Probabilistic Robustness Analysis for DNNs based on PAC Learning

by   Renjue Li, et al.

This paper proposes a black box based approach for analysing deep neural networks (DNNs). We view a DNN as a function f from inputs to outputs, and consider the local robustness property for a given input. Based on scenario optimization technique in robust control design, we learn the score difference function f_i-f_ℓ with respect to the target label ℓ and attacking label i. We use a linear template over the input pixels, and learn the corresponding coefficients of the score difference function, based on a reduction to a linear programming (LP) problems. To make it scalable, we propose optimizations including components based learning and focused learning. The learned function offers a probably approximately correct (PAC) guarantee for the robustness property. Since the score difference function is an approximation of the local behaviour of the DNN, it can be used to generate potential adversarial examples, and the original network can be used to check whether they are spurious or not. Finally, we focus on the input pixels with large absolute coefficients, and use them to explain the attacking scenario. We have implemented our approach in a prototypical tool DeepPAC. Our experimental results show that our framework can handle very large neural networks like ResNet152 with 6.5M neurons, and often generates adversarial examples which are very close to the decision boundary.


page 1

page 4

page 14

page 15

page 21

page 23

page 24

page 25


Amplification trojan network: Attack deep neural networks by amplifying their inherent weakness

Recent works found that deep neural networks (DNNs) can be fooled by adv...

Accelerating Robustness Verification of Deep Neural Networks Guided by Target Labels

Deep Neural Networks (DNNs) have become key components of many safety-cr...

Scenario Approach for Parametric Markov Models

In this paper, we propose an approximating framework for analyzing param...

Efficiently Finding Adversarial Examples with DNN Preprocessing

Deep Neural Networks (DNNs) are everywhere, frequently performing a fair...

DeepOpt: Scalable Specification-based Falsification of Neural Networks using Black-Box Optimization

Decisions made by deep neural networks (DNNs) have a tremendous impact o...

On Extensions of CLEVER: A Neural Network Robustness Evaluation Algorithm

CLEVER (Cross-Lipschitz Extreme Value for nEtwork Robustness) is an Extr...

Please sign up or login with your details

Forgot password? Click here to reset