#SCA
#MLSecOps
"Whisper Leak: a side-channel attack on Large Language Models", Nov. 2025.
]-> https://github.com/yo-yo-yo-jbo/whisper_leak
// Whisper Leak - side-channel attack that infers user prompt topics from encrypted LLM traffic by analyzing packet size and timing patterns in streaming responses. Despite TLS encryption protecting content, these metadata patterns leak sufficient information to enable topic classification
Post #1717
187