Stress-Testing Neural Network Verifiers with Provably Robust Instances

ArXi:2605.17153v1 Announce Type: new Neural network verifiers aim to provide formal guarantees on model behavior, but existing verification benchmarks are fundamentally limited by their lack of ground-truth labels. As a result, verifier evaluation relies on indirect heuristics, which prevents exact scoring and systematic study of verifier failure modes. We address this gap by