Search papers, labs, and topics across Lattice.
3
0
5
3
LLMs can now autonomously generate human-readable explanations of encrypted network traffic, bridging the gap between raw byte sequences and semantic understanding.
Encrypted traffic classification gets a major upgrade: TrafficMoE's dynamic, context-aware approach outperforms static methods by disentangling headers/payloads and filtering noise.
By mixing flows and using a teacher-student approach, MMAE learns more robust representations of encrypted traffic, achieving state-of-the-art classification performance.
