Scalable Parallel Verification of Quantized Neural Networks via MIQCP Optimization Encoding
Quantized Neural Networks are widely used in safety-critical systems due to their efficiency, yet they remain vulnerable to adversarial perturbations. Existing verification approaches based on the Big-<inline-formula> <tex-math notation="LaTeX">$M$ </tex-math></inline-formula> Mixed-Integer Linear Programming (MILP) su...