Neural Network Verification

Ask about this topic

Overview

Neural network verification asks whether a model satisfies precise properties, such as resisting bounded input perturbations or keeping a controller within a safe region. Common approaches include interval and linear bound propagation, abstract interpretation, reachability analysis, and solver-based methods such as mixed-integer programming and branch-and-bound. Researchers are extending these techniques from feed-forward classifiers to transformers, recurrent and graph networks, and closed-loop control systems, while also developing benchmarks, proof systems, and tools for trustworthy execution. A central challenge is balancing sound guarantees and tight bounds against the time and memory required, especially for large models and realistic arithmetic.

Latest papers

CardsList

126 papers16 papers in the last four weeks, up 7% on the four weeks before. 0.1% of all new papers.

  1. Sparse Sum-of-Squares Layers for Certified Learning

    Oct 25, 2026Ege Gursoy, Nicolas MansardSemidefinite ProgrammingDifferentiable Optimization

    LAAS-CNRS · ANITI

  2. Convex Equilibrium Potentials for Monge--Ampère: Curvature Bounds and A Posteriori Evaluation

    Oct 22, 2026Edison Vázquez, Yingdong Lu, Tomasz NowickiNeural PDE SolversPartial Differential Equations

    Departamento de Matemáticas, CINVESTAV, México · IBM Research, Thomas J. Watson Research Center, Yorktown Heights, New York, USA

  3. Training Mixed-Monotone Neural Networks for Verification Without Set Propagation

    Oct 22, 2026Jonas Fingerhut, Lukas Koller, Matthias AlthoffNeural Network VerificationNeural Network Optimization

    Technical University of Munich

  4. Enumeration-Guided Training of Neural Hamilton-Jacobi Safety Certificates

    Oct 20, 2026Mihaela-Larisa Clement, Tosca Pierro, Ezio Bartocci +1Safety-Critical ControlReachability Analysis

    TU Wien, Vienna, Austria · AIT Austrian Institute of Technology, Vienna, Austria · Università Politecnica delle Marche, Italy

  5. Certified neural approximations for parabolic obstacle problems

    Oct 16, 2026Davood DamircheliNeural PDE SolversPartial Differential Equations

    Department of Mathematics, Louisiana State University, Baton Rouge, 70803, LA, USA

  6. Masked Attention Pooling Is Invariant to Padding and Permutation: A Formal Proof in Lean

    Oct 12, 2026Yusuf Khaled Sadek, Enes YilmazMultiple Instance LearningPermutation-Invariant Learning

    The Ohio State University, Columbus, OH, USA

  7. 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

  8. 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

  9. zkLLMPoT: Efficient Zero Knowledge Proof of Training for Large Language Models

    Oct 6, 2026Junkai Liang, Zhanpeng Guo, Pengfei Wu +5Zero-Knowledge MLLLM Auditing

    Peking University · Singapore Management University · China Telecom Quantum Information Technology Group Co., Ltd +1

  10. Toward AI Trustworthiness: Finding Analytically Proven Forward-Invariant Sets for AI-Controlled Systems

    Oct 5, 2026Haoyang Song, Xikun Yang, Qixin WangNeural Network VerificationTrust in AI

    Department of Computing, The Hong Kong Polytechnic University, Hong Kong SAR, China.

  11. Certified Mechanistic Edits: Behavioral Guarantees for Skill Removal and Preservation

    Oct 2, 2026Md Sazid Uddin, Md. Khairul Alam Mazumder, M. F. MridhaMachine UnlearningNeural Network Verification

    Department of Computer Science American International University-Bangladesh (AIUB), Dhaka, Bangladesh

  12. Security Properties of Neural Networks as Decision Problems

    Sep 30, 2026Adrian WurmNeural Network VerificationAdversarial Attacks

    BTU Cottbus–Senftenberg, Lehrstuhl Theoretische Informatik Platz der Deutschen Einheit 1, 03046 Cottbus, Germany

  13. Stochastic World Models for Verifying Vision-Based Neural Feedback Systems

    Sep 29, 2026I. Samuel Akinwande, Mykel J. Kochenderfer, Clark BarrettNeural Surrogate ModelingNeural Network Verification

    Department of Aeronautics and Astronautics, Stanford University · Department of Computer Science, Stanford University

  14. CLAD: Constrained Abstract Domain for Neural Network Verification

    Sep 28, 2026Hai Duong, Thanh Le, ThanhVu NguyenNeural Network VerificationNeural Network Robustness

    Department of Computer Science George Mason University Fairfax, VA, USA · Unaffiliated Yokosuka, Japan

  15. Verifying Neural Networks with Reinforcement Learning

    Sep 28, 2026Hai Duong, Thanh Le, ThanhVu NguyenNeural Network VerificationBranch and Bound

    Department of Computer Science George Mason University Fairfax, VA, USA · Unaffiliated Yokosuka, Japan

  16. ZonoGPT: Towards An Abstract Domain for Verifying Large GPT Models

    Sep 28, 2026Hai Duong, Thanh Le, ThanhVu NguyenNeural Network VerificationAbstract Interpretation

    Department of Computer Science George Mason University Fairfax, VA, USA · Unaffiliated Yokosuka, Japan

  17. AC Power Flow Contingency Analysis Using a Single Deep Neural Network

    Sep 25, 2026Md Obaidur Rahman, Junjie Qin, Vassilis KekatosPower SystemsNeural Surrogate Modeling

    Elmore Family School of Electrical and Computer Engineering Purdue University, West Lafayette, IN 47906

  18. Learning Provable Neural Network Observer for Uncertain Dynamical Systems

    Sep 25, 2026Zhangyi Wang, Jiaxu Liu, Song Chen +2Neural Network StabilityLyapunov Stability

    College of Control Science and Engineering, Zhejiang University, China · School of Science, Huzhou Normal University, China · Department of Mathematics, National University of Singapore, Singapore

  19. 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

  20. NNV3: Expanding Neural Network Verification to New Architectures and Domains

    Sep 24, 2026Anne M. Tumlin, Samuel Sasaki, Ben Wooding +8Neural Network VerificationReachability Analysis

    Vanderbilt University, USA · The University of Texas at Dallas, USA

  21. Exploring Solver-Level Warmstarting for Neural Network Verification

    Sep 22, 2026Annelot Bosman, Minghao Liu, Marta Kwiatkowska +2Neural Network Verification

    Leiden Institute of Advanced Computer Science, Leiden · University of Oxford, United Kingdom · Chair for AI Methodology, RWTH Aachen University, Germany +1

  22. Scalable Incremental Robustness Analysis of Neural Network Feedback Systems

    Sep 18, 2026Zichen Wang, Peter Seiler, Geir Dullerud +1Neural Network ControlNeural Network Robustness

    Coordinated Science Laboratory and the Department of Electrical and Computer Engineering, University of Illinois Urbana–Champaign · Department of Electrical Engineering and Computer Science, at the University of Michigan · Electrical and Computer Engineering Department at the University of Minnesota

  23. OPEN-1B: A Fully Auditable Training Run

    Sep 15, 2026John Donaghy, Brian Wilcox, Oğuzhan Ersoy +6Neural Network VerificationLLM Auditing

    Gensyn

  24. Certified Inference and Training for Deep Equilibrium Networks: A Continuation Framework with Polynomial Complexity Guarantees

    Sep 15, 2026Alex BorisevichNeural Network Verification

  25. Certified Uncertainty Propagation in One-Shot Federated Bayesian Models via Posterior Event Transport

    Sep 14, 2026Mahyar Mohammadi, Mohammad Hossein Badiei, Abolfazl Yaghmaei +1Bayesian Neural NetworksNeural Network Verification

    School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, 1417614411, Iran · School of Computer Science, Institute for Research in Fundamental Sciences (IPM), P.O. Box 19395-5746, Tehran, Iran

  26. Closing the Loop: Branch-and-Bound for Scalable Verification of Nonlinear Neural Feedback Systems

    Sep 14, 2026I. Samuel Akinwande, Mykel J. Kochenderfer, Clark BarrettNeural Network VerificationBranch and Bound

    Department of Aeronautics and Astronautics, Stanford University Stanford, CA, 94305, USA · Department of Computer Science, Stanford University Stanford, CA, 94305, USA

  27. The Misery of Mechanistic Interpretability: A Formal Perspective

    Sep 14, 2026Tobias Ladner, Matthias AlthoffNeural Network VerificationLLM Interpretability

    Technical University of Munich, Germany

  28. Neuron Activation-based Computation of Logical Explanations for Deep Neural Networks

    Sep 12, 2026Tomáš Kolárik, Faezeh Labbaf, Fabrizio Leopardi +3Explainable Artificial IntelligenceNeural Network Interpretability

    University of Lugano (USI), Lugano, Switzerland · Florida State University, United States of America · SUPSI, IDSIA, Lugano, Switzerland

  29. Testing Between the Test Cases: Proving End-to-End Steering in Conditions You Never Drove

    Sep 10, 2026Menuka Ghalan, Charles Rodgers, Zachary D. AsherNeural Network VerificationEnd-to-End Autonomous Driving

    Department of Computer Science, Western Michigan University, Kalamazoo, MI, USA · Department of Mechanical and Aerospace Engineering, Western Michigan University, Kalamazoo, MI, USA

  30. Replay-Gated Neural Execution: Decoupling Persistent Behavioral Specifications from Neural Realizations in Frozen Language Models

    Sep 5, 2026Xianliang Zeng, Zhanzhan ZhaoRuntime Enforcement for AI AgentsNeural Network Verification

    The Chinese University of Hong Kong, Shenzhen Shenzhen, China