arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2304.02693cs.CVcs.CRcs.LG
收藏

图像分割模型的认证半径引导攻击框架

A Certified Radius-Guided Attack Framework to Image Segmentation Models

Huazhong University of Science and Technology(华中科技大学);Beijing Institute of Technology(北京理工大学);Illinois Institute of Technology(伊利诺伊理工学院)

Wenjie Qu, Youqi Li, Binghui Wang

AI总结:

针对图像分割模型易受对抗扰动影响的问题,提出认证半径引导攻击框架,利用像素认证半径设计白盒损失与黑盒PBGD攻击,实现渐近最优性能。

摘要:

图像分割是许多安全关键应用中的重要问题。近期研究表明,现代图像分割模型容易受到对抗性扰动的影响,而现有的攻击方法主要沿用攻击图像分类模型的思路。我们认为图像分割与分类存在固有差异,并专门为图像分割模型设计了一个攻击框架。我们的攻击框架受认证半径启发,该半径最初被防御者用于防御针对分类模型的对抗性扰动。我们首次从攻击者视角利用认证半径的性质,提出了一种针对图像分割模型的认证半径引导攻击框架。具体而言,我们首先将分类模型最先进的认证方法随机平滑(randomized smoothing)进行适配,以推导像素的认证半径。随后,我们更加注重破坏具有相对较小认证半径的像素,并设计了一种逐像素认证半径引导损失;将其插入任何现有白盒攻击中,即可得到我们的认证半径引导白盒攻击。接着,我们通过bandit提出了针对图像分割模型的首次黑盒攻击。基于bandit反馈,我们设计了一种新颖的梯度估计器,该估计器查询高效且可证明无偏、稳定。我们利用该梯度估计器设计了投影bandit梯度下降(PBGD)攻击,以及认证半径引导的PBGD(CR-PBGD)攻击。我们证明PBGD和CR-PBGD攻击能以最优速率实现渐近最优的攻击性能。我们在多个现代图像分割模型和数据集上评估了认证半径引导的白盒和黑盒攻击。结果验证了我们的认证半径引导攻击框架的有效性。

英文摘要:

Image segmentation is an important problem in many safety-critical applications. Recent studies show that modern image segmentation models are vulnerable to adversarial perturbations, while existing attack methods mainly follow the idea of attacking image classification models. We argue that image segmentation and classification have inherent differences, and design an attack framework specially for image segmentation models. Our attack framework is inspired by certified radius, which was originally used by defenders to defend against adversarial perturbations to classification models. We are the first, from the attacker perspective, to leverage the properties of certified radius and propose a certified radius guided attack framework against image segmentation models. Specifically, we first adapt randomized smoothing, the state-of-the-art certification method for classification models, to derive the pixel's certified radius. We then focus more on disrupting pixels with relatively smaller certified radii and design a pixel-wise certified radius guided loss, when plugged into any existing white-box attack, yields our certified radius-guided white-box attack. Next, we propose the first black-box attack to image segmentation models via bandit. We design a novel gradient estimator, based on bandit feedback, which is query-efficient and provably unbiased and stable. We use this gradient estimator to design a projected bandit gradient descent (PBGD) attack, as well as a certified radius-guided PBGD (CR-PBGD) attack. We prove our PBGD and CR-PBGD attacks can achieve asymptotically optimal attack performance with an optimal rate. We evaluate our certified-radius guided white-box and black-box attacks on multiple modern image segmentation models and datasets. Our results validate the effectiveness of our certified radius-guided attack framework.

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。

↑