An Intermediate-level Attack Framework on The Basis of Linear Regression

03/21/2022
by   Yiwen Guo, et al.
0

This paper substantially extends our work published at ECCV, in which an intermediate-level attack was proposed to improve the transferability of some baseline adversarial examples. We advocate to establish a direct linear mapping from the intermediate-level discrepancies (between adversarial features and benign features) to classification prediction loss of the adversarial example. In this paper, we delve deep into the core components of such a framework by performing comprehensive studies and extensive experiments. We show that 1) a variety of linear regression models can all be considered in order to establish the mapping, 2) the magnitude of the finally obtained intermediate-level discrepancy is linearly correlated with adversarial transferability, 3) further boost of the performance can be achieved by performing multiple runs of the baseline attack with random initialization. By leveraging these findings, we achieve new state-of-the-arts on transfer-based ℓ_∞ and ℓ_2 attacks.

READ FULL TEXT

page 7

page 9

research
08/20/2020

Yet Another Intermediate-Level Attack

The transferability of adversarial examples across deep neural network (...
research
07/23/2019

Enhancing Adversarial Example Transferability with an Intermediate Level Attack

Neural networks are vulnerable to adversarial examples, malicious inputs...
research
04/26/2023

Improving Adversarial Transferability via Intermediate-level Perturbation Decay

Intermediate-level attacks that attempt to perturb feature representatio...
research
06/22/2023

Rethinking the Backward Propagation for Adversarial Transferability

Transfer-based attacks generate adversarial examples on the surrogate mo...
research
08/01/2023

Robust Linear Regression: Phase-Transitions and Precise Tradeoffs for General Norms

In this paper, we investigate the impact of test-time adversarial attack...
research
04/22/2022

Enhancing the Transferability via Feature-Momentum Adversarial Attack

Transferable adversarial attack has drawn increasing attention due to th...
research
12/25/2017

Secure Network Code for Adaptive and Active Attacks with No-Randomness in Intermediate Nodes

We analyze the security for network code when the eavesdropper can conta...

Please sign up or login with your details

Forgot password? Click here to reset