Some Complexity Results for Robustness Verification for Binarized Neural Networks
This paper investigates the computational complexity of verification problems for Binarized Neural Networks (BNNs). Researchers demonstrated that BNN satisfiability is NP-complete by reducing it from the Boolean satisfiability problem (SAT). Additionally, they found that uniform image occlusion results in a piecewise-constant network output, allowing for a polynomial-time algorithm to check robustness. AI
IMPACT Establishes theoretical limits for BNN verification, potentially guiding future research in efficient and robust model design.