pith. sign in

arxiv: 2508.02987 · v1 · pith:XYCS6ZYJnew · submitted 2025-08-05 · 💻 cs.CV

Adversarial Attention Perturbations for Large Object Detection Transformers

classification 💻 cs.CV
keywords afogdetectionadversarialobjectdetectorsperturbationsattentiontransformers
0
0 comments X
read the original abstract

Adversarial perturbations are useful tools for exposing vulnerabilities in neural networks. Existing adversarial perturbation methods for object detection are either limited to attacking CNN-based detectors or weak against transformer-based detectors. This paper presents an Attention-Focused Offensive Gradient (AFOG) attack against object detection transformers. By design, AFOG is neural-architecture agnostic and effective for attacking both large transformer-based object detectors and conventional CNN-based detectors with a unified adversarial attention framework. This paper makes three original contributions. First, AFOG utilizes a learnable attention mechanism that focuses perturbations on vulnerable image regions in multi-box detection tasks, increasing performance over non-attention baselines by up to 30.6%. Second, AFOG's attack loss is formulated by integrating two types of feature loss through learnable attention updates with iterative injection of adversarial perturbations. Finally, AFOG is an efficient and stealthy adversarial perturbation method. It probes the weak spots of detection transformers by adding strategically generated and visually imperceptible perturbations which can cause well-trained object detection models to fail. Extensive experiments conducted with twelve large detection transformers on COCO demonstrate the efficacy of AFOG. Our empirical results also show that AFOG outperforms existing attacks on transformer-based and CNN-based object detectors by up to 83% with superior speed and imperceptibility. Code is available at https://github.com/zacharyyahn/AFOG.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Out-of-the-box: Black-box Causal Attacks on Object Detectors

    cs.CV 2025-12 unverdicted novelty 6.0

    BlackCAtt creates smaller, explainable black-box attacks on object detectors by targeting minimal causal pixel sets, outperforming or matching standard methods and acting as a meta-algorithm when combined with them.