Black-box Adversarial Example Generation with Normalizing Flows

07/06/2020
by   Hadi M. Dolatabadi, et al.
0

Deep neural network classifiers suffer from adversarial vulnerability: well-crafted, unnoticeable changes to the input data can affect the classifier decision. In this regard, the study of powerful adversarial attacks can help shed light on sources of this malicious behavior. In this paper, we propose a novel black-box adversarial attack using normalizing flows. We show how an adversary can be found by searching over a pre-trained flow-based model base distribution. This way, we can generate adversaries that resemble the original data closely as the perturbations are in the shape of the data. We then demonstrate the competitive performance of the proposed approach against well-known black-box adversarial attack methods.

READ FULL TEXT
research
07/15/2020

AdvFlow: Inconspicuous Black-box Adversarial Attacks using Normalizing Flows

Deep learning classifiers are susceptible to well-crafted, imperceptible...
research
09/14/2021

PETGEN: Personalized Text Generation Attack on Deep Sequence Embedding-based Classification Models

What should a malicious user write next to fool a detection model? Ident...
research
03/24/2018

Security Theater: On the Vulnerability of Classifiers to Exploratory Attacks

The increasing scale and sophistication of cyberattacks has led to the a...
research
04/26/2021

Delving into Data: Effectively Substitute Training for Black-box Attack

Deep models have shown their vulnerability when processing adversarial s...
research
01/15/2021

Black-box Adversarial Attacks in Autonomous Vehicle Technology

Despite the high quality performance of the deep neural network in real-...
research
11/08/2020

Adversarial Black-Box Attacks On Text Classifiers Using Multi-Objective Genetic Optimization Guided By Deep Networks

We propose a novel genetic-algorithm technique that generates black-box ...
research
11/30/2021

Black box tests for algorithmic stability

Algorithmic stability is a concept from learning theory that expresses t...

Please sign up or login with your details

Forgot password? Click here to reset