Salience Induction against Multi-Hop RAG Agents: Threat and Defense

Agentic retrieval-augmented generation RAG systems increasingly retrieve external evidence and orchestrate tools for knowledge-intensive applications. In Multi-Hop question answering, agents chain facts across documents. Existing defenses focus on content poisoning, which injects false facts, and...

Owner-Harm: A Missing Threat Model for AI Agent Safety

Existing AI agent safety benchmarks focus on generic criminal harm cybercrime, harassment, weapon synthesis, leaving a systematic blind spot for a distinct and commercially consequential threat category: agents harming their own deployers. Real-world incidents illustrate the gap: Slack AI...

Meridian: Multiple defense-in-depth gaps (collection/depth caps, telemetry, retry, fan-out)

Summary Meridian v2.1.0 Meridian.Mapping and Meridian.Mediator shipped with nine defense-in-depth gaps reachable through its public APIs. Two are HIGH severity — the advertised DefaultMaxCollectionItems and DefaultMaxDepth safety caps are silently bypassed on the IMapper.Mapsource, destination...

Cybersecurity of Teleoperated Quadruped Robots: A Systematic Survey of Vulnerabilities, Threats, and Open Defense Gaps

Teleoperated quadruped robots are increasingly deployed in safety-critical missions -- industrial inspection, military reconnaissance, and emergency response -- yet the security of their communication and control infrastructure remains insufficiently characterized. Quadrupeds present distinct...

Crash Tests for Security: Why BAS Is Proof of Defense, Not Assumptions

Car makers don’t trust blueprints. They smash prototypes into walls. Again and again. In controlled conditions. Because design specs don’t prove survival. Crash tests do. They separate theory from reality. Cybersecurity is no different. Dashboards overflow with “critical” exposure alerts...