DECKER: 跨键盘提取与识别的域不变嵌入
DECKER: Domain-invariant Embedding for Cross-Keyboard Extraction and Recognition
AI总结：
针对键盘声学侧信道攻击的跨键盘、跨用户和噪声环境泛化问题，提出包含四阶段域不变击键推理框架DECKER，并构建了多维度数据集HEAR，实验表明该方法在跨键盘和跨用户场景下显著提升击键识别性能。
摘要：
键盘上的声学侧信道攻击（ASCA）构成了重大的安全风险，因为击键可以从打字声音中推断出来，从而泄露敏感信息。先前的ASCA研究受限于小规模数据集，在用户、键盘和环境方面的多样性不足，限制了跨设备、麦克风和噪声条件的分析。我们引入了HEAR数据集，旨在沿着三个轴研究ASCA：键盘泛化、噪声适应和用户偏差。HEAR包含来自53名参与者使用37种笔记本电脑键盘的录音，在三种现实场景中收集：（1）外部麦克风捕获，（2）无网络噪声的设备麦克风捕获，以及（3）基于VoIP的流式捕获。这使得能够在用户、键盘和环境之间进行受控评估。在HEAR上，我们建立了一个ASCA基准，涵盖了单模态和多模态设置中来自原始音频和频谱图的传统特征和预训练表示。我们提出了DECKER，一个域不变的击键推理框架，包含四个阶段：（1）键盘签名归一化以减少设备着色，（2）域对抗解耦以抑制键盘身份，（3）有监督的跨键盘对比对齐以强制键一致性，以及（4）声学风格随机化以合成未见过的键盘响应。我们进一步探索了使用基于LLM的后处理层进行句子级推理，通过语言上下文优化击键序列。在HEAR上的结果表明，DECKER在跨键盘和跨用户设置中显著提高了击键识别性能，并通过语言模型校正进一步获得提升。这些发现强调，ASCA在多样化的用户、设备和噪声环境中仍然有效，凸显了其实际安全风险。
英文摘要：
Acoustic side-channel attacks (ASCA) on keyboards pose a significant security risk, as keystrokes can be inferred from typing acoustics, revealing sensitive information. Prior ASCA studies are limited by small-scale datasets with restricted diversity in users, keyboards, and environments, constraining analysis across devices, microphones, and noise conditions. We introduce HEAR, a dataset designed to study ASCA along three axes: keyboard generalization, noise adaptation, and user bias. HEAR contains recordings from 53 participants using 37 laptop keyboards, collected in three realistic settings: (1) external microphone capture, (2) device microphone capture without network noise, and (3) VoIP-based streaming capture. This enables controlled evaluation across users, keyboards, and environments. On HEAR, we establish an ASCA benchmark spanning conventional features and pre-trained representations from raw audio and spectrograms in unimodal and multimodal settings. We propose DECKER, a domain-invariant keystroke inference framework with four stages: (1) Keyboard Signature Normalization to reduce device coloration, (2) domain-adversarial disentanglement to suppress keyboard identity, (3) supervised cross-keyboard contrastive alignment to enforce key consistency, and (4) Acoustic Style Randomization to synthesize unseen keyboard responses. We further explore sentence-level inference using an LLM-based post-processing layer to refine keystroke sequences via linguistic context. Results on HEAR show DECKER improves keystroke identification over strong baselines, particularly in cross-keyboard and cross-user settings, with further gains from language-model rectification. These findings highlight that ASCA remains effective across diverse users, devices, and noisy environments, underscoring its practical security risk.
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。
