Neural Network Verification

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

141 papers11 papers in the last four weeks, down 35% on the four weeks before. 0.1% of all new papers.

  1. Zonotopic Analysis of Quantization Error in Neural Networks

    Nov 18, 2026Robert Debbas, Éric Goubault, Sylvie PutotNeural Network VerificationNeural Network Quantization

  2. The 7th International Verification of Neural Networks Competition (VNN-COMP 2026): Summary and Results

    Nov 18, 2026Tobias Ladner, Konstantin Kaulen, Stanley Bak +6Neural Network Verification

  3. BernBRS: Certified Backward Reachability for Deep Bernstein Neural Networks

    Nov 17, 2026Ibrahim Albool, Yasser ShoukryNeural Network VerificationReachability Analysis

  4. Hyperlyve: Parallelized Enumeration and Exact Lyapunov Stability Certification for Deep ReLU Networks

    Nov 16, 2026Brian Yarbrough, Jesse Wayment, Jingbo Wang +2Neural Network StabilityLyapunov Stability

  5. Learning and Verifying Stabilizing Controllers with Structured Neural Control Lyapunov Functions

    Nov 16, 2026Jose Luis Ledesma Martin, Patricia PauliControl Lyapunov FunctionsNeural Network Verification

  6. Conv-Reluplex: A Verification Framework For Convolution Neural Networks

    Nov 11, 2026Jin Xu, Zishan Li, Miaomiao Zhang +1Neural Network VerificationConvolutional Neural Networks

  7. Scalable Neural Safety Certification via Monotonicity

    Nov 8, 2026Amirreza Alavi, Majid Zamani, Saber JafarpourMonotone Neural NetworksDynamical Systems

  8. Robustness Verification against Patch Attacks via Group-Lasso Semidefinite Relaxation

    Nov 3, 2026Yukina Nakagawa, Takami Sato, Ken Kobayashi +1Neural Network VerificationCertified Robustness

  9. Iterated Narrow Networks: Turing Completeness at Width 4 on Convex Input Spaces and the Complexity of Verification

    Nov 2, 2026Olivier Bournez, Johanne Cohen, Adrian WurmReLU Neural NetworksNeural Network Verification

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

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

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

    Oct 22, 2026Jonas Fingerhut, Lukas Koller, Matthias AlthoffNeural Network VerificationMonotone Neural Networks

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

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

  13. Certified neural approximations for parabolic obstacle problems

    Oct 16, 2026Davood DamircheliNeural PDE SolversPartial Differential Equations

  14. Certified Robustness via Sparse Second-Order Cone Relaxations

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

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

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

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

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

  17. 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

  18. 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

  19. Security Properties of Neural Networks as Decision Problems

    Sep 30, 2026Adrian WurmNeural Network VerificationAdversarial Attacks

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

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

  21. CLAD: Constrained Abstract Domain for Neural Network Verification

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

  22. Verifying Neural Networks with Reinforcement Learning

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

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

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

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

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

  25. Learning Provable Neural Network Observer for Uncertain Dynamical Systems

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