Federated Learning (FL) is a promising approach for privacy-preserving network traffic analysis, but its practical deployment is challenged by the non-IID nature of real-world data. While prior work has addressed statistical heterogeneity, the impact of temporal traffic volatility-the natural daily ebb and flow of network activity-on model stability remains largely unexplored. This volatility can lead to inconsistent data availability at clients, destabilizing the entire training process. In this paper, we systematically address the problem of temporal volatility in federated QUIC classification. We first demonstrate the instability of standard FL in this dynamic setting. We then propose and evaluate a client-side data buffer as a practical mechanism to ensure stable and consistent local training, decoupling it from real-time traffic fluctuations. Using the real-world CESNETQUIC22 dataset partitioned into 14 autonomous clients, we then demonstrate that this approach enables robust convergence. Our results show that a stable federated system achieves a 95.2% F1 score, a mere 2.3 percentage points below a non-private centralized model. This work establishes a blueprint for building operationally stable FL systems for network management, proving that the challenges of dynamic network environments can be overcome with targeted architectural choices.

Cybersecurity remains a critical challenge in the digital age, with network traffic flow anomaly detection being a key pivotal instrument in the fight against cyber threats. In this study, we address the prevalent issue of data integrity in network traffic datasets, which are instrumental in developing machine learning (ML) models for anomaly detection. We introduce two refined versions of the CICIDS-2017 dataset, NFS-2023-nTE and NFS-2023-TE, processed using NFStream to ensure methodologically sound flow expiration and labeling. Our research contrasts the performance of the Random Forest (RF) algorithm across the original CICIDS-2017, its refined counterparts WTMC-2021 and CRiSIS-2022, and our NFStream-generated datasets, in both binary and multi-class classification contexts. We observe that the RF model exhibits exceptional robustness, achieving consistent high-performance metrics irrespective of the underlying dataset quality, which prompts a critical discussion on the actual impact of data integrity on ML efficacy. Our study underscores the importance of continual refinement and methodological rigor in dataset generation for network security research. As the landscape of network threats evolves, so must the tools and techniques used to detect and analyze them.

We propose a method for the stabilization of quantum computations (including quantum state storage). The method is based on the operation of projection into $\cal SYM$, the symmetric subspace of the full state space of R redundant copies of the computer. We describe an efficient algorithm and quantum network effecting $\cal SYM$--projection and discuss the stabilizing effect of the proposed method in the context of unitary errors generated by hardware imprecision, and nonunitary errors arising from external environmental interaction. Finally, limitations of the method are discussed.

We describe a complete protocol for bit commitment based on the transmission of polarized photons. We show that under the laws of quantum physics, this protocol cannot be cheated by either party except with exponentially small probability (exponential in the running time needed to implement the honest protocol). A more thorough analysis is required to adjust all the constants used in this paper to get the best performance from our construction. Better performances may probably be achieved by using a third conjugate transmission-reception basis of circular polarization.>