SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.15735 · CVPR · 2023

Improving the Transferability of Adversarial Samples by Path-Augmented Method

Yichen Li, Xiaosen Wang, Jen-Tse Huang, Wenxuan Wang, Michael Lyu, Jianping Zhang, Weibin Wu, Yuxin Su

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Deep neural networks have achieved unprecedented success on diverse vision tasks. However, they are vulnerable to adversarial noise that is imperceptible to humans. This phenomenon negatively affects their deployment in real-world scenarios, especially security-related ones. To evaluate the robustness of a target model in practice, transfer-based attacks craft adversarial samples with a local model and have attracted increasing attention from researchers due to their high efficiency. The state-of-the-art transfer-based attacks are generally based on data augmentation, which typically augments multiple training images from a linear path when learning adversarial samples. However, such methods selected the image augmentation path heuristically and may augment images that are semantics-inconsistent with the target images, which harms the transferability of the generated adversarial samples. To overcome the pitfall, we propose the Path-Augmented Method (PAM). Specifically, PAM first constructs a candidate augmentation path pool. It then settles the employed augmentation paths during adversarial sample generation with greedy search. Furthermore, to avoid augmenting semantics-inconsistent images, we train a Semantics Predictor (SP) to constrain the length of the augmentation path. Extensive experiments confirm that PAM can achieve an improvement of over 4.8% on average compared with the state-of-the-art baselines in terms of the attack success rates.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2303.15735")
get_code_for_paper("2303.15735")
have("2303.15735")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2303.15735.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2303.15735.svg)](https://syntology.ai/paper/2303.15735)

Connect an agent — have() is free.