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

509 papers35 papers in the last four weeks, down 34% on the four weeks before. 0.3% of all new papers.

  1. ATLAS-AL: Adaptive Trust-Region for Latent Adversarial Searches via Active Learning

    Oct 5, 2026Marsalis Gibson, Claire Tomlin, Shankar SastryAdversarial RobustnessActive Learning

  2. Transferable Adversarial Robustness for Speech Foundation Models via Hierarchical Stabilization

    Oct 4, 2026Aref Mousavi, Shahab Sherafat, Kiarash Kiani Feriz +4Adversarial Representation LearningSpeech Foundation Models

  3. FoSeRL: Formal Sequential Robustness Certification for Reinforcement Learning Policies

    Oct 3, 2026Sara Taheri, Deep Kumar Ganguly, Jan Křetínský +1Adversarial RobustnessCertified Robustness

  4. JASPER: Special Session on Joint Reliability And Security Assessment of SPlit Computing for Edge Robustness

    Oct 3, 2026Enrico Magliano, Giuseppe Esposito, Amir Hossein Shahdadian +13Edge ComputingAdversarial Robustness

  5. Aggregate accuracy conceals concentrated temporal vulnerability in a spiking speech classifier

    Oct 2, 2026İsmail Can DikmenAdversarial RobustnessSpiking Neural Networks

  6. CalCErt: Bin-wise Certification of Confidence Calibration in Medical Image Classification

    Oct 2, 2026Leo Fillioux, Stergios Christodoulidis, Stergios Christodoulidis +2Model CalibrationProbability Calibration

  7. Evolutionary Computation for Trustworthy AI: From Attacks and Defenses to Self-Evolving Era

    Oct 2, 2026Junhao Dong, Chenkai Wang, Xuanhui Lin +8Trust in AIAI Agent Safety

  8. When Normalization Selects the Sign: Auditing Robustness Ablations in Quantum Attention

    Oct 2, 2026Owen Friedewald, Srikar Alla, Ali Shiri Sichani +1Adversarial RobustnessQuantum Neural Networks

  9. SAGE: Similarity-Based Cleaning of Poisoned Training Data from Verified Examples

    Oct 1, 2026Chaeeun Han, Soodeh Atefi, Yevgeniy Vorobeychik +1Adversarial RobustnessData Poisoning Attacks

  10. Controllable Stochastic Quantization Encoding for Adversarially Robust Spiking Neural Networks

    Oct 1, 2026Yujia Liu, Peiyu Liu, Yajing Zheng +1Adversarial RobustnessSpiking Neural Networks

  11. Localisation-Aware Uncertainty for Pretrained Object Detection

    Oct 1, 2026Charmaine Barker, Daniel Bethell, Simos GerasimouEvidential Deep LearningUncertainty Quantification

  12. Robust Evidential Learning Through Latent Consistency

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

  13. Curvature Under Attack in hZACH-ViT: Gauge Symmetry, Boundary Saturation, and Adversarial Failure

    Sep 30, 2026Athanasios Angelakis, Marta Gomez-BarreroVision TransformerAdversarial Robustness

  14. Probabilistic Adversarial Training

    Sep 30, 2026Andi Zhang, Xingyu Zhao, Siddartha KhastgirAdversarial TrainingAdversarial Robustness

  15. LogiC-Diff: Embedding Security Properties Into AI-Enabled Cyber-Physical Systems

    Sep 29, 2026Ziyan An, John Stankovic, Meiyi MaCyber-Physical SystemsTime Series Forecasting

  16. Improving scalable oversight with co-trained monitors

    Sep 28, 2026Joseph H. Rudoler, Kevin Tan, Benedict Tessler +2Scalable OversightAdversarial Robustness

  17. No Free Efficiency: Revisiting the Trade-off Between Training Efficiency and Model Vulnerability

    Sep 27, 2026Yiyong Liu, Jun Sakuma, Michael Backes +1Adversarial RobustnessEfficient Language Model Training

  18. ZeroGAR: Benchmarking the Adversarial Robustness of Zero-Shot Graph Models

    Sep 27, 2026Zhongjian Zhang, Xiao Wang, Busheng Zhang +5Graph Representation LearningAdversarial Attacks

  19. AnchorRep: Defending LLMs Against Cross-Model Adversarial Transfer via Representation Repulsion

    Sep 26, 2026Gal Wertheizer, Rom Himelstein, Tomer Peretz +1Adversarial RobustnessAdversarial Robustness of Language Models

  20. Evasion Attacks on Cost-Utility-Based Adversarial Training for Online AutoML in IoT Networks

    Sep 25, 2026Chukwunonso Henry Nwokoye, Wajiha Zaheer, Khalil El-Khatib +1Adversarial RobustnessAdversarial Training

  21. JevAdvBench: A Benchmark and Black-Box Attacks for Reinforcement Learning for Calibrated Decisions Models

    Sep 25, 2026Jianyi Hu, Hangtao Zhang, Yi Liu +5Adversarial RobustnessBlack-Box Adversarial Attacks

  22. AERIAL: Adversarial Evaluation of Robustness in Accuracy-Preserving Low-Precision EEG Decoders

    Sep 24, 2026Saim Rehman, Muhammad ShafiqueQuantization-Aware TrainingEEG Decoding

  23. Upholding Robustness in Federated Learning: Trends, Emerging Strategies, and Research Opportunities

    Sep 23, 2026Pravija Raj P, Ashish Gupta, Andrea Augello +1Federated Learning AggregationAdversarial Robustness

  24. Adversarially Robust PAC Learning with Optimal VC Rates

    Sep 21, 2026Steve Hanneke, Amirreza ShaeiriSample ComplexityAdversarial Robustness

  25. Reinforcement Learning Inspired Black-box Adversarial Attacks for Computer Vision

    Sep 21, 2026Florian Krone, Elena Hoemann, Sven HallerbachAdversarial AttacksAdversarial Robustness