VU#754548: Cinnamon's kotaemon contains improper authorization checks in Kotaemon multi‑user chat handlers
3 min
Only Pay What You Must Spend: On-Demand Privacy Budget Payment for Differentially Private RAG
Automated Extraction of Records of Processing Activities (RoPA) Using Hybrid RAG and Locally Deployed Large Language Models
Show HN: AI·rete·RAG – a Rete rule engine decides, RAG explains why
Design and Evaluation of a Controlled Post-Alert Incident Orchestration and Response Subsystem Using a Rule Engine and a Local Large Language Model
BackTrend: Evaluating Scientific Weak-Signal Prediction via Backward Reconstruction
The Copy Ceiling: An Input-Exposure Control for Ontology-Grounded Generation over Curated Corpora
Document Retrieval-Aware Chunking (D-RAC): Universal Retrieval-Aware Ingestion of Enterprise Documents via PDF Normalization and Multimodal Markdown Conversion
Predictable Failure in Multi-Hop Retrieval: Score-Distributional Confidence Scoring and Abstention
An Interpretable Memory Decision Controller for LLM Agents Based on Three-Signal Complementarity: Decoupling Confidence and Consistency
Micro-Collaborative Poisoning: A Distributed Attack on RAG Systems
RAFT: A Stateful Retrieval-Augmented Framework for Troubleshooting Agents
1
Q&A on Any Spreadsheet Requires Interpreting Its Grid Structure
Better Vector Search for Long Documents: Chunking Inside Manticore Search
15 min
Google Research Introduces Retrieve-for-Train (R4T): An RL-Compiled Diffusion Retriever for 12× to 20× Faster Query Fan-Out
4 min1
Beyond Private Training: The New Landscape of AI Privacy
Self-Evolving Search Index
InceptionRAG: Stealthy Poisoning Attack Against Retrieval-Augmented Generation
1
CiteShade: Citation Laundering in Multi-Source Retrieval-Augmented Generation and Its Counterfactual Defense
1
Approval Integrity and Recovery in LLM Answer Publication
A Graph-Based Approach for Mapping Kernel-Level Telemetry to MITRE ATT&CK
Bridging the First-Hour Gap: Evaluating AI Reliability and Benchmarking Deficiencies in Cyber Incident Response for Law Enforcement
Atlas: Efficient Verifiable Semantic Search
4