# Transform-Dependent Adversarial Attacks

Source: [Transform-Dependent Adversarial Attacks](<https://www.sota2.com/research/paper/68fa775b1e209131cea72ad0>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:16:49.987Z

Authors: Yaoteng Tan, Zikui Cai, M. Salman Asif

Published: 2024-06-12T17:31:36.000Z

## Abstract

Deep networks are highly vulnerable to adversarial attacks, yet conventional attack methods utilize static adversarial perturbations that induce fixed mispredictions. In this work, we exploit an overlooked property of adversarial perturbations--their dependence on image transforms--and introduce transform-dependent adversarial attacks. Unlike traditional attacks, our perturbations exhibit metamorphic properties, enabling diverse adversarial effects as a function of transformation parameters. We demonstrate that this transform-dependent vulnerability exists across different architectures (e.g., CNN and transformer), vision tasks (e.g., image classification and object detection), and a wide range of image transforms. Additionally, we show that transform-dependent perturbations can serve as a defense mechanism, preventing sensitive information disclosure when image enhancement transforms pose a risk of revealing private content. Through analysis in blackbox and defended model settings, we show that transform-dependent perturbations achieve high targeted attack success rates, outperforming state-of-the-art transfer attacks by 17-31% in blackbox scenarios. Our work introduces novel, controllable paradigm for adversarial attack deployment, revealing a previously overlooked vulnerability in deep networks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2406.08443>)

[PDF](<https://arxiv.org/pdf/2406.08443.pdf>)
