TechniqueRLHF / Alignment7 recent entries30 Jul 2026Batten Down Your Packages: Mitigation Guidance for Supply Chain CompromiseWritten by: Kelli Vanderlee, Stuart Carrera For years, the cybersecurity industry's understanding of software supply chain compromise has been anchored by a few watershed events, including Russian cyb→4 Aug 2026When Collaboration Becomes a Trigger: Collective Evidence-Threshold Backdoors in Multi-Agent SystemsarXiv:2608.01085v1 Announce Type: cross Abstract: LLM-based multi-agent systems (MAS) extend LLM capabilities through iterative communication and shared contexts. However, this collaboration introduce
TechniqueRAG2 recent entries7 Jul 2026CAGE-1: Control, Assurance, and Governance Evaluation for Enterprise Agentic AIarXiv:2607.03510v1 Announce Type: cross Abstract: Enterprise artificial intelligence is moving from experimentation into operational workflows. Early programs focused on model access and retrieval-aug→14 Sept 2026Repair Before Reinforce: Context-Augmented Knowledge Graph Reasoning for Multi-Hop Question AnsweringarXiv:2609.12230v1 Announce Type: new Abstract: Question-answering often requires reasoning across multiple connected facts rather than retrieving a single isolated relation. Knowledge graphs (KGs) pr
TechniqueAgents8 recent entries23 Sept 2026The Price of Safety: Benign-Case Utility and Token Overhead of Memory-Poisoning Defenses in LLM AgentsarXiv:2609.22818v1 Announce Type: cross Abstract: Memory-poisoning defenses for LLM agents are typically evaluated by their ability to prevent attacks. However, the traffic they process is rarely adve→24 Sept 2026Proactive Defense: Hardening Code Pipelines and CI/CD InfrastructureIntroduction The landscape of software supply chain security has undergone a significant shift. Recent campaigns demonstrate that sophisticated threat actors are systematically targeting the engineeri→24 Sept 2026False-science induction in autonomous scientific discoveryarXiv:2609.27883v1 Announce Type: cross Abstract: Closed-loop discovery systems increasingly execute experiments and update decisions autonomously, turning record integrity into part of the experiment→28 Sept 2026Nvidia says its new AI safety platform can contain rogue agents within ‘milliseconds’Nvidia is launching a new safety platform designed to contain and monitor AI agents, a move that comes in response to a wave of rogue hacking incidents, as reported earlier by Reuters. In an announcem→28 Sept 2026NVIDIA Open Agent Safety Platform Reference Design combines NVIDIA OpenShell and NVIDIA Sentry. OpenShell is an open-source secure runtime t…NVIDIA Open Agent Safety Platform Reference Design combines NVIDIA OpenShell and NVIDIA Sentry. OpenShell is an open-source secure runtime that gives AI agents clear, enforceable boundaries. It traces→2 Oct 2026Fault-Tolerant Budget Conservation in Distributed Multi-Agent DelegationarXiv:2610.00349v1 Announce Type: new Abstract: Resource limits are becoming an authorization boundary for AI agents that delegate work across concurrent and failure-prone workers. Parent-child alloca→5 Oct 2026Securing Computer-Use Agents Against Branch Steering AttacksarXiv:2610.03089v1 Announce Type: cross Abstract: Modern Computer Use Agents (CUAs) directly interact with graphical user interfaces and execute third-party web tools, exposing them to indirect prompt→8 Oct 2026Constrained-Action AI Remediation for SIEM/XDR via a NeMo-Guardrails ProxyarXiv:2610.09906v1 Announce Type: cross Abstract: Security Operations Centers (SOCs) for information technology and operational technology share one incident-response problem: a flood of correlated al
TechniqueFine-tuning2 recent entries14 Sept 2026Repair Before Reinforce: Context-Augmented Knowledge Graph Reasoning for Multi-Hop Question AnsweringarXiv:2609.12230v1 Announce Type: new Abstract: Question-answering often requires reasoning across multiple connected facts rather than retrieving a single isolated relation. Knowledge graphs (KGs) pr→2 Oct 2026Backdoor Containment via Expert Quarantine and Shutdown in LLMsarXiv:2610.00663v1 Announce Type: new Abstract: Backdoored large language models (LLMs) can behave normally on benign inputs while producing attacker-specified outputs under hidden triggers. Existing
TechniqueMultimodal1 recent entries3 Aug 2026When Unlearning Fails: Reliable Data Deletion under Post-Training in Agent NetworksarXiv:2607.28829v1 Announce Type: cross Abstract: Self-improving federated agent networks keep training after deployment by collecting new trajectories with the current policy and feeding them back in
TechniqueSafety8 recent entries15 Sept 2026AcquireBound: Runtime Authorization for Resources Acquired by AI AgentsarXiv:2609.14744v1 Announce Type: new Abstract: By acquiring compute, credentials, accounts, services, and other agents, autonomous AI agents can introduce new authority into a task. Payment, budget, →18 Sept 2026PAPC: Platform Mediation for Privacy-Propagation Externalities in AI-Mediated WorkflowsarXiv:2609.19226v1 Announce Type: cross Abstract: AI-mediated platforms coordinate work through LLM agents acting for different principals. In these workflows, privacy loss can be created before a fin→23 Sept 2026The Price of Safety: Benign-Case Utility and Token Overhead of Memory-Poisoning Defenses in LLM AgentsarXiv:2609.22818v1 Announce Type: cross Abstract: Memory-poisoning defenses for LLM agents are typically evaluated by their ability to prevent attacks. However, the traffic they process is rarely adve→24 Sept 2026Proactive Defense: Hardening Code Pipelines and CI/CD InfrastructureIntroduction The landscape of software supply chain security has undergone a significant shift. Recent campaigns demonstrate that sophisticated threat actors are systematically targeting the engineeri→28 Sept 2026Nvidia says its new AI safety platform can contain rogue agents within ‘milliseconds’Nvidia is launching a new safety platform designed to contain and monitor AI agents, a move that comes in response to a wave of rogue hacking incidents, as reported earlier by Reuters. In an announcem→28 Sept 2026NVIDIA Open Agent Safety Platform Reference Design combines NVIDIA OpenShell and NVIDIA Sentry. OpenShell is an open-source secure runtime t…NVIDIA Open Agent Safety Platform Reference Design combines NVIDIA OpenShell and NVIDIA Sentry. OpenShell is an open-source secure runtime that gives AI agents clear, enforceable boundaries. It traces→2 Oct 2026Fault-Tolerant Budget Conservation in Distributed Multi-Agent DelegationarXiv:2610.00349v1 Announce Type: new Abstract: Resource limits are becoming an authorization boundary for AI agents that delegate work across concurrent and failure-prone workers. Parent-child alloca→8 Oct 2026Constrained-Action AI Remediation for SIEM/XDR via a NeMo-Guardrails ProxyarXiv:2610.09906v1 Announce Type: cross Abstract: Security Operations Centers (SOCs) for information technology and operational technology share one incident-response problem: a flood of correlated al