Combinatorial Attacks on Binarized Neural Networks
Binarized Neural Networks (BNNs) have recently attracted significant interest due to their computational efficiency. Concurrently, it has been shown that neural networks may be overly sensitive to "attacks" - tiny adversarial changes in the input - which may be detrimental to their use in safety-critical domains. Designing attack algorithms that effectively fool trained models is a key step towards learning robust neural networks. The discrete, non-differentiable nature of BNNs, which distinguishes them from their full-precision counterparts, poses a challenge to gradient-based attacks. In this work, we study the problem of attacking a BNN through the lens of combinatorial and integer optimization. We propose a Mixed Integer Linear Programming (MILP) formulation of the problem. While exact and flexible, the MILP quickly becomes intractable as the network and perturbation space grow. To address this issue, we propose IProp, a decomposition-based algorithm that solves a sequence of much smaller MILP problems. Experimentally, we evaluate both proposed methods against the standard gradient-based attack (FGSM) on MNIST and Fashion-MNIST, and show that IProp performs favorably compared to FGSM, while scaling beyond the limits of the MILP.
Code (0)
등록된 구현이 없습니다.
Tasks
Computational EfficiencySimilar Papers 제목 키워드 기반
BinarizedAttack: Structural Poisoning Attacks to Graph-based Anomaly Detection
Graph-based Anomaly Detection (GAD) is becoming prevalent due to the powerful representation abilities of graphs as well as recent advances in graph mining techniques. These GAD tools, however, expose a new attacking sur…
Anomaly DetectionCombinatorial OptimizationGraph MiningRepresentation LearningTowards adversarial robustness with 01 loss neural networks
Motivated by the general robustness properties of the 01 loss we propose a single hidden layer 01 loss neural network trained with stochastic coordinate descent as a defense against adversarial attacks in machine learnin…
Adversarial RobustnessBinary ClassificationARBiBench: Benchmarking Adversarial Robustness of Binarized Neural Networks
Network binarization exhibits great potential for deployment on resource-constrained devices due to its low computational cost. Despite the critical importance, the security of binarized neural networks (BNNs) is rarely …
Adversarial RobustnessBenchmarkingBinarizationBinarizing Physics-Inspired GNNs for Combinatorial Optimization
Physics-inspired graph neural networks (PI-GNNs) have been utilized as an efficient unsupervised framework for relaxing combinatorial optimization problems encoded through a specific graph structure and loss, reflecting …
Neural Models for Output-Space Invariance in Combinatorial Problems
Recently many neural models have been proposed to solve combinatorial puzzles by implicitly learning underlying constraints using their solved instances, such as sudoku or graph coloring (GCP). One drawback of the propos…
Node Classification