arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.04035cs.CR
收藏

利用对抗攻击防御针对 DNN 加速器的基于机器学习的功耗侧信道攻击

Defense against ML-based Power Side-channel Attacks on DNN Accelerators with Adversarial Attacks

Xiaobei Yan, Chip Hong Chang, Tianwei Zhang

AI总结:

本文提出 AIAShield,通过对抗攻击生成细粒度功耗噪声并结合神经架构搜索,防御基于机器学习的功耗侧信道模型窃取,且开销低、可迁移性强。

摘要:

人工智能(AI)硬件加速器已被广泛采用,以提升深度学习应用的效率。然而,它们也引发了安全担忧,即其易受功耗侧信道攻击(SCA)影响。在这些攻击中,攻击者利用非预期通信通道推断加速器处理的敏感信息,从而给模型带来严重的隐私和版权风险。先进的机器学习算法还被进一步用于辅助侧信道分析,加剧了 AI 加速器的隐私问题。传统防御策略只是简单地向 AI 模型运行过程注入执行噪声,这不可避免地会带来巨大开销。在本文中,我们提出 AIAShield,这是一种新型防御方法,用于保护基于 FPGA 的 AI 加速器,并缓解通过基于功耗的 SCA 实施的模型窃取威胁。AIAShield 的关键洞见是利用机器学习领域中突出的对抗攻击技术来精心构造噪声,这种噪声能够显著混淆攻击者的侧信道观测,同时对受保护模型的执行只产生极小开销。在硬件层面,我们设计了一个基于环形振荡器的新模块,以实现细粒度噪声生成。在算法层面,我们重新利用神经架构搜索来恶化攻击者的窃取结果。在 Nvidia Deep Learning Accelerator(NVDLA)上进行的大量实验表明,AIAShield 优于现有解决方案,并具有出色的可迁移性。

英文摘要:

Artificial Intelligence (AI) hardware accelerators have been widely adopted to enhance the efficiency of deep learning applications. However, they also raise security concerns regarding their vulnerability to power side-channel attacks (SCA). In these attacks, the adversary exploits unintended communication channels to infer sensitive information processed by the accelerator, posing significant privacy and copyright risks to the models. Advanced machine learning algorithms are further employed to facilitate the side-channel analysis and exacerbate the privacy issue of AI accelerators. Traditional defense strategies naively inject execution noise to the runtime of AI models, which inevitably introduce large overheads. In this paper, we present AIAShield, a novel defense methodology to safeguard FPGA-based AI accelerators and mitigate model extraction threats via power-based SCAs. The key insight of AIAShield is to leverage the prominent adversarial attack technique from the machine learning community to craft delicate noise, which can significantly obfuscate the adversary's side-channel observation while incurring minimal overhead to the execution of the protected model. At the hardware level, we design a new module based on ring oscillators to achieve fine-grained noise generation. At the algorithm level, we repurpose Neural Architecture Search to worsen the adversary's extraction results. Extensive experiments on the Nvidia Deep Learning Accelerator (NVDLA) demonstrate that AIAShield outperforms existing solutions with excellent transferability.

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。

↑