arXiv cs.AI· Bikrant Bikram Pratap Maurya·· 10 小时前AI 评分38
域不变与语言模型辅助的键盘声学侧信道攻击
Domain-Invariant and Language-Model-Assisted Acoustic Side-Channel Attacks on Keyboards
AI 导读
研究提出将声学模型显式做成域不变、并用语言模型纠正其噪声预测，使键盘声学侧信道攻击（ASCA）在未见键盘、不同用户、嘈杂环境和压缩传输信道下仍能恢复输入文本。此前该类攻击仅在单一键盘、固定麦克风、安静房间且训练测试同设备的实验室条件下被验证成功。该工作仅用普通麦克风、无需接触受害者设备。
正文 · 原文
Abstract:Acoustic side-channel attacks (ASCA) recover typed text from the sound of keystrokes, using only a commodity microphone and no access to the victim's device. Prior work establishes that such attacks succeed under idealized laboratory conditions - a single keyboard, a fixed microphone, a quiet room, and training and testing on the same device but leaves open the question that matters for security: whether keystroke inference survives the open world of unseen keyboards, diverse users, noisy environments, and compressed transmission channels. The answer developed here is that it does, provided the acoustic model is made explicitly domain-invariant and its noisy predictions are corrected by a language model.
| Subjects: | Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.13922 [cs.CR] |
| (or arXiv:2611.13922v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2611.13922 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Bikrant Bikram Pratap Maurya [view email]
[v1]
Tue, 10 Nov 2026 11:10:42 UTC (75 KB)
来源：arXiv cs.AI · arxiv.org