This paper presents a multi-agent DevSecOps framework that integrates static code scanning, large language model (LLM) based security reasoning, automated repair generation, policy-as-code enforcement, and runtime monitoring into a unified event-driven pipeline. Five specialized agents collaborate through LangGraph shared state graphs: a Code Security Agent combining Semgrep rule matching with LLM contextual review, a Fix Agent generating reviewable candidate patches, a Policy Agent producing OPA Rego and Kubernetes NetworkPolicy files, and an Enforcement Agent operating in both CI gate and runtime response modes. Evaluation on a test application containing 50 planted vulnerabilities across Python code and infrastructure-as-code demonstrates that the combined Semgrep+LLM detection achieves 92.0% recall (F1=95.8%), compared to 34.0% for Semgrep alone, with zero false positives under the manually labeled test oracle. The Fix Agent commits candidate patches for 98.4% of detected vulnerabilities at an average of 35.5 seconds each. The Enforcement Agent correctly blocks non-compliant configurations and completes CI gate decisions in under 34 seconds. Runtime monitoring detects injection attacks, brute-force attempts, and unauthorized access with risk-proportional automated response within 42 seconds.
Hai-Ning Fan, Li-Jie Zheng, Chen-Hao Han et al.· Journal of networking and ne...· 0 citations
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
Integrated sensing and communications (ISAC) is moving from proof-of-concept demonstrations to system-level deployment in sixth-generation (6G) networks. Because sensing and communication share hardware, spectrum, and waveform resources, ISAC design now involves many tightly coupled choices, including waveform selection, sensing algorithm setup, resource scheduling, and deployment planning. This design space is already too large to manage well through manual tuning or isolated optimizers. This article introduces the \textit{Agent Compiler}, a large language model (LLM)-enabled compilation layer that translates high-level engineering intent into complete and executable ISAC system configurations. The Agent Compiler works in four stages: intent parsing, task decomposition, policy graph synthesis, and infrastructure mapping. It produces a verifiable intermediate representation called the ISAC Policy Graph (IPG). A runtime engine then deploys the compiled configuration and supports closed-loop adaptation at three levels: fast parameter updates, partial recompilation of affected subgraphs, and full workflow recompilation. The core design principle is strict time-scale separation: the LLM handles slow-loop strategic decisions, while proven algorithms retain real-time control in the fast loop. A UAV-assisted disaster rescue example illustrates the full compilation process. We also discuss open issues, including compilation latency, output reliability, constraint verification, and pipeline security, to guide future research.
Lijie Zheng, Xudong Zhong, Baoquan Ren et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
