Risk-Calibrated Bayesian Streaming Intrusion Detection with SRE-Aligned Decisions
cs.CR, cs.LG
Submitted: 2025-09-17
Updated: 2026-09-14
Comments: v2: correction note added (title page and abstract). An audit of the shared codebase found the score, threshold, and latency descriptions unsupported by the implementation, and the evaluation streams to be assembled constructions. No quantitative result tables are affected. See arXiv:2605.24696 (corrected v3) and doi:10.5281/zenodo.22673735
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
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