2 papers
cs.CR2026
API Secrets Should Never Become Tokens in the LLM's Vocabulary: A Threat Analysis of API Credential Handling in LLM Agent Systems and an Empirical Evaluation of a Vault-Mediated Execution Boundary
Patrick Kenney, Hadi Ahmadi, Denis Lusson +2
Tool-using large language model (LLM) agents turn credential hygiene from a storage problem into an execution-security problem. A key pasted into a prompt, or embedded in a system…
cs.IR2025
From Search to Reasoning: A Five-Level RAG Capability Framework for Enterprise Data
Gurbinder Gill, Ritvik Gupta, Denis Lusson +2
Retrieval-Augmented Generation (RAG) has emerged as the standard paradigm for answering questions on enterprise data. Traditionally, RAG has centered on text-based semantic search…