BSLI is a Bayesian selective inference method that maintains posteriors over latent burden and identifiability, uses scientific gates for answerability, and optimizes cost-calibrated query-stop decisions via an exact Bellman policy, showing improved performance on a large benchmark.
CORTEX: Collaborative LLM Agents for High-Stakes Alert Triage, September 2025
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
years
2026 10roles
background 3representative citing papers
ZERO-APT is a closed-loop framework that integrates an LLM attacker, configurable LLM defender, and judge agent to achieve 79% attack success rate, 0.860 causal consistency, and full decision auditability in penetration testing under intelligent defense.
DTDA is an LLM agent that produces novel security alerts at 80.1% customer-validated precision and 0.78 F1 on hidden activity while running at production scale inside Microsoft Defender.
AI-native asset intelligence framework converts heterogeneous security signals into normalized asset importance scores by separating intrinsic exposure from contextual factors using modeling and deterministic aggregation.
A RAG system with query-based log filtering achieves up to 94% recall in malware incident analysis and 96% attack-step detection, with ablation studies confirming the filtering step is essential.
Proposes a typed Security Context enforced across LLM agent components, Runtime Core, Tool Adapter Layer, and HITL gates for auditable, scoped cybersecurity workflows.
CyberAId is a proposed on-premise multi-agent system that coordinates LLM subagents with classical security tools to improve threat response and regulatory alignment in financial services.
The report defines AI integrity threats (model sabotage and subversion) and recommends four US government policy actions to defend frontier AI systems against backdoors and secret loyalties.
A literature survey synthesizes 119 studies on AI-driven alert screening into a four-stage taxonomy of filtering, triage, correlation, and generative augmentation while identifying gaps in deployment realism and robustness.
citing papers explorer
-
AI Integrity: Defending Against Backdoors and Secret Loyalties
The report defines AI integrity threats (model sabotage and subversion) and recommends four US government policy actions to defend frontier AI systems against backdoors and secret loyalties.