AgentGuardian: Learning Access Control Policies to Govern AI Agent Behavior

Kari Jaaskelainen

16 Jan 2026 — 1 min read

AI agents can be powerful—and unpredictable. AgentGuardian is a new security framework that keeps them on-task by learning and enforcing access rules tailored to each agent.

How it works:

Staging phase: It watches the agent run in a controlled setting, logging execution traces and typical inputs to learn what “legitimate” behavior looks like.
Adaptive policies: From this, it builds context-aware rules that govern tool calls in real time, using both incoming input and the control flow of multi-step actions.

Why it matters: AgentGuardian flags malicious or misleading inputs without blocking normal work. Its control-flow-based checks also curb hallucination-driven errors and other orchestration glitches.

Tested on two real-world AI agent applications, the framework improved safety while preserving functionality.

Bottom line: smarter guardrails for agents that act—and interact—in the real world.

Paper: https://arxiv.org/abs/2601.10440v1

Authors: Nadya Abaev, Denis Klimov, Gerard Levinov, David Mimran, Yuval Elovici, Asaf Shabtai

Paper: https://arxiv.org/abs/2601.10440v1

Register: https://www.AiFeta.com

AI AIAgents Security AccessControl LLM Safety Cybersecurity ResponsibleAI arXiv

Meet GRACE: a moral governor for safer, more transparent AI

AI agents are getting powerful—so how do we make sure they do the right thing, not just the effective thing? Meet GRACE, a reason-based moral governor that keeps AI behavior aligned with human norms by separating moral reasoning from goal-driven decision-making. * Moral Module: uses deontic logic and explicit reasons

Why some fine-tuned LLMs miss phishing—and how to fix it

Not all fine-tuned LLMs spot phishing equally. A new study tests Llama 3.1 8B, Gemma 2 9B, and Mistral on high-stakes phishing detection—and uses SHAP and mechanistic interpretability to reveal why models do (or don’t) generalize. * Architecture × data diversity matters: Gemma 2 9B hits state-of-the-art performance (F1

AI that explains itself—by following the science

AI that explains itself—by following the science Black-box AI can be powerful, but it often can’t tell us why it made a decision. Concept Bottleneck Models (CBMs) try to fix that by predicting human-understandable concepts first, then the final answer. The catch: standard CBMs ignore domain-specific cause-and-effect and

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

TL;DR: Finding reliable answers in genomics is hard. GenomAgent turns one big AI into a coordinating team of specialists—and beats the current leader by 12% on a key benchmark. Genomic facts live across many databases. Standard chatbots struggle because they can’t flexibly query those sources. GeneGPT added

Read more

Meet GRACE: a moral governor for safer, more transparent AI

Why some fine-tuned LLMs miss phishing—and how to fix it

AI that explains itself—by following the science

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A