用标准Transformer实现未裁剪数据的全密钥侧信道攻击
A Simple Transformer Pipeline for Full-Key Side-Channel Attacks on Uncropped Datasets
- 仅调整输入输出层，复用标准Transformer编码器
- 在ASCADv1f等数据集上性能媲美先进方法
- 低显存（<10GB）和短训练时间（≤3.34小时）
基于深度学习的侧信道分析长期聚焦单字节目标与手动裁剪的迹线，可能丢失可利用的泄露信息。尽管近期研究提出专用架构与重采样技术弥补此缺陷，但缺乏针对未裁剪迹线的简单Transformer基线。本文提出开源Transformer实现，采用标准Transformer编码器主干，仅调整输入输出层适配侧信道场景。我们发布ASCADv1f、ASCADv1r和CHES-CTF-2018三个数据集的实现代码、训练方案及预训练权重，在保持与已有结果竞争力的同时，显存使用低于10GB，单卡A6000训练时间不超过3.34小时。
原文摘要 · Abstract (English)
Deep learning-based side-channel analysis has historically focused on single-byte targets and manually cropped traces, which risks discarding exploitable leakage. While recent work has proposed specialized architectures and resampling techniques to address this gap, the literature lacks a simple transformer baseline for simultaneous full-key attacks on uncropped traces. We present an open-source transformer implementation for uncropped full-key attacks which uses the standard transformer encoder backbone, adapting only the input and output layers to the side-channel setting. We release our implementation, training recipes, and pretrained weights for uncropped ASCADv1f, ASCADv1r, and CHES-CTF-2018 which achieve performance competitive with previously-reported results, while using less than 10GB of VRAM and requiring at most 3.34 hours of training on a single NVIDIA A6000.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。