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 2306.16614cs.LGcs.AIcs.CRcs.CV
收藏

基于分组的鲁棒性:面向现实世界定制化鲁棒性的通用框架

Group-based Robustness: A General Framework for Customized Robustness in the Real World

Carnegie Mellon University(卡内基梅隆大学);Tel Aviv University(特拉维夫大学);Duke University(杜克大学)

Weiran Lin, Keane Lucas, Neo Eyal, Lujo Bauer, Michael K. Reiter, Mahmood Sharif

AI总结:

针对传统鲁棒性指标无法准确评估现实中分组定向攻击威胁的问题,研究提出基于分组的鲁棒性指标、配套的损失函数与攻击策略,以及可将该鲁棒性最高提升3.52倍的防御方法。

摘要:

众所周知,机器学习模型易受规避攻击的影响——这类攻击通过扰动模型输入来诱导错误分类。在本研究中,我们发现了现有攻击无法准确评估真实威胁的现实场景。具体而言,我们发现衡量定向鲁棒性和非定向鲁棒性的传统指标,无法恰当地反映模型抵御从一组源类别到另一组目标类别攻击的能力。为弥补现有方法的不足,我们正式定义了一种名为group-based robustness(基于分组的鲁棒性)的新指标,它是对现有指标的补充,更适合评估特定攻击场景下的模型性能。我们通过实验证明,在传统鲁棒性指标不适用的场景中,基于分组的鲁棒性能够区分模型对特定威胁模型的脆弱性。此外,为高效且准确地衡量基于分组的鲁棒性,我们1)提出了两种损失函数,2)提出了三种新的攻击策略。实验表明,在成功率相当的情况下,使用我们提出的新损失函数寻找规避样本,可节省的计算量最高可达目标类别数量的倍数;使用我们提出的新攻击策略寻找规避样本,与暴力搜索方法相比最多可节省99%的时间。最后,我们提出了一种防御方法,可将基于分组的鲁棒性最高提升3.52倍。

英文摘要:

Machine-learning models are known to be vulnerable to evasion attacks that perturb model inputs to induce misclassifications. In this work, we identify real-world scenarios where the true threat cannot be assessed accurately by existing attacks. Specifically, we find that conventional metrics measuring targeted and untargeted robustness do not appropriately reflect a model's ability to withstand attacks from one set of source classes to another set of target classes. To address the shortcomings of existing methods, we formally define a new metric, termed group-based robustness, that complements existing metrics and is better-suited for evaluating model performance in certain attack scenarios. We show empirically that group-based robustness allows us to distinguish between models' vulnerability against specific threat models in situations where traditional robustness metrics do not apply. Moreover, to measure group-based robustness efficiently and accurately, we 1) propose two loss functions and 2) identify three new attack strategies. We show empirically that with comparable success rates, finding evasive samples using our new loss functions saves computation by a factor as large as the number of targeted classes, and finding evasive samples using our new attack strategies saves time by up to 99\% compared to brute-force search methods. Finally, we propose a defense method that increases group-based robustness by up to 3.52$\times$.

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。

↑