Transferability Ranking of Adversarial Examples

08/23/2022
by   Mosh Levy, et al.
0

Adversarial examples can be used to maliciously and covertly change a model's prediction. It is known that an adversarial example designed for one model can transfer to other models as well. This poses a major threat because it means that attackers can target systems in a blackbox manner. In the domain of transferability, researchers have proposed ways to make attacks more transferable and to make models more robust to transferred examples. However, to the best of our knowledge, there are no works which propose a means for ranking the transferability of an adversarial example in the perspective of a blackbox attacker. This is an important task because an attacker is likely to use only a select set of examples, and therefore will want to select the samples which are most likely to transfer. In this paper we suggest a method for ranking the transferability of adversarial examples without access to the victim's model. To accomplish this, we define and estimate the expected transferability of a sample given limited information about the victim. We also explore practical scenarios: where the adversary can select the best sample to attack and where the adversary must use a specific sample but can choose different perturbations. Through our experiments, we found that our ranking method can increase an attacker's success rate by up to 80 ranking).

READ FULL TEXT
research
07/02/2020

Generating Adversarial Examples withControllable Non-transferability

Adversarial attacks against Deep Neural Networks have been widely studie...
research
01/06/2018

Adversarial Perturbation Intensity Achieving Chosen Intra-Technique Transferability Level for Logistic Regression

Machine Learning models have been shown to be vulnerable to adversarial ...
research
02/27/2018

Understanding and Enhancing the Transferability of Adversarial Examples

State-of-the-art deep neural networks are known to be vulnerable to adve...
research
02/28/2022

Enhance transferability of adversarial examples with model architecture

Transferability of adversarial examples is of critical importance to lau...
research
04/11/2017

The Space of Transferable Adversarial Examples

Adversarial examples are maliciously perturbed inputs designed to mislea...
research
12/03/2021

Attack-Centric Approach for Evaluating Transferability of Adversarial Samples in Machine Learning Models

Transferability of adversarial samples became a serious concern due to t...
research
03/18/2022

Concept-based Adversarial Attacks: Tricking Humans and Classifiers Alike

We propose to generate adversarial samples by modifying activations of u...

Please sign up or login with your details

Forgot password? Click here to reset