arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2411.03022cs.CRcs.AI
收藏

Flashy Backdoor:针对DVS相机SNN的真实环境后门攻击

Flashy Backdoor: Real-world Environment Backdoor Attack on SNNs with DVS Cameras

Radboud University(拉德堡德大学);Ikerlan Research Centre(伊克尔兰研究中心)

Roberto Riaño, Gorka Abad, Stjepan Picek, Aitor Urbieta

AI总结:

本研究首次针对DVS相机下的SNN提出真实环境后门攻击方法(Framed、Strobing、Flashy Backdoor),实现高达100%攻击成功率并保持高干净准确率,揭示现有防御的不足,呼吁加强SNN安全性研究。

摘要:

虽然传统深度神经网络(DNNs)的安全漏洞已被广泛研究,但脉冲神经网络(SNNs)对对抗性攻击的脆弱性仍大多未被充分探索。迄今为止,向SNN模型注入后门的机制仅限于数字场景;因此,我们首次评估了真实环境中的后门攻击。我们首先评估现有数字后门攻击的适用性,并识别其在物理环境中部署的局限性。针对发现的每个局限性,我们提出了三种新颖的SNN后门攻击方法,即Framed、Strobing和Flashy Backdoor。我们还评估了针对SNN改编的传统后门防御措施的有效性,如剪枝、微调和微调剪枝。结果表明,虽然这些措施和防御可以缓解某些攻击,但它们往往无法抵御如Flashy Backdoor等更强的攻击方法,或者牺牲过多的干净准确率,导致模型无法使用。总体而言,我们所有的方法在每个测试数据集上都能实现高达100%的攻击成功率,同时保持高干净准确率。此外,我们使用常用指标评估触发器的隐蔽性,发现它们高度隐蔽。因此,我们提出了更适合在这些场景中识别中毒样本的新替代方案。我们的结果表明,需要进一步研究以确保基于SNN的系统免受后门攻击,并确保其在真实场景中的安全应用。代码、实验和结果可在我们的仓库中获取。

英文摘要:

While security vulnerabilities in traditional Deep Neural Networks (DNNs) have been extensively studied, the susceptibility of Spiking Neural Networks (SNNs) to adversarial attacks remains mostly underexplored. Until now, the mechanisms to inject backdoors into SNN models have been limited to digital scenarios; thus, we present the first evaluation of backdoor attacks in real-world environments. We begin by assessing the applicability of existing digital backdoor attacks and identifying their limitations for deployment in physical environments. To address each of the found limitations, we present three novel backdoor attack methods on SNNs, i.e., Framed, Strobing, and Flashy Backdoor. We also assess the effectiveness of traditional backdoor procedures and defenses adapted for SNNs, such as pruning, fine-tuning, and fine-pruning. The results show that while these procedures and defenses can mitigate some attacks, they often fail against stronger methods like Flashy Backdoor or sacrifice too much clean accuracy, rendering the models unusable. Overall, all our methods can achieve up to a 100% Attack Success Rate while maintaining high clean accuracy in every tested dataset. Additionally, we evaluate the stealthiness of the triggers with commonly used metrics, finding them highly stealthy. Thus, we propose new alternatives more suited for identifying poisoned samples in these scenarios. Our results show that further research is needed to ensure the security of SNN-based systems against backdoor attacks and their safe application in real-world scenarios. The code, experiments, and results are available in our repository.

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。

↑