Attack Agnostic Statistical Method for Adversarial Detection

11/22/2019
by   Sambuddha Saha, et al.
0

Deep Learning based AI systems have shown great promise in various domains such as vision, audio, autonomous systems (vehicles, drones), etc. Recent research on neural networks has shown the susceptibility of deep networks to adversarial attacks - a technique of adding small perturbations to the inputs which can fool a deep network into misclassifying them. Developing defenses against such adversarial attacks is an active research area, with some approaches proposing robust models that are immune to such adversaries, while other techniques attempt to detect such adversarial inputs. In this paper, we present a novel statistical approach for adversarial detection in image classification. Our approach is based on constructing a per-class feature distribution and detecting adversaries based on comparison of features of a test image with the feature distribution of its class. For this purpose, we make use of various statistical distances such as ED (Energy Distance), MMD (Maximum Mean Discrepancy) for adversarial detection, and analyze the performance of each metric. We experimentally show that our approach achieves good adversarial detection performance on MNIST and CIFAR-10 datasets irrespective of the attack method, sample size and the degree of adversarial perturbation.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/22/2020

Maximum Mean Discrepancy is Aware of Adversarial Attacks

The maximum mean discrepancy (MMD) test, as a representative two-sample ...
research
09/10/2019

Learning to Disentangle Robust and Vulnerable Features for Adversarial Detection

Although deep neural networks have shown promising performances on vario...
research
03/27/2023

Diffusion Denoised Smoothing for Certified and Adversarial Robust Out-Of-Distribution Detection

As the use of machine learning continues to expand, the importance of en...
research
06/08/2019

Strategies to architect AI Safety: Defense to guard AI from Adversaries

The impact of designing for security of AI is critical for humanity in t...
research
02/07/2020

RAID: Randomized Adversarial-Input Detection for Neural Networks

In recent years, neural networks have become the default choice for imag...
research
09/10/2019

FDA: Feature Disruptive Attack

Though Deep Neural Networks (DNN) show excellent performance across vari...

Please sign up or login with your details

Forgot password? Click here to reset