melis, Maura Pintor +5Adversarial AttacksNeural Network Robustness

    Sapienza University of Rome, Italy · University of Cagliari, Italy · University of Genoa, Italy

  24. A New Kind of Adversarial Example: Measuring the Human-Model Gap, and Its Relationship to OOD Detection

    Jul 22, 2026Ali BorjiAdversarial RobustnessAdversarial Examples

    BrainChip Inc., Laguna Hills, CA, USA

  25. 1-Lipschitz Neural Networks on Hadamard Manifolds

    Jul 21, 2026Davide Murari, Marta Ghirardelli, Ben Adcock +3Riemannian Neural NetworksNeural Network Robustness

    Department of Applied Mathematics and Theoretical Physics, University of Cambridge · Department of Mathematical Sciences, Norwegian University of Science and Technology (NTNU) · Department of Mathematics, Simon Fraser University

  26. Adversarial Robustness of Phishing Email Detection: A Comparative Study of TF-IDF + Logistic Regression and Fine-Tuned DistilBERT

    Jul 20, 2026Tanveer Ahmed, Seyedali PourmoafilAdversarial RobustnessCybersecurity

    School of Physics, Engineering and Computer Science, University of Hertfordshire, Hatfield, Herts AL10 9AB, United Kingdom

  27. A Multi-Model Hybrid Defense Approach Against White-box Adversarial Attacks in Computer Network Traffic

    Jul 19, 2026Khushnaseeb RoshanNetwork Intrusion DetectionAdversarial Robustness

    Department of Computer Science, Aligarh Muslim University (AMU), Aligarh, INDIA

  28. Boundary-Seeking GAN-Augmented TabTransformer for Adversarially Robust Intrusion Detection

    Jul 17, 2026Raihan Sultan Pasha Basuki, Aliyah KurniasihSynthetic Data AugmentationTransformer

    Department of Computer Science, Universitas Ary Ginanjar, Menara 165, Cilandak No.kav 1 Lt 2 & 18, Jakarta Selatan, 12560, DKI Jakarta, Indonesia

  29. Random Logit Scaling: Defending Deep Neural Networks Against Black-Box Score-Based Adversarial Example Attacks

    Jul 16, 2026Hamid Dashtbani, Mehdi Dousti Gandomani, AmirMahdi SadeghzadehAdversarial RobustnessBlack-Box Adversarial Attacks

    Department of Computer Engineering Sharif University of Technology

  30. Traffic-Aware Randomized Smoothing for LLM-Based Network Intrusion Detection

    Jul 15, 2026Zhenpeng LiRandomized SmoothingNetwork Intrusion Detection