arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.02673cs.CR
收藏

通过拓扑演化动力学实现深度学习的鲁棒后门检测

Robust Backdoor Detection for Deep Learning via Topological Evolution Dynamics

Xiaoxing Mo, Yechao Zhang, Leo Yu Zhang, Wei Luo, Nan Sun, Shengshan Hu, Shang Gao, Yang Xiang

AI总结:

针对后门检测依赖样本可分度量空间的局限,本文提出模型无关的 TED 拓扑演化动力学方法,通过输入演化轨迹识别后门,并在视觉与 NLP 任务中显著优于现有方法。

摘要:

深度学习中的后门攻击会在模型中植入隐藏后门,以便在特定输入模式出现时触发恶意行为。现有检测方法都假设存在一个度量空间(针对原始输入或其潜在表示),在该空间中正常样本与恶意样本是可分离的。我们通过引入一种新型 SSDT(Source-Specific and Dynamic-Triggers,源特定且动态触发器)后门,表明该假设存在严重局限,因为这种后门会模糊正常样本与恶意样本之间的差异。为克服这一局限,我们不再寻找适用于不同深度学习模型的完美度量空间,而是求助于更鲁棒的拓扑构造。我们提出 TED(Topological Evolution Dynamics,拓扑演化动力学),将其作为模型无关的鲁棒后门检测基础。TED 的主要思想是把深度学习模型视为一个将输入演化到输出的动力学系统。在这样的动力学系统中,良性输入遵循与其他良性输入相似的自然演化轨迹;相比之下,恶意样本呈现出明显不同的轨迹,因为它起初靠近良性样本,但最终转向攻击者指定目标样本的邻域,以激活后门。我们在跨不同网络架构的视觉和自然语言数据集上进行了广泛评估。结果表明,TED 不仅实现了高检测率,而且显著优于现有最先进检测方法,尤其是在应对复杂的 SSDT 攻击时。复现结果的代码已在 GitHub 上公开。

英文摘要:

A backdoor attack in deep learning inserts a hidden backdoor in the model to trigger malicious behavior upon specific input patterns. Existing detection approaches assume a metric space (for either the original inputs or their latent representations) in which normal samples and malicious samples are separable. We show that this assumption has a severe limitation by introducing a novel SSDT (Source-Specific and Dynamic-Triggers) backdoor, which obscures the difference between normal samples and malicious samples. To overcome this limitation, we move beyond looking for a perfect metric space that would work for different deep-learning models, and instead resort to more robust topological constructs. We propose TED (Topological Evolution Dynamics) as a model-agnostic basis for robust backdoor detection. The main idea of TED is to view a deep-learning model as a dynamical system that evolves inputs to outputs. In such a dynamical system, a benign input follows a natural evolution trajectory similar to other benign inputs. In contrast, a malicious sample displays a distinct trajectory, since it starts close to benign samples but eventually shifts towards the neighborhood of attacker-specified target samples to activate the backdoor. Extensive evaluations are conducted on vision and natural language datasets across different network architectures. The results demonstrate that TED not only achieves a high detection rate, but also significantly outperforms existing state-of-the-art detection approaches, particularly in addressing the sophisticated SSDT attack. The code to reproduce the results is made public on GitHub.

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。

↑