PropGuard introduces a propagation-aware framework to safeguard LLM-MAS against malicious attacks by constructing a dual-view graph, identifying suspicious propagation paths, and applying source-guide…

IstGPT introduces a novel LLM-based framework for real-time, fine-grained anomaly detection in complex industrial cyber-physical systems, achieving state-of-the-art performance across multiple benchma…

FALAT is a diagnostic framework that treats failure attribution in complex LLM agent trajectories as a dependency-guided search problem, successfully identifying both the responsible agent and the dec…

TIGER is an inference-time framework that uses graph-based evidence routing to independently assess and repair unsupported facts (hallucinations) in multimodal generation.

The paper proposes DA-GC, a certified causal attribution framework that accurately identifies cross-slice attack origins in 6G networks under strict real-time latency constraints by systematically mod…

This paper systematically studies how soft errors propagate during Large Language Model (LLM) inference using a novel fault-injection framework, providing critical insights and mitigation strategies f…

The paper proposes SCOPE, a lightweight LLM framework that significantly improves the accuracy and efficiency of automated Air Traffic Control (ATC) readback monitoring, achieving high performance in…

This paper introduces a failure-aware observability framework to diagnose wasted computation in multi-agent LLM systems by mapping recurring failure modes to online trace signals.

This paper surveys model forensics in AI-native wireless networks, detailing key security problems and demonstrating practical workflows for verifying model authenticity and detecting malicious functi…

The paper introduces a new benchmark (BGTD) and a multimodal framework (mmTraffic) that enables explainable, evidence-grounded interpretation of encrypted network traffic using LLMs.

The paper proposes Multi-Order Communication (MOC) to overcome the limitations of standard first-order message passing in LLM-based multi-agent systems, significantly improving performance by capturin…

The paper proposes a communication-centric 6G-LLM architecture for tactical autonomous defense vehicles, demonstrating significant improvements in coordination and communication efficiency over conven…

The paper proposes a system-aware unsupervised framework that combines lightweight online detection with a contextual digital twin and LLM to provide interpretable, actionable anomaly diagnoses for In…

The paper presents an end-to-end system that translates high-level operator intents into low-level, safe routing constraints for LEO mega-constellations, achieving high accuracy and safety guarantees.

This paper demonstrates that an off-the-shelf Large Language Model (LLM) can function as a high-performing, explainable, human-in-the-loop layer for detecting cyberattacks in Industrial Control System…

The paper proposes ExAI5G, a logic-based explainable AI framework that integrates a Transformer-based IDS with XAI techniques to provide highly accurate and transparent intrusion detection for 5G netw…

HunterAgent is a neuro-symbolic framework that reconstructs causal attack chains from fragmented, anti-forensics-corrupted logs, achieving high accuracy while drastically reducing hallucination.

The paper proposes a Digital Twin (DT)-driven hybrid system that combines deterministic heuristics and constrained Large Language Model (LLM) reasoning to achieve highly accurate and interpretable rea…

The paper proposes a declarative, autonomous, self-protecting framework for securing complex 5G/6G networks by leveraging a standardized security ontology and automated graph reasoning to neutralize l…

The paper proposes SAGE, a framework that uses Signal-Amplified Guided Embeddings to overcome 'Signal Submersion' in LLMs, significantly boosting vulnerability detection accuracy across multiple progr…