Combinatorial Attacks on Binarized Neural Networks

10/08/2018
by   Elias B. Khalil, et al.
0

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.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

02/11/2020

Robustness of Bayesian Neural Networks to Gradient-Based Attacks

Vulnerability to adversarial attacks is one of the principal hurdles to ...
11/20/2017

Verifying Neural Networks with Mixed Integer Programming

Neural networks have demonstrated considerable success in a wide variety...
03/11/2022

A Mixed Integer Programming Approach for Verifying Properties of Binarized Neural Networks

Many approaches for verifying input-output properties of neural networks...
03/26/2022

Efficient Global Robustness Certification of Neural Networks via Interleaving Twin-Network Encoding

The robustness of deep neural networks has received significant interest...
11/28/2018

A randomized gradient-free attack on ReLU networks

It has recently been shown that neural networks but also other classifie...
02/17/2020

Identifying Critical Neurons in ANN Architectures using Mixed Integer Programming

We introduce a novel approach to optimize the architecture of deep neura...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.