CyberIntel ⬡ News
★ Saved ◆ Cyber Reads
← Back ◬ AI & Machine Learning

ILION: Deterministic Pre-Execution Safety Gates for Agentic AI Systems

arXiv AI Archived Mar 17, 2026 ✓ Full text saved

arXiv:2603.13247v1 Announce Type: new Abstract: The proliferation of autonomous AI agents capable of executing real-world actions - filesystem operations, API calls, database modifications, financial transactions - introduces a class of safety risk not addressed by existing content-moderation infrastructure. Current text-safety systems evaluate linguistic content for harm categories such as violence, hate speech, and sexual content; they are architecturally unsuitable for evaluating whether a pr

Full text archived locally
✦ AI Summary · Claude Sonnet


    Computer Science > Artificial Intelligence [Submitted on 22 Feb 2026] ILION: Deterministic Pre-Execution Safety Gates for Agentic AI Systems Florin Adrian Chitan The proliferation of autonomous AI agents capable of executing real-world actions - filesystem operations, API calls, database modifications, financial transactions - introduces a class of safety risk not addressed by existing content-moderation infrastructure. Current text-safety systems evaluate linguistic content for harm categories such as violence, hate speech, and sexual content; they are architecturally unsuitable for evaluating whether a proposed action falls within an agent's authorized operational scope. We present ILION (Intelligent Logic Identity Operations Network), a deterministic execution gate for agentic AI systems. ILION employs a five-component cascade architecture - Transient Identity Imprint (TII), Semantic Vector Reference Frame (SVRF), Identity Drift Control (IDC), Identity Resonance Score (IRS) and Consensus Veto Layer (CVL) - to classify proposed agent actions as BLOCK or ALLOW without statistical training or API dependencies. The system requires zero labeled data, operates in sub-millisecond latency, and produces fully interpretable verdicts. We evaluate ILION on ILION-Bench v2, a purpose-built benchmark of 380 test scenarios across eight attack categories with 39% hard-difficulty adversarial cases and a held-out development split. ILION achieves F1 = 0.8515, precision = 91.0%, and a false positive rate of 7.9% at a mean latency of 143 microseconds. Comparative evaluation against three baselines - Lakera Guard (F1 = 0.8087), OpenAI Moderation API (F1 = 0.1188), and Llama Guard 3 (F1 = 0.0105) - demonstrates that existing text-safety infrastructure systematically fails on agent execution safety tasks due to a fundamental task mismatch. ILION outperforms the best commercial baseline by 4.3 F1 points while operating 2,000 times faster with a false positive rate four times lower. Comments: 16 pages, 7 tables, 7 figures. Benchmark and code available at this https URL. Patent application A/00052, OSIM Romania Subjects: Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR) ACM classes: I.2.11; D.4.6; K.6.5 Cite as: arXiv:2603.13247 [cs.AI]   (or arXiv:2603.13247v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2603.13247 Focus to learn more Submission history From: Florin-Adrian Chitan [view email] [v1] Sun, 22 Feb 2026 12:25:42 UTC (1,004 KB) Access Paper: view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-03 Change to browse by: cs cs.CR References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation 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 Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)
    💬 Team Notes
    Article Info
    Source
    arXiv AI
    Category
    ◬ AI & Machine Learning
    Published
    Archived
    Mar 17, 2026
    Full Text
    ✓ Saved locally
    Open Original ↗