[2603.22350] Session Risk Memory (SRM): Temporal Authorization for Deterministic Pre-Execution Safety Gates

-->

Computer Science > Artificial Intelligence

arXiv:2603.22350 (cs)

[Submitted on 22 Mar 2026]

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

Authors:Florin Adrian Chitan<br>View a PDF of the paper titled Session Risk Memory (SRM): Temporal Authorization for Deterministic Pre-Execution Safety Gates, by Florin Adrian Chitan

View PDF

Abstract: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.

Comments:<br>12 pages, 3 figures. Companion paper to arXiv:2603.13247. Benchmark dataset and artifacts available on Zenodo: https://doi.org/10.5281/zenodo.15410944

Subjects:

Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR)

ACM classes:<br>I.2.11; D.4.6; K.6.5

Cite as:<br>arXiv:2603.22350 [cs.AI]

(or<br>arXiv:2603.22350v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2603.22350

Focus to learn more

arXiv-issued DOI via DataCite

Submission history<br>From: Florin-Adrian Chitan [view email]<br>[v1]<br>Sun, 22 Mar 2026 08:30:28 UTC (548 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Session Risk Memory (SRM): Temporal Authorization for Deterministic Pre-Execution Safety Gates, by Florin Adrian Chitan<br>View PDF

view license

Current browse context:

cs.AI

next >

new<br>recent<br>| 2026-03

Change to browse by:

cs<br>cs.CR

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .

Which authors of this paper are endorsers? |<br>Disable MathJax (What is MathJax?)