paper-with-me

Papers

Session Risk Memory (SRM): Temporal Authorization for Deterministic Pre-Execution Safety Gates

2026-03-22 · Florin Adrian Chitan arxiv

Deterministic pre-execution safety gates evaluate whether individual agent actions are compatible with their assigned roles. While effective at per-action authorization, these systems are structurally blind to distributed attacks that decompose harmful intent across multiple individually-compliant steps. This paper introduces Session Risk Memory (SRM), a lightweight deterministic module that extends stateless execution gates with trajectory-level authorization. SRM maintains a compact semantic centroid representing the evolving behavioral profile of an agent session and accumulates a risk signal through exponential moving average over baseline-subtracted gate outputs. It operates on the same semantic vector representation as the underlying gate, requiring no additional model components, training, or probabilistic inference. We evaluate SRM on a multi-turn benchmark of 80 sessions containing slow-burn exfiltration, gradual privilege escalation, and compliance drift scenarios. Results show that ILION+SRM achieves F1 = 1.0000 with 0% false positive rate, compared to stateless ILION at F1 = 0.9756 with 5% FPR, while maintaining 100% detection rate for both systems. Critically, SRM eliminates all false positives with a per-turn overhead under 250 microseconds. The framework introduces a conceptual distinction between spatial authorization consistency (evaluated per action) and temporal authorization consistency (evaluated over trajectory), providing a principled basis for session-level safety in agentic systems.

📄 PDF Abstract BibTeX arXiv:2603.22350

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Before the Tool Call: Deterministic Pre-Action Authorization for Autonomous AI Agents

2026-03-21 · Uchi Uchibeke arxiv

AI agents today have passwords but no permission slips. They execute tool calls (fund transfers, database queries, shell commands, sub-agent delegation) with no standard mechanism to enforce authorization before the acti…

LT-Mem: Volatility-Aware Spatio-Temporal Memory for Lifelong Scene Understanding

2026-08-19 · Yumin Lee, Hyoseok Ju, Giseop Kim arxiv

Long-term robot operation in evolving environments requires object-level understanding that persists across repeated revisits. Existing systems either overwrite history to maintain an up-to-date map or store semantic sna…

Scene Understanding

SoK: Trust-Authorization Mismatch in LLM Agent Interactions

2025-12-07 · Guanquan Shi, Haohua Du, Zhiqiang Wang, Xiaoyu Liang 외 arxiv

Large Language Models (LLMs) are evolving into autonomous agents capable of executing complex workflows via standardized protocols (e.g., MCP). However, this paradigm shifts control from deterministic code to probabilist…

Hybrid Inspection and Task-Based Access Control in Zero-Trust Agentic AI

2026-05-04 · Majed El Helou, Benjamin Ryder, Chiara Troiani, Jean Diaconu 외 arxiv

Authorizing Large Language Model (LLM)-driven agents to dynamically invoke tools and access protected resources introduces significant security risks, and the risks grow dramatically as agents engage in multi-turn conver…

Temporal Validity on Real Software Histories: Eliminating Stale-Fact Errors in Code-Assistant Memory over GitHub Fixes

2026-08-21 · Neeraj Yadav arxiv

Retrieval-augmented generation (RAG) has no model of time: when a fact changes across a coding session - a function is renamed, an endpoint moves, a dependency is bumped - RAG retrieves both the old and new value with ne…