Certified Robustness

Ask about this topic

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

86 papers12 papers in the last four weeks, up 100% on the four weeks before. 0.1% of all new papers.

  1. A Certified Robustness Framework for Backdoor Poisoning Attacks using ff-Divergences

    Oct 26, 2026Evan Rose, Alina OpreaCertified RobustnessData Poisoning Attacks

    Northeastern University

  2. Towards Certifiable State Estimation under Observability Degeneracy

    Oct 14, 2026Baoshan SongRobot State EstimationSemidefinite Programming

  3. Certified Robustness via Sparse Second-Order Cone Relaxations

    Oct 12, 2026Mohammadreza Maleki, Daniel Sadig, Rushendra Sidibomma +3Convex RelaxationSecond-Order Cone Programming

    Toronto Metropolitan University · University of Minnesota Twin Cities · Johns Hopkins University +2

  4. Adversarial Detection for Pre-trained Classifiers via Lipschitz-Margin Analysis with Certification

    Oct 11, 2026Rui Zhang, Xinle Cao, Huazhen Yu +2Adversarial Example DetectionAdversarial Robustness

    Nanjing University of Aeronautics and Astronautics · The State Key Laboratory of Blockchain and Data Security, Zhejiang University · Nanjing University of Information Science and Technology

  5. Neural Network Verification for Deep Joint Source-Channel Coding

    Oct 8, 2026Thanh Le, Hai Duong, Takeshi Matsumura +1Deep Joint Source-Channel CodingCertified Robustness

    Wireless Systems Laboratory, National Institute of Information and Communication Technology, Yokosuka, Kanagawa, Japan · George Mason University, Fairfax, VA, USA

  6. MRCert: Towards Post-deployment Patch Robustness Certification for Adversarially Patched Samples via Type-specific Masking

    Oct 7, 2026Qilin Zhou, Zhengyuan Wei, Haipeng Wang +3Adversarial RobustnessCertified Robustness

    City University of Hong Kong · The Education University of Hong Kong

  7. Removing Information Content Does Not Certify Tamper Resistance in Open-Weight Models

    Oct 6, 2026Domenic Rosati, Alessa Carbo, Ali Dadsetan +5Certified RobustnessMachine Unlearning

    Dalhousie University · Vector Institute · Johns Hopkins University +1

  8. Lipschitz Thinking: Ten Years of Certifiable-by-Design Robust Neural Networks

    Oct 5, 2026Fabio Brau, Giorgio Piras, Maura Pintor +1Neural Network RobustnessCertified Robustness

    Department of Electrical and Electronic Engineering, University of Cagliari, Cagliari, Italy

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

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

    LMU Munich, Germany · TUM, Munich, Germany · Masaryk University, Brno, Czech Republic +1

  10. Bounded Reachability & Jailbreak Detection via Contraction-Constrained State Space Models

    Oct 2, 2026Omanshu ThapliyalCertified RobustnessState Space Models

    Strategic Data Solutions Lab, Hitachi America Ltd. Santa Clara, CA 94086, USA

  11. The Geometry of Randomized Smoothing on Feasible Sets

    Sep 30, 2026Syed Izhan Khilji, Alireza Furutanpey, Schahram DustdarRandomized SmoothingSelective Prediction

    Technische Universität Wien · NeverBlink · Technische Universität Wien Universitat Pompeu Fabra

  12. Interpretable but Fragile? Robustness of Concept Bottlenecks under Geometric-Semantic Perturbations

    Sep 29, 2026Hanwei Zhang, Tianma Hu, Gaojie Jin +2Concept Bottleneck ModelsCertified Robustness

    Department of Computer Science, Saarland University, Saarbrücken, Germany · School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China · Department of Artificial Intelligence & Institute of Artificial Intelligence and Brain Sciences, University of Macau, Macau SAR, China +1

  13. When a Flatness Proxy Is Not a Function: Robustness Certificates and Training Interventions

    Sep 29, 2026Vicente Opazo, Jose Calatayud-Mateu, Cristobal Rojas +1Flat MinimaCertified Robustness

    Centro Nacional de Inteligencia Artificial (CENIA) · Barcelona Supercomputing Center (BSC) · Pontificia Universidad Cat´olica de Chile

  14. LipSSM: Structurally Lipschitz-Bounded Cascaded State-Space Model via Metric Transfer between Consecutive SSM Layers

    Sep 25, 2026Natsuki Yoshino, Ren Uchida, Kazuki Matsumoto +1Lipschitz Neural NetworksNeural Network Robustness

    Tokyo University of Agriculture and Technology (TUAT), Tokyo, Japan

  15. Reachability-Based Formal Verification of Graph Neural Networks with Node and Edge Features

    Sep 24, 2026Anne M. Tumlin, Ben Wooding, Zhenxuan Shao +3Neural Network VerificationReachability Analysis

    Vanderbilt University, Nashville, TN, USA

  16. What Can a Recurrent State Safely Forget?

    Sep 20, 2026Linzhe Zhang, Changming XuRecurrent Neural NetworksCertified Robustness

    Graduate School, Northeastern University.

  17. Certifying Lower Bounds for Risk-Sensitive Reinforcement Learning under Adversarial State Perturbations

    Sep 9, 2026Tong Li, Saunak Kumar Panda, Yisha XiangRisk-Sensitive RLAdversarial Perturbations

    Department of Industrial and Systems Engineering, University of Houston, 4302 University Dr, Houston, 77004, TX, USA. · Department of Decision and Information Science, University of Houston, 4302 University Dr, Houston, 77004, TX, USA.

  18. Towards a Resilience-Theoretic Foundation for Adversarial Robustness in Industrial Control System Anomaly Detection

    Sep 7, 2026Branka Stojanović, Andreas Flatscher, Michael SommaCyber-Physical SystemsAdversarial Robustness

    1JOANNEUM RESEARCH Forschungsgesellschaft mbH, Austria · 2TU Graz, Institute for Technical Informatics, Austria

  19. Certified Safety Radii in Forecast-Error Space for Wasserstein Distributionally Robust Small Signal Stability-Constrained AC Optimal Power Flow via Lifted Spectrahedral Containment

    Aug 31, 2026Ziqi Zhang, Xi ChenOptimal Power FlowDistributionally Robust Optimization

    College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211100, China

  20. Robust Validation to Geometric Perturbations for Autonomous Pose Estimation

    Aug 21, 2026Gregoire Theau, Melanie DucoffeCertified RobustnessObject Pose Estimation

    Airbus SAS, France

  21. KAN-Robust-Bench: A Benchmark for Evaluating the Robustness of Kolmogorov-Arnold Networks

    Aug 21, 2026Mohammad Meymani, Roozbeh Razavi-FarAdversarial RobustnessKolmogorov-Arnold Networks

    Trustworthy and Secure AI (TSAI) Lab, Faculty of Computer Science, University of New Brunswick, Fredericton, Canada

  22. Certified Multi-Turn Robustness for LLM Safety via Compositional Bounds and Safety Persistence

    Aug 21, 2026Yang Liu, Bin Chong, Wenkai Yang +9Adversarial Robustness of Language ModelsLanguage Model Robustness

    Peking University · Renmin University of China · Tsinghua University +2

  23. Uncovering the Limits of Proof Sharing for Neural Networks

    Aug 19, 2026Kanak Das, Shubham Ugare, Bor-Yuh Evan Chang +3Abstract InterpretationNeural Network Verification

    University of California, Riverside · University of Illinois Urbana-Champaign · University of Colorado Boulder & Amazon

  24. Certified but Private: Scalable Zero-Knowledge Proofs for Neural Network Guarantees

    Aug 17, 2026Youwei Zhong, Ben Merbaum, Timos Antonopoulos +4Certified RobustnessNeural Network Verification

    Yale University · University of Illinois Urbana-Champaign

  25. Quality-Diversity Stress Tests for Process Reward Models:What Archive Coverage Can and Cannot Certify

    Aug 8, 2026Ibne Farabi Shihab, Fariya AfrinProcess Reward ModelsAdversarial Attacks

    Department of Computer Science, Iowa State University · Department of Computer Science, Kalinga Institute of Industrial Technology

  26. 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)

  27. CAGE: Certified Authorization under Typed-Return Uncertainty for Tool-Using Agents

    Jul 31, 2026Blaise Delattre, Cong Wang, Yang CaoLLM Agent SecurityTool-Using Agents

    Department of Computer Science, School of Computing, Institute of Science Tokyo, Tokyo, Japan · City University of Hong Kong

  28. Certified Training for Convolutional Perturbations

    Jul 20, 2026Benedikt Brückner, Alessio LomuscioImage Corruption RobustnessNeural Network Robustness

    Safe Intelligence · Imperial College London

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

    Jul 15, 2026Zhenpeng LiRandomized SmoothingNetwork Intrusion Detection

  30. Trustworthy Machine Learning through the Lens of Combinatorial Optimization: Survey and Research Perspectives

    Jul 8, 2026Thibaut Vidal, Julien FerryInterpretable MLCertified Robustness

    CIRRELT & SCALE-AI Chair in Data-Driven Supply Chains, Department of Mathematics and Industrial Engineering, Polytechnique Montreal, Montreal, Canada