arXiv AI
Aug 3
Learning Lookahead Lemmas for Neural Network Verification
arXiv:2607. 29051v1 Announce Type: cross Abstract: State-of-the-art neural network verifiers use the branch-and-bound procedure as their core solving mechanism.
PICID: Proof-Driven Clause Learning in Neural Network Verification
Related stories
arXiv AI
Jun 11
\texttt{Range-Arithmetic}: Verifiable Deep Learning Inference on an Untrusted Party
arXiv:2505. 17623v2 Announce Type: replace-cross Abstract: Verifiable computing (VC) has gained prominence in decentralized machine learning systems, where resource-intensive tasks like deep neural network (DNN) inference are offloaded to external participants due to blockchain limitations.
arXiv Machine Learning
Sep 23
Exploring Solver-Level Warmstarting for Neural Network Verification
arXiv:2609.25962v1 Announce Type: new Abstract: Neural network verification has become a key tool for providing formal guarantees on the behaviour of neural networks. However, many verification probl...
arXiv Machine Learning
Aug 21
Uncovering the Limits of Proof Sharing for Neural Networks
arXiv:2608. 19351v1 Announce Type: new Abstract: Robustness verification of neural networks is increasingly important, due to their use in many critical domains.
arXiv AI
Aug 28
ProofEvolve: Neuro-Symbolic Evolution for Formal Automated Theorem Proving
ProofEvolve is a neuro‑symbolic framework that evolves formally verified symbolic proof structures alongside neural models to expand the knowledge boundary in automated theorem proving. The neural component proposes variation operators such as decompositions, repairs, and schema recombinations, while the Lean kernel verifies every proof transition, ensuring formal soundness. Across three competition‑level Lean benchmarks, ProofEvolve achieves the highest average solve rate among evaluated proof systems.
arXiv Machine Learning
Jun 4
veriFIRE: an Industrial Case Study in Verifying Consistency Properties for a DNN-Based Wildfire Detection System
arXiv:2606. 04121v1 Announce Type: cross Abstract: We present our ongoing work on the veriFIRE project: a collaboration between industry and academia, aimed at applying verification to increase the reliability of a real-world, safety-critical system.
arXiv Machine Learning
Aug 19
Certified but Private: Scalable Zero-Knowledge Proofs for Neural Network Guarantees
PANDA is a scalable system that uses zero‑knowledge proofs to certify the robustness and fairness of neural networks without revealing their private parameters. Built on the CROWN robustness framework, PANDA introduces a novel algorithm for proving linear relaxation bounds on non‑linear activation layers, producing lightweight proofs. The system can generate proofs for networks with over 2.9 million parameters in just five minutes and verify them in ten seconds, scaling polynomially with network size and enabling verification of models four orders of magnitude larger than prior ZKP‑based approaches.
arXiv Machine Learning
Aug 14
Branch and Bound for Relational Verification of Neural Networks
arXiv:2608. 13118v1 Announce Type: new Abstract: Verification of neural networks against relational specifications, such as global robustness, is crucial for safety-critical applications of cyber-physical systems (CPS), given their increasing adoption of AI components.
arXiv AI
Jun 16
Mask-Proof: An LLM-based Automated Data Curation Pipeline on Mathematical Proofs
arXiv:2606. 15258v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly capable of mathematical problem solving and can even assist with research-level proofs, yet we still lack a scalable and reproducible way to measure step-level reasoning in long proofs across diverse sources.
Hugging Face Trending Papers
Aug 13
Branch and Bound for Relational Verification of Neural Networks
Verification of neural networks against relational specifications, such as global robustness, is crucial for safety-critical applications of cyber-physical systems (CPS), given their increasing adoption of AI components. Compared to simple trace properties (e.
arXiv Machine Learning
Sep 15
Neuron Activation-based Computation of Logical Explanations for Deep Neural Networks
The paper introduces a flexible symbolic framework that efficiently computes logical explanations for deep neural networks by parameterizing explanations with internal neuron activations and leveraging general-purpose logical engines like SMT solvers. Unlike previous methods that rely on specialized verifiers or are limited to individual input features, this approach is not restricted in shape and can scale to deep architectures. Experiments on image recognition and medical benchmarks demonstrate improved computational efficiency and the ability to explain networks that were previously intractable for logic-based methods.
arXiv AI
Jul 21
Lookahead Branching for Neural Network Verification
arXiv:2607. 17290v1 Announce Type: cross Abstract: In this work, we investigate the effect of lookahead branching strategies in neural network verification.