SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.02727 · 2024

Enhancing targeted transferability via feature space fine-tuning

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

Adversarial examples (AEs) have been extensively studied due to their potential for privacy protection and inspiring robust neural networks. Yet, making a targeted AE transferable across unknown models remains challenging. In this paper, to alleviate the overfitting dilemma common in an AE crafted by existing simple iterative attacks, we propose fine-tuning it in the feature space. Specifically, starting with an AE generated by a baseline attack, we encourage the features conducive to the target class and discourage the features to the original class in a middle layer of the source model. Extensive experiments demonstrate that only a few iterations of fine-tuning can boost existing attacks' targeted transferability nontrivially and universally. Our results also verify that the simple iterative attacks can yield comparable or even better transferability than the resource-intensive methods, which rest on training target-specific classifiers or generators with additional data. The code is available at: github.com/zengh5/TA_feature_FT.

For agents

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

get_harvested_code_for_paper("2401.02727")
get_code_for_paper("2401.02727")
have("2401.02727")

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

curl https://syntology.ai/api/ran/2401.02727.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.02727.svg)](https://syntology.ai/paper/2401.02727)

Connect an agent — have() is free.