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 2412.00746cs.SE
收藏

BDefects4NN:用于神经网络中受控定位研究的后门缺陷数据库

BDefects4NN: A Backdoor Defect Database for Controlled Localization Studies in Neural Networks

Yisong Xiao, Aishan Liu, Xinwei Zhang, Tianyuan Zhang, Tianlin Li, Siyuan Liang, Xianglong Liu, Yang Liu, Dacheng Tao

AI总结:

本文构建首个神经元粒度后门缺陷数据库 BDefects4NN,支持受控根因定位,并通过 1,654 个缺陷模型评估定位与修复技术,揭示现有方法及实际场景中的局限。

摘要:

预训练的大型深度学习模型如今已成为下游中间件用户的主导组件,并彻底改变了学习范式,取代了传统的本地从零开始训练方法。为降低开发成本,开发者经常将第三方预训练深度神经网络(DNN)集成到其智能软件系统中。然而,使用不受信任的 DNN 会带来重大安全风险,因为这些模型可能因黑盒训练过程而包含故意植入的后门缺陷。这些后门缺陷可由隐藏触发器激活,使攻击者能够恶意控制模型并损害智能软件的整体可靠性。为确保 DNN 在关键软件系统中的安全采用,建立一个用于定位研究的后门缺陷数据库至关重要。本文通过引入 BDefects4NN 来填补这一研究空白,它是首个后门缺陷数据库,提供神经元粒度的带标签后门缺陷 DNN,并支持对缺陷根本原因进行受控定位研究。在 BDefects4NN 中,我们定义了三条缺陷注入规则,并在四种流行网络架构和三个广泛采用的数据集上采用四种代表性后门攻击,形成了包含 1,654 个后门缺陷 DNN 的综合数据库,这些 DNN 具有四种缺陷数量和不同的受感染神经元。基于 BDefects4NN,我们开展了大量实验,评估六种故障定位准则和两种缺陷修复技术,结果表明它们对后门缺陷的有效性有限。此外,我们还研究了实际场景中的后门缺陷模型,特别是自动驾驶中的车道检测和大型语言模型(LLM),揭示了潜在威胁,并强调了当前在精确缺陷定位方面的局限性。

英文摘要:

Pre-trained large deep learning models are now serving as the dominant component for downstream middleware users and have revolutionized the learning paradigm, replacing the traditional approach of training from scratch locally. To reduce development costs, developers often integrate third-party pre-trained deep neural networks (DNNs) into their intelligent software systems. However, utilizing untrusted DNNs presents significant security risks, as these models may contain intentional backdoor defects resulting from the black-box training process. These backdoor defects can be activated by hidden triggers, allowing attackers to maliciously control the model and compromise the overall reliability of the intelligent software. To ensure the safe adoption of DNNs in critical software systems, it is crucial to establish a backdoor defect database for localization studies. This paper addresses this research gap by introducing BDefects4NN, the first backdoor defect database, which provides labeled backdoor-defected DNNs at the neuron granularity and enables controlled localization studies of defect root causes. In BDefects4NN, we define three defect injection rules and employ four representative backdoor attacks across four popular network architectures and three widely adopted datasets, yielding a comprehensive database of 1,654 backdoor-defected DNNs with four defect quantities and varying infected neurons. Based on BDefects4NN, we conduct extensive experiments on evaluating six fault localization criteria and two defect repair techniques, which show limited effectiveness for backdoor defects. Additionally, we investigate backdoor-defected models in practical scenarios, specifically in lane detection for autonomous driving and large language models (LLMs), revealing potential threats and highlighting current limitations in precise defect localization.

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。

↑