Overview

Certified robustness studies whether a model’s predictions or actions remain safe within a defined range of perturbations, rather than relying only on empirical attack tests. Common approaches include interval bound propagation, convex relaxations and branch-and-bound verification, Lipschitz bounds, and randomized smoothing; exact methods such as mixed-integer programming can provide stronger guarantees on smaller problems. Researchers apply these tools to image and language models, transformers, time-series systems, reinforcement-learning agents, and safety-critical applications, using benchmarks such as MNIST, CIFAR, and ImageNet as well as domain-specific tests. A central challenge is balancing tight, realistic certificates with the computation needed to obtain them, especially when perturbations involve semantic changes, physical conditions, multiple input types, or finite-precision execution.

Latest papers

CardsList

99 papers10 papers in the last four weeks, down 29% on the four weeks before. 0.1% of all new papers.

  1. Learning Better Certified Models from Empirically-Robust Teachers

    Feb 2, 2026Alessandro De PalmaCertified RobustnessAdversarial Knowledge Distillation

  2. Feature-Space Smoothing: Certified Robustness of Deep Representations

    Jan 22, 2026Song Xia, Meiwen Ding, Chenqi Kong +2Adversarial RobustnessCertified Robustness

  3. Pareto DNN Verification: Fast for Most Queries

    Dec 23, 2025Yizhak Y. Elboher, Avraham Raviv, Amihay Elboher +3Neural Network VerificationCertified Robustness

  4. Dual Randomized Smoothing: Beyond Global Noise Variance

    Dec 1, 2025Chenhao Sun, Yuhao Mao, Martin VechevRandomized SmoothingNeural Network Robustness

  5. Towards the Worst-case Robustness of Large Language Models

    Jan 31, 2025Huanran Chen, Zeming Wei, Yao Huang +2Adversarial Robustness of Language ModelsAdversarial Attacks on LLMs

  6. Expressiveness of Multi-Neuron Convex Relaxations in Neural Network Certification

    Oct 9, 2024Yuhao Mao, Yani Zhang, Martin VechevNeural Network VerificationConvex Relaxation

  7. Training Verifiably Robust Agents Using Set-Based Reinforcement Learning

    Aug 17, 2024Manuel Wendl, Lukas Koller, Tobias Ladner +1RL ControlReinforcement Learning

  8. Understanding Certified Training with Interval Bound Propagation

    Jun 17, 2023Yuhao Mao, Mark Niklas Müller, Marc Fischer +1Neural Network VerificationNeural Network Robustness