This paper reviews cybersecurity vulnerabilities in CubeSats, proposing TinyML-based, resource-efficient intrusion detection systems to address limitations of traditional security measures.

The paper introduces a threat-oriented digital twinning methodology to enable reproducible and controllable cybersecurity evaluation of autonomous platforms, overcoming limitations in accessing real-w…

The paper develops a novel, resource-aware cybersecurity risk assessment framework specifically tailored for power-limited CubeSat missions, demonstrating that adapting controls can significantly impr…

This paper addresses the critical need for trustworthy LLMs in science by proposing a comprehensive, multi-layered defense framework and methodology to evaluate unique scientific vulnerabilities.

The paper details a data science competition focused on identifying hidden backdoor triggers (trojan horses) in deep forecasting models used for critical space operations.

This paper provides the first systematic threat analysis of State-Space Models (SSMs) in safety-critical applications, introducing novel attack classes and formal metrics to quantify their security an…

This paper systematically analyzes 48 studies on perception attacks against autonomous vehicles, revealing that the increasing reliance on multi-sensor fusion creates new, complex vulnerabilities that…

The paper proposes an end-to-end LLM framework that automates SOC operations by integrating ensemble-based threat detection, syntax-constrained query generation, and evidence-grounded incident resolut…

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 a cross-layer behavioral fingerprinting framework that fuses physical and network data to detect comprehensive attacks in dense LEO satellite constellations, achieving high detectio…

The paper introduces Glass Box, a runtime constitutional AI verification layer designed to ensure the safety and adherence to physical laws for autonomous AI systems operating in orbital data centers.

The paper proposes a proactive, resilient architecture for autonomous vehicles by integrating redundancy, diversity, and adaptive reconfiguration to defend against various cyber and physical attacks.

Space Fabric introduces a novel satellite-based Trusted Execution Architecture (TEE) that establishes trust for orbital computing by generating cryptographic secrets and binding workload execution to…

The paper introduces TrojanMerge, a framework demonstrating that model merging can be exploited to systematically compromise the safety alignment of multiple individually safe LLMs.

SentinelSphere is an AI platform that integrates advanced deep learning for real-time threat detection with an LLM-powered training system to holistically address both technical and human-factor cyber…

The paper demonstrates a semantic denial-of-service attack against LLM-controlled robots by injecting short, safety-plausible phrases into the audio channel, causing the robot to halt or disrupt execu…

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…

This paper proposes using cyber deception with honey drones (HDs) to defend UAV mission systems against Denial-of-Service (DoS) attacks, achieving superior performance using a novel Hypergame-Theoreti…

The paper introduces a challenging benchmark for LLM agents to perform unsupervised threat hunting on raw Windows event logs, finding that current frontier models perform poorly and are not ready for…

The paper introduces ASTRAL, a multimodal LLM-driven framework that reconstructs and analyzes fragmented cyber-physical system architectures to enable comprehensive and quantitative security risk asse…