activity
20242026
collaborators

11 papers

cs.CR2026

OVIG: Optimistic Verification of AI Training Integrity via Gradient Signals

Hongxu Su, Jianzhu Yao, Huan Zhang +2

The rapid growth of AI has increased the demand for domain-specific post-training, while the cost and specialization of accelerator infrastructure push many model owners to outsour…

cs.CR2026

TAO: Tolerance-Aware Optimistic Verification for Floating-Point Neural Networks

Jianzhu Yao, Hongxu Su, Taobo Liao +4

Neural networks increasingly run on hardware outside the user's control (cloud GPUs, inference marketplaces). Yet ML-as-a-Service reveals little about what actually ran or whether…

cs.LG2026

Memory-Efficient Differentially Private Training with Gradient Random Projection

Alex Mulrooney, Devansh Gupta, James Flemings +4

Differential privacy (DP) protects sensitive data during neural network training, but standard methods like DP-Adam suffer from high memory overhead due to per-sample gradient clip…

cs.LG2026

Certified Training with Branch-and-Bound for Lyapunov-stable Neural Control

Zhouxing Shi, Haoyu Li, Cho-Jui Hsieh +1

We study the problem of learning verifiably Lyapunov-stable neural controllers that provably satisfy the Lyapunov asymptotic stability condition within a region-of-attraction (ROA)…

cs.LG2025

SoundnessBench: A Soundness Benchmark for Neural Network Verifiers

Xingjian Zhou, Keyi Shen, Andy Xu +4

Neural network (NN) verification aims to formally verify properties of NNs, which is crucial for ensuring the behavior of NN-based models in safety-critical applications. In recent…

cs.LG2025

PREMAP: A Unifying PREiMage APproximation Framework for Neural Networks

Xiyue Zhang, Benjie Wang, Marta Kwiatkowska +1

Most methods for neural network verification focus on bounding the image, i.e., set of outputs for a given input set. This can be used to, for example, check the robustness of neur…