FaRAccel:面向Transformer模型高效抗位翻转攻击的FPGA加速防御架构
FaRAccel: FPGA-Accelerated Defense Architecture for Efficient Bit-Flip Attack Resilience in Transformer Models
AI总结:
针对Transformer抗位翻转攻击的FaR方法存在性能与内存开销问题,提出基于FPGA的FaRAccel硬件加速架构,通过可重构逻辑与轻量存储实现低延迟高能效推理,保留原方法鲁棒性,填补算法与高效部署的缺口。
摘要:
“遗忘与重连”(Forget and Rewire, FaR)方法通过对线性层进行动态重连来混淆关键参数,已展现出对基于Transformer的模型上位翻转攻击(Bit-Flip Attacks, BFAs)的强韧性。然而,FaR的应用带来了不可忽视的性能与内存开销,主要源于激活路径的运行时修改以及缺乏硬件层面的优化。为克服这些局限,我们提出FaRAccel——一种在FPGA上实现的新型硬件加速器架构,专门用于卸载并优化FaR运算。FaRAccel集成了用于动态激活重路由的可重构逻辑,以及重连配置的轻量级存储,可实现低延迟推理且能量开销极小。我们在一组Transformer模型上评估了FaRAccel,结果表明其大幅降低了FaR的推理延迟、提升了能效,同时保留了原始FaR方法的鲁棒性增益。据我们所知,这是首个针对Transformer中BFAs的硬件加速防御方案,有效弥合了算法韧性与现实AI平台高效部署之间的差距。
英文摘要:
Forget and Rewire (FaR) methodology has demonstrated strong resilience against Bit-Flip Attacks (BFAs) on Transformer-based models by obfuscating critical parameters through dynamic rewiring of linear layers. However, the application of FaR introduces non-negligible performance and memory overheads, primarily due to the runtime modification of activation pathways and the lack of hardware-level optimization. To overcome these limitations, we propose FaRAccel, a novel hardware accelerator architecture implemented on FPGA, specifically designed to offload and optimize FaR operations. FaRAccel integrates reconfigurable logic for dynamic activation rerouting, and lightweight storage of rewiring configurations, enabling low-latency inference with minimal energy overhead. We evaluate FaRAccel across a suite of Transformer models and demonstrate substantial reductions in FaR inference latency and improvement in energy efficiency, while maintaining the robustness gains of the original FaR methodology. To the best of our knowledge, this is the first hardware-accelerated defense against BFAs in Transformers, effectively bridging the gap between algorithmic resilience and efficient deployment on real-world AI platforms.
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。