Jev-Guard: Fast Routing and Auditing Agent Actions over Editable Policy Trees
cs.CR, cs.CL
Submitted: 2026-10-13
Updated: 2026-10-13
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- PhreshPhish: A Real-World, High-Quality, Large-Scale Phishing Website Dataset and Benchmark
- AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
- OmniCompliance-100K: A Multi-Domain, Rule-Grounded, Real-World Safety Compliance Dataset
- Towards Trustworthy Multimodal Moderation via Policy-Aligned Reasoning and Hierarchical Labeling
- GSPR: Aligning LLM Safeguards as Generalizable Safety Policy Reasoners
- SafeMT: Multi-turn Safety for Multimodal Language Models
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills
- Token Composition: A Graph Based on EVM Logs