Safety Verification and Robustness Analysis of Neural Networks via Quadratic Constraints and Semidefinite Programming
share
Analyzing the robustness of neural networks against norm-bounded uncertainties and adversarial attacks has found many applications ranging from safety verification to robust training. In this paper, we propose a semidefinite programming (SDP) framework for safety verification and robustness analysis of neural networks with general activation functions. Our main idea is to abstract various properties of activation functions (e.g., monotonicity, bounded slope, bounded values, and repetition across layers) with the formalism of quadratic constraints. We then analyze the safety properties of the abstracted network via the S-procedure and semidefinite programming. Compared to other semidefinite relaxations proposed in the literature, our method is less conservative, especially for deep networks, with an order of magnitude reduction in computational complexity. Furthermore, our approach is applicable to any activation functions.
READ FULL TEXT