AccHashtag: Accelerated Hashing for Detecting Fault-Injection Attacks on Embedded Neural Networks
AccHashtag: Accelerated Hashing for Detecting Fault-Injection Attacks on Embedded Neural Networks
复制标题
DOI：
10.1145/3555808
复制
发表时间：
2022-08
影响因子：
2.2
通讯作者：
Mojan Javaheripi;Jung-Woo Chang;F. Koushanfar
中科院分区：
文献类型：
--
作者：
Mojan Javaheripi;Jung-Woo Chang;F. Koushanfar
我们提出了AccHashtag，这是第一个对深度神经网络（DNN）进行高精度故障注入攻击检测的框架，具有可证明的检测性能界限。故障注入攻击的最新文献显示，位翻转会导致DNN精度严重下降。在这种情况下，攻击者在执行过程中通过向动态随机存取存储器（DRAM）注入故障来更改一些DNN权重位。为了检测比特翻转，AccHashtag在部署之前从良性DNN中提取唯一签名。签名用于验证模型的完整性，并在运行中验证推理输出。我们提出了一种新的敏感性分析，确定最脆弱的DNN层的故障注入攻击。DNN签名是通过使用低冲突哈希函数对脆弱层中的权重进行编码来构造的。在DNN推理过程中，从目标层中提取新的哈希值，并与地面真实签名进行比较。AccHashtag采用了一种轻量级的方法，允许在嵌入式平台上进行实时故障检测。我们在现场可编程门阵列（FPGA）上为AccHashtag设计了一个专门的计算核心，以促进与DNN执行并行的在线哈希生成。对各种DNN进行的最先进的位翻转攻击的广泛评估证明了AccHashtag在攻击检测和执行开销方面的竞争优势。
We propose AccHashtag, the first framework for high-accuracy detection of fault-injection attacks on Deep Neural Networks (DNNs) with provable bounds on detection performance. Recent literature in fault-injection attacks shows the severe DNN accuracy degradation caused by bit flips. In this scenario, the attacker changes a few DNN weight bits during execution by injecting faults to the dynamic random-access memory (DRAM). To detect bit flips, AccHashtag extracts a unique signature from the benign DNN prior to deployment. The signature is used to validate the model’s integrity and verify the inference output on the fly. We propose a novel sensitivity analysis that identifies the most vulnerable DNN layers to the fault-injection attack. The DNN signature is constructed by encoding the weights in vulnerable layers using a low-collision hash function. During DNN inference, new hashes are extracted from the target layers and compared against the ground-truth signatures. AccHashtag incorporates a lightweight methodology that allows for real-time fault detection on embedded platforms. We devise a specialized compute core for AccHashtag on field-programmable gate arrays (FPGAs) to facilitate online hash generation in parallel to DNN execution. Extensive evaluations with the state-of-the-art bit-flip attack on various DNNs demonstrate the competitive advantage of AccHashtag in terms of both attack detection and execution overhead.