LLMs Have Rhythm: Fingerprinting Large Language Models Using Inter-Token Times and Network Traffic Analysis

<p dir="ltr">As Large Language Models (LLMs) become increasingly integrated into many technological ecosystems across various domains and industries, identifying which model is deployed or being interacted with is critical for the security and trustworthiness of the systems. Current...

وصف كامل

محفوظ في:

التفاصيل البيبلوغرافية
المؤلف الرئيسي:	Saeif Alhazbi (17058108) (author)
مؤلفون آخرون:	Ahmed Hussain (5233775) (author), Gabriele Oligeri (14151426) (author), Panos Papadimitratos (22565177) (author)
منشور في:	2025
الموضوعات:	Information and computing sciences Artificial intelligence Cybersecurity and privacy Machine learning Large language models small language models fingerprinting network traffic analysis deep learning network security Computational modeling Analytical models Watermarking Telecommunication traffic Virtual private networks Timing Feature extraction Local area networks
الوسوم:	إضافة وسم لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!

LLMs Have Rhythm: Fingerprinting Large Language Models Using Inter-Token Times and Network Traffic Analysis

مواد مشابهة