arXiv:2606. 04517v1 Announce Type: cross Abstract: Graph-based deep learning methods have been widely employed in encrypted traffic analysis to exploit latent correlations across different granularities.
The paper demonstrates that encrypted traffic classification accuracy can be dramatically inflated by the choice of data split protocol. Using the same model and code, macro‑F1 scores drop from 0.992 under a standard random split to 0.567 when flows from a single packet capture are kept on one side of the split, a gap of 0.426 that is statistically significant. The authors evaluate multiple split strategies on QUIC traffic, showing that server‑disjoint splitting harms performance while other splits are comparable, and provide a diagnostic based on single‑identifier probes to identify the appropriate split axis before training.
arXiv:2506. 01260v2 Announce Type: replace Abstract: Scaling models has led to significant advancements in deep learning, but training these models in decentralized settings remains challenging due to communication bottlenecks.
arXiv:2603.25507v2 Announce Type: replace-cross Abstract: Network Traffic Classification (NTC) increasingly relies on data-driven models, yet its practical deployment is often constrained by limited...
LightSplit introduces a lightweight orthogonal random projection at the split learning cut layer to reduce communication overhead and limit information exposure. By sending low‑dimensional projections instead of raw activations, the method preserves end‑to‑end differentiability while discarding irreversibly part of the representation, thereby mitigating reconstruction attacks. Experiments on seven benchmarks show up to 32× compression with minimal accuracy loss and strong resistance to state‑of‑the‑art inversion attacks.
arXiv:2606. 16359v1 Announce Type: cross Abstract: Fully Homomorphic Encryption (FHE) enables privacy-preserving machine learning but incurs extreme computational and memory overhead.
arXiv:2608. 04545v1 Announce Type: new Abstract: We study the problem of learning compact rule-based compressors for structured network traffic.
arXiv:2609.16898v1 Announce Type: cross Abstract: Private deep neural network (DNN) inference based on hybrid homomorphic encryption (HE) and multi-party computation (MPC) can protect user data with...
arXiv:2606. 00155v1 Announce Type: cross Abstract: Modern network intrusion detection systems (NIDS) are caught in a structural contradiction: the protocols carrying the highest threat intelligence are precisely those encrypted under TLS 1.
arXiv:2608.30745v1 Announce Type: new Abstract: The widespread adoption of encrypted traffic poses severe challenges to current security situational awareness systems based on network traffic monitor...
arXiv:2606. 07819v1 Announce Type: new Abstract: Recently, the efficiency of Large Language Models (LLMs) deployment has become a critical concern in practical applications.
arXiv:2607. 18280v1 Announce Type: cross Abstract: Large language models (LLMs) are often compressed through static parameter pruning or dynamic token-level computation, yet aggressive sparsification can trigger rapid performance degradation beyond an essential sparsity boundary.