arXiv AI
AuthGateBench: Benchmarking LLMs as Authorization Gate
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Oct 15
Same Operation, Different Permission: Evaluating Whether Guardrails Honor Authorization
arXiv:2610.16838v1 Announce Type: new Abstract: As language-model agents write code, move money and change records on behalf of users, deciding whether an action is authorized has become a central sa...
arXiv AI
Jul 24
GuardianAgentBench: Where Agents Fail and How to Guard Them
arXiv:2607. 20982v1 Announce Type: new Abstract: As large language model agents increasingly operate autonomously with access to tools and external environments, ensuring their safe and reliable behavior becomes critical.
arXiv AI
Sep 23
ActGov: Governing LLM Agent Actions via Policy-Constrained Validation
ActGov is a runtime enforcement framework that validates each action proposed by a large language model (LLM) agent before it interacts with external tools, ensuring that actions stay within task‑scoped authorization boundaries and comply with dynamically constructed policies. It builds policies from tool specifications, benign tasks, and failure traces, verifying updates via SMT‑based counterexample checking. In evaluations on AgentDojo and AgentDyn benchmarks, ActGov consistently reduces indirect prompt‑injection attack success while maintaining task utility, outperforming existing defenses.
Hugging Face Trending Papers
Sep 21
ActGov: Governing LLM Agent Actions via Policy-Constrained Validation
Large language model (LLM) agents increasingly execute long-horizon workflows through external tools, allowing untrusted outputs to influence subsequent actions and exceed user authorization. Existing...
arXiv AI
Jul 3
Behind the Refusal: Determining Guardrail Activation via Behavioral Monitoring
arXiv:2607. 02121v1 Announce Type: cross Abstract: As Large Language Models (LLMs) and agentic systems become integrated into real-world applications, ensuring their safety and security is critical.
arXiv AI
Oct 12
Cancerous Backdoor Attack: Gradual Activation via Invisible Tokens and A Stage Controller
The paper introduces the Cancerous Backdoor Attack, a novel backdoor technique for large language models that activates gradually through multiple hidden stages rather than a single trigger-response. It uses invisible tokens to embed intermediate stages into the model’s reasoning process and a stage controller to monitor the attack’s progression during inference. Experiments on various reasoning datasets show that this method consistently corrupts model outputs over time and outperforms existing backdoor baselines.