Some Complexity Results for Robustness Verification for Binarized Neural Networks
This paper studies the computational complexity of verification problems for Binarized Neural Networks (BNNs).
The paper provides a novel analysis of the computational complexity of BNN verification, including a reduction from SAT and a polynomial-time robustness-checking algorithm.
Before reading this…
To understand this paper, make sure you know these concepts first:
- Boolean satisfiability problem (SAT)find papers →
- neural networksfind papers →
Abstract
More Like ThisThis paper studies the computational complexity of verification problems for Binarized Neural Networks (BNNs), where activations (and sometimes weights) are binary. We analyze two problems: satisfiability and robustness under uniform image occlusion. We show that BNN satisfiability is NP-complete via a reduction from Boolean satisfiability problem (SAT), and that uniform occlusion induces a piecewise-constant structure in the network output, enabling a polynomial-time robustness-checking algorithm.