Biblio

Recent advancements in Deep Neural Networks (DNNs) have enabled widespread deployment in multiple security-sensitive domains. The need for resource-intensive training and the use of valuable domain-specific training data have made these models the top intellectual property (IP) for model owners. One of the major threats to DNN privacy is model extraction attacks where adversaries attempt to steal sensitive information in DNN models. In this work, we propose an advanced model extraction framework DeepSteal that steals DNN weights remotely for the first time with the aid of a memory side-channel attack. Our proposed DeepSteal comprises two key stages. Firstly, we develop a new weight bit information extraction method, called HammerLeak, through adopting the rowhammer-based fault technique as the information leakage vector. HammerLeak leverages several novel system-level techniques tailored for DNN applications to enable fast and efficient weight stealing. Secondly, we propose a novel substitute model training algorithm with Mean Clustering weight penalty, which leverages the partial leaked bit information effectively and generates a substitute prototype of the target victim model. We evaluate the proposed model extraction framework on three popular image datasets (e.g., CIFAR-10/100/GTSRB) and four DNN architectures (e.g., ResNet-18/34/Wide-ResNetNGG-11). The extracted substitute model has successfully achieved more than 90% test accuracy on deep residual networks for the CIFAR-10 dataset. Moreover, our extracted substitute model could also generate effective adversarial input samples to fool the victim model. Notably, it achieves similar performance (i.e., 1-2% test accuracy under attack) as white-box adversarial input attack (e.g., PGD/Trades).

Ensuring the integrity and security of the memory system is critical. Recent studies have shown serious security concerns due to "rowhammer" attacks, where repeated accesses to a row of memory cause bit flips in adjacent rows. Recent work by Google's Project Zero has shown how to leverage rowhammer-induced bit-flips as the basis for security exploits that include malicious code injection and memory privilege escalation. Being an important security concern, industry has attempted to defend against rowhammer attacks. Deployed defenses employ two strategies: (1) doubling the system DRAM refresh rate and (2) restricting access to the CLFLUSH instruction that attackers use to bypass the cache to increase memory access frequency (i.e., the rate of rowhammering). We demonstrate that such defenses are inadequte: we implement rowhammer attacks that both avoid using the CLFLUSH instruction and cause bit flips with a doubled refresh rate. Our next-generation CLFLUSH-free rowhammer attack bypasses the cache by manipulating cache replacement state to allow frequent misses out of the last-level cache to DRAM rows of our choosing. To protect existing systems from more advanced rowhammer attacks, we develop a software-based defense, ANVIL, which thwarts all known rowhammer attacks on existing systems. ANVIL detects rowhammer attacks by tracking the locality of DRAM accesses using existing hardware performance counters. Our detector identifies the rows being frequently accessed (i.e., the aggressors), then selectively refreshes the nearby victim rows to prevent hammering. Experiments running on real hardware with the SPEC2006 benchmarks show that ANVIL has less than a 1% false positive rate and an average slowdown of 1%. ANVIL is low-cost and robust, and our experiments indicate that it is an effective approach for protecting existing and future systems from even advanced rowhammer attacks.