arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.16494cs.CV
收藏

对抗鲁棒性及对抗训练策略的基准测试:目标检测

Benchmarking Adversarial Robustness and Adversarial Training Strategies for Object Detection

Alexis Winter, Jean-Vincent Martini, Romaric Audigier, Angelique Loesch, Bertrand Luvison

AI总结:

本文提出统一基准框架,评估目标检测模型对抗鲁棒性及训练策略,发现基于Transformer的架构对抗转移性差,混合攻击数据集训练效果最佳。

摘要:

目标检测模型是自动化系统如自动驾驶车辆和基于感知的机器人中的关键组件,但它们对对抗性攻击的敏感性带来了严重的安全风险。在防御这些模型的进展中,进展落后于分类,受缺乏标准化评估的阻碍。几乎不可能彻底比较攻击或防御方法,因为现有工作使用不同的数据集、不一致的效率指标和不同的扰动成本测量方法。本文通过研究三个关键问题来填补这一空白:(1)我们如何创建一个公平的基准来公平比较攻击?(2)现代攻击在不同架构之间(尤其是从卷积神经网络到视觉Transformer)的转移性如何?(3)最有效的对抗训练策略是什么?为回答这些问题,我们首先提出一个专注于数字、非补丁攻击的统一基准框架。该框架引入了特定的指标来分离定位和分类错误,并使用多种感知指标评估攻击成本。使用此基准,我们对最先进的攻击和广泛的检测器进行了广泛的实验。我们的发现揭示了两个主要结论:第一,针对目标检测模型的现代对抗性攻击在基于Transformer的架构中表现出显著的转移性不足。第二,我们证明了最稳健的对抗训练策略利用了一组混合高扰动攻击的混合数据集,这些攻击具有不同的目标(例如空间和语义),其性能优于任何单一攻击的训练。

英文摘要:

Object detection models are critical components of automated systems, such as autonomous vehicles and perception-based robots, but their sensitivity to adversarial attacks poses a serious security risk. Progress in defending these models lags behind classification, hindered by a lack of standardized evaluation. It is nearly impossible to thoroughly compare attack or defense methods, as existing work uses different datasets, inconsistent efficiency metrics, and varied measures of perturbation cost. This paper addresses this gap by investigating three key questions: (1) How can we create a fair benchmark to impartially compare attacks? (2) How well do modern attacks transfer across different architectures, especially from Convolutional Neural Networks to Vision Transformers? (3) What is the most effective adversarial training strategy for robust defense? To answer these, we first propose a unified benchmark framework focused on digital, non-patch-based attacks. This framework introduces specific metrics to disentangle localization and classification errors and evaluates attack cost using multiple perceptual metrics. Using this benchmark, we conduct extensive experiments on state-of-the-art attacks and a wide range of detectors. Our findings reveal two major conclusions: first, modern adversarial attacks against object detection models show a significant lack of transferability to transformer-based architectures. Second, we demonstrate that the most robust adversarial training strategy leverages a dataset composed of a mix of high-perturbation attacks with different objectives (e.g., spatial and semantic), which outperforms training on any single attack.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑