The paper introduces ASPO, a self-adaptive multi-agent system that uses LLM-based reasoning combined with deterministic optimization to select conflict-free and resource-feasible security mitigation p…

LanG is a governance-aware, open-source agentic AI platform that unifies security operations by providing advanced correlation, automated rule generation, and attack reconstruction capabilities.

The paper proposes a system that operationalizes cybersecurity governance frameworks by integrating them with attack-path modeling and Deep Reinforcement Learning to generate practical, resource-const…

The paper proposes a tool-mediated LLM architecture for autonomous cyber defense, formally proving its stability and demonstrating that it significantly reduces an attacker's expected payoff in real-w…

The paper introduces C-MADF, a causally constrained multi-agent framework that significantly reduces false positives in autonomous cyber defense by restricting response actions to structurally consist…

The paper introduces MAGE, a novel defensive framework that uses a dedicated 'shadow memory' to proactively detect and mitigate long-horizon threats against LLM agents during complex, multi-step inter…

The paper proposes the Layered Attack Surface Model (LASM), a structural taxonomy that maps security threats and defenses across the complex, multi-layered architecture of AI agents, revealing signifi…

DeepStage is a deep reinforcement learning framework that achieves autonomous, stage-aware defense against multi-stage APT campaigns by fusing graph-based telemetry and predicting attacker stages.

This paper analyzes attacks against centralized agent governance systems (SAGA) when the central provider is compromised and proposes three novel, trade-off-aware architectures (SAGA-BFT, SAGA-MON, SA…

The paper proposes an autonomous red teaming framework combining LLMs and RL to generate sophisticated, multi-stage cyber attack campaigns, demonstrating its necessity for evaluating robust AI-enabled…

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…

SafeMCP is a server-side defense plugin that uses look-ahead reasoning to proactively filter and constrain tool acquisition for LLM agents, thereby mitigating catastrophic risks associated with expand…

The paper proposes a novel attack paradigm demonstrating how compromising a single robot in an LLM-controlled multi-robot system can rapidly propagate malicious intent to cause coordinated unsafe acti…

This paper demonstrates that a complex deep reinforcement learning policy for power grid control can be successfully distilled into a lightweight, auditable decision tree and random forest surrogate t…

This paper proposes a lightweight, multi-layer Machine Learning-based security framework for Industrial IoT (IIoT) to enhance trust convergence and detect advanced threats.

This paper proposes a set of design principles and a conceptual benchmark (SOC-bench) to systematically evaluate the blue team operational capabilities of multi-agent AI systems in autonomous Security…

The paper introduces APIOT, the first LLM framework capable of autonomously performing the full discovery, exploitation, patching, and verification cycle against bare-metal industrial OT devices.

This paper introduces Mobius Injection, a novel, lightweight attack that weaponizes autonomous LLM agents into zombie nodes to launch highly scalable AbO-DDoS attacks by exploiting a vulnerability cal…

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…

The paper introduces Governed MCP, a kernel-resident gateway that enforces comprehensive, robust tool governance for AI agents' privileged tool calls, significantly improving safety beyond userspace m…