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 2406.00775cs.LGcs.CR
收藏

约束自适应攻击:针对表格数据深度神经网络的有效对抗攻击

Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular Data

University of Luxembourg(卢森堡大学);LIST / RIKEN AIP(LIST / 理化学研究所人工智能项目)

Thibault Simonetto, Salah Ghamizi, Maxime Cordy

AI总结:

针对表格数据深度模型对抗鲁棒性评估的空白,本文提出自适应梯度攻击CAPGD及结合MOEVA的高效规避攻击CAA,在多数实验设置下显著降低模型准确率且速度快,建议将其作为表格机器学习防御的最低测试标准。

摘要:

针对表格数据的最先进深度学习模型最近达到了可在工业环境中部署的 acceptable 性能。然而,这些模型的鲁棒性仍鲜有探索。与计算机视觉不同,由于表格数据的内在属性(如分类特征、不可变性和特征关系约束),目前没有有效的攻击方法来正确评估深度表格模型的对抗鲁棒性。为了填补这一空白,我们首先提出了 CAPGD,这是一种通过自适应机制克服现有梯度攻击失败的梯度攻击。这种新攻击不需要参数调整,并且与先前的梯度攻击相比,进一步将准确率降低了高达 81 个百分点。其次,我们设计了 CAA,这是一种高效的规避攻击,结合了我们的 CAPGD 攻击和最佳的基于搜索的攻击 MOEVA。我们在五种架构和四个关键用例上证明了我们攻击的有效性。我们的实证研究表明,CAA 在 20 种设置中的 17 种中优于所有现有攻击,与 CAPGD 和 MOEVA 相比,分别导致准确率下降了高达 96.1 个百分点和 21.9 个百分点,同时速度比 MOEVA 快达五倍。鉴于我们新攻击的有效性和高效性,我们认为它们应成为表格机器学习中任何新防御或鲁棒架构的最低测试标准。

英文摘要:

State-of-the-art deep learning models for tabular data have recently achieved acceptable performance to be deployed in industrial settings. However, the robustness of these models remains scarcely explored. Contrary to computer vision, there are no effective attacks to properly evaluate the adversarial robustness of deep tabular models due to intrinsic properties of tabular data, such as categorical features, immutability, and feature relationship constraints. To fill this gap, we first propose CAPGD, a gradient attack that overcomes the failures of existing gradient attacks with adaptive mechanisms. This new attack does not require parameter tuning and further degrades the accuracy, up to 81% points compared to the previous gradient attacks. Second, we design CAA, an efficient evasion attack that combines our CAPGD attack and MOEVA, the best search-based attack. We demonstrate the effectiveness of our attacks on five architectures and four critical use cases. Our empirical study demonstrates that CAA outperforms all existing attacks in 17 over the 20 settings, and leads to a drop in the accuracy by up to 96.1% points and 21.9% points compared to CAPGD and MOEVA respectively while being up to five times faster than MOEVA. Given the effectiveness and efficiency of our new attacks, we argue that they should become the minimal test for any new defense or robust architectures in tabular machine learning.

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。

↑