OpenAlex ·
Separation of Duties for Privileged LLM Agents: A Governed Execution Architecture with Measured Security-Utility Trade-offs
- Published
- Source
- OpenAlex
- Published in
- arXiv (Cornell University)
- DOI
- 10.48550/arxiv.2609.38224
- Original
- Read it at the publisher
- Topics
Abstract
Large language model agents are increasingly granted real privileges (executing commands, modifying files, calling APIs), so an agent that errs has already acted. Existing defences concentrate on the agent's inputs, while the path from a candidate action to privileged side effects remains less directly studied. We argue that this path must be governed outside the model, and study an architecture interposing four roles (planner, policy gate, executor, auditor) between agent and operating system. Two choices are central: actions arrive as structured intents, so adjudication never parses shell syntax; and approval is a one-shot credential bound to the exact bytes that will run. We evaluate on a 313-case benchmark across eight variants, with prompt-only baselines from three hosted LLMs on 150 stratified cases, five repetitions (2,250 attempted calls; 2,249 completed). Effective attack success falls from 98.3% under direct execution to 7.7% deployed. Re-execution against the real implementation yields a similar aggregate rate (7.6% over 66 sandbox-evaluable payloads) but substantial case-level disagreement, at a corrected false-denial rate of 11.1%. A substantial final-stage reduction (from 30.8% to 7.7%) is attributable to the operating-system sandbox, and the benchmark found four implementation defects, none by design review.
The authors’ abstract, as arXiv lists it. arXiv’s listings, abstracts included, are free for anyone to reuse.
Read it on ReadSearch
Each opens after you create an account, and brings you back to this paper.
More in Artificial Intelligence
BEHAVE: Functional Behavior Modeling Enables Self-Improving Agents for Hardware Design and Verification
Making Analog Training Scale: Co-Designing Mapping, Optimizer, and Converters
Analog Computing revisited: A fully analog and minimalistic Damage Detector for Ultrasonic Testing enabling Material-Integrated Structural Health Monitoring
cktFormer: Transformer-Based Approach for Automated Analog Circuit Design
GEM-KMeans: Memory-Efficient and Accurate Clustering on Massive Scale with GPU Optimization
Get the few papers worth your time in Artificial Intelligence every morning.
ReadSearch reads the new papers in your field each day and brings you the few worth reading, each with its key finding in a sentence.