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 2302.11408cs.LGcs.AIcs.CRcs.CV
收藏

ASSET:跨多种深度学习范式的鲁棒后门数据检测

ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning Paradigms

Virginia Tech(弗吉尼亚理工大学);Sony AI(索尼人工智能);Northeastern University(东北大学)

Minzhou Pan, Yi Zeng, Lingjuan Lyu, Xue Lin, Ruoxi Jia

AI总结:

ASSET通过主动诱导后门与干净样本的模型行为差异,首次为监督学习、自监督学习和迁移学习提供统一且鲁棒的后门数据检测方法,并能检测最新的干净标签攻击。

摘要:

后门数据检测传统上在端到端监督学习(SL)环境中进行研究。然而,近年来,由于对标注数据的需求较少,自监督学习(SSL)和迁移学习(TL)得到了广泛采用。在这些新环境中,成功的后门攻击也已被证实。但我们缺乏对现有检测方法在各种学习环境中的适用性的透彻理解。通过评估56种攻击设置,我们表明大多数现有检测方法的性能在不同攻击和投毒比例下差异显著,并且所有方法在最新的干净标签攻击上均失败。此外,当应用于SSL和TL时,它们要么变得不适用,要么遭受严重的性能损失。我们提出了一种新的检测方法,称为通过偏移进行主动分离(ASSET),该方法主动诱导后门样本和干净样本之间不同的模型行为,以促进它们的分离。我们还提供了自适应选择要移除的可疑点数量的程序。在端到端SL环境中,ASSET在不同攻击下防御性能的一致性以及对投毒比例变化的鲁棒性方面优于现有方法;特别是,它是唯一能够检测最新干净标签攻击的方法。此外,ASSET在SSL和TL中的平均检测率分别比最佳现有方法高出69.3%和33.2%,从而为这些新的深度学习环境提供了第一个实用的后门防御。我们将该项目开源以推动进一步发展和鼓励参与:https://github.com/ruoxi-jia-group/ASSET。

英文摘要:

Backdoor data detection is traditionally studied in an end-to-end supervised learning (SL) setting. However, recent years have seen the proliferating adoption of self-supervised learning (SSL) and transfer learning (TL), due to their lesser need for labeled data. Successful backdoor attacks have also been demonstrated in these new settings. However, we lack a thorough understanding of the applicability of existing detection methods across a variety of learning settings. By evaluating 56 attack settings, we show that the performance of most existing detection methods varies significantly across different attacks and poison ratios, and all fail on the state-of-the-art clean-label attack. In addition, they either become inapplicable or suffer large performance losses when applied to SSL and TL. We propose a new detection method called Active Separation via Offset (ASSET), which actively induces different model behaviors between the backdoor and clean samples to promote their separation. We also provide procedures to adaptively select the number of suspicious points to remove. In the end-to-end SL setting, ASSET is superior to existing methods in terms of consistency of defensive performance across different attacks and robustness to changes in poison ratios; in particular, it is the only method that can detect the state-of-the-art clean-label attack. Moreover, ASSET's average detection rates are higher than the best existing methods in SSL and TL, respectively, by 69.3% and 33.2%, thus providing the first practical backdoor defense for these new DL settings. We open-source the project to drive further development and encourage engagement: https://github.com/ruoxi-jia-group/ASSET.

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。

↑