Provenance-Based Intrusion Detection Systems (PIDSs) detect Advanced Persistent Threats (APTs) by analyzing system interactions. However, existing methods largely treat relations uniformly, overlooking statistical heterogeneity; in CADETS, relation frequencies differ by approximately $140{,}000\times$. This may cause PIDSs to focus more on frequent relations and overlook differences in normal error levels across relations, increasing the risk of false alarms and missed detections. We present RECAL, an unsupervised framework using relation-balanced masked graph learning to better capture rare interaction patterns. It further calibrates reconstruction errors against each relation's benign error distribution to produce comparable anomaly evidence, helping distinguish attacks from benign behavior and reduce false alarms. On three DARPA E3 datasets, RECAL achieves F1 scores of 99.99\%, 99.93\%, and 99.99\%, outperforming the best baseline on each dataset by 0.88, 0.82, and 0.42 percentage points, respectively. Compared with the baseline reporting the lowest FPR, RECAL reduces mean FPR by approximately $105\times$, $4\times$, and $41\times$.
Li-Jie Zheng, Ji He, Alessandro Brighente et al.· 0 citations
—Unmanned aerial vehicles (UAVs) have been extensively deployed in wireless communication scenario. However, UAV communication faces the challenges of information leakage and energy limitation. Therefore, this paper studies energy-efficient covert communication in adversarial UAV-enabled wireless systems, where a UAV covertly delivers information to a legitimate ground receiver under the detection of a malicious detector with noise uncertainty. Our objective is to maximize covert energy efficiency, defined as the achievable covert throughput per unit of energy consumption, via the joint design of transmit power and flying location. To this end, we derive the detector’s minimum detection error probability to establish a covertness constraint. Based on this model, we formulate a three-dimensional joint optimization problem for transmit power and two-dimensional location, capturing the fundamental tradeoff among covertness, communication reliability, and energy efficiency. Through sys-tem geometric exploration, metric monotonicity analysis, and theoretical derivation, the original three-dimensional problem is reduced to a one-dimensional search over the flying angle, which enables efficient computation of the optimal UAV configuration via vectorized computation. Numerical results verify the theoretical derivations and illustrate the superiority of the joint design as well as the impact of system parameters on energy efficiency performance.
Yang-Fan Xu, Bin Yang, Yulong Shen et al.· IEEE Transactions on Dependa...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
