Fingerprinting Search Keywords over HTTPS at Scale
The possibility of fingerprinting the search keywords issued by a user on popular web search engines is a significant threat to user privacy. This threat has received surprisingly little attention in the network traffic analysis literature. In this work, we consider the problem of keyword fingerprinting of HTTPS traffic -- we study the impact of several factors, including client platform diversity, choice of search engine, feature sets as well as classification frameworks. We conduct both closed-world and open-world evaluations using nearly 4 million search queries collected over a period of three months. Our analysis reveals several insights into the threat of keyword fingerprinting in modern HTTPS traffic.
Code (0)
등록된 구현이 없습니다.
Tasks
DiversitySimilar Papers 제목 키워드 기반
Neural Audio Fingerprint for High-specific Audio Retrieval based on Contrastive Learning
Most of existing audio fingerprinting systems have limitations to be used for high-specific audio retrieval at scale. In this work, we generate a low-dimensional representation from a short unit segment of audio, and cou…
Audio FingerprintContrastive LearningMusic Information RetrievalRetrievalAvatar Fingerprinting for Authorized Use of Synthetic Talking-Head Videos
Modern avatar generators allow anyone to synthesize photorealistic real-time talking avatars, ushering in a new era of avatar-based human communication, such as with immersive AR/VR interactions or videoconferencing with…
Robust open-set classification for encrypted traffic fingerprinting
Encrypted network traffic has been known to leak information about their underlying content through side-channel information leaks. Traffic fingerprinting attacks exploit this by using machine learning techniques to thre…
Classificationopen-set classificationQuantizationFusion-based Few-Shot Morphing Attack Detection and Fingerprinting
The vulnerability of face recognition systems to morphing attacks has posed a serious security threat due to the wide adoption of face biometrics in the real world. Most existing morphing attack detection (MAD) methods r…
Face RecognitionFew-Shot LearningFingerprinting Fine-tuned Language Models in the Wild
There are concerns that the ability of language models (LMs) to generate high quality synthetic text can be misused to launch spam, disinformation, or propaganda. Therefore, the research community is actively working on …
Attribute