Search papers, labs, and topics across Lattice.
This paper introduces ROBBIN, a hardware-aware Rowhammer-based backdoor injection attack that optimizes backdoor construction by integrating device-specific vulnerabilities into the design process. By characterizing the bit-flip patterns of target DRAM and strategically selecting page mappings for model weights, ROBBIN achieves a high attack success rate (ASR) while maintaining test accuracy (TA) across different DRAM devices. Evaluations on ResNet-20 and VGG-16 with CIFAR-10 show that ROBBIN consistently reaches nearly 90% ASR with TA above 83%, highlighting its robustness across diverse hardware setups.
ROBBIN achieves nearly 90% attack success while preserving over 83% accuracy, making it a game-changer for reliable backdoor attacks across varying DRAM devices.
Existing Rowhammer-based inference-time backdoor attacks design their bit-flip strategies purely at the algorithmic level, without accounting for the bit-flips that the underlying DRAM hardware will actually produce. This disconnection between the algorithmic backdoor construction and its hardware realization leads to unreliable attack performance, as collateral bit-flips at unintended locations degrade both the attack success rate (ASR) on triggered inputs and the test accuracy (TA) for normal inputs. Consequently, the performance of such attacks varies significantly across different DRAM devices, as each device presents a unique set of exploitable bit-flip locations. This work presents ROBBIN, a hardware-aware Rowhammer-based backdoor injection attack that integrates the device-specific vulnerability into the backdoor construction process. ROBBIN first characterizes the bit-flip patterns of a target DRAM and uses this information to iteratively select DRAM \textit{page} mappings for the model weights that would maximize ASR while preserving TA under Rowhammering. By treating every hammering-induced bit-flip as an integral part of the attack design rather than first constructing a hardware-agnostic backdoor and dismissing collateral flips as side effects, ROBBIN produces backdoors that remain robust across devices. Evaluated on ResNet-20 and VGG-16 with CIFAR-10 across three commodity DDR4 chips, ROBBIN consistently achieves close to 90\% ASR while maintaining TA above 83\%, demonstrating reliable backdoor efficacy across diverse DRAM devices.
