2 citations · 4 across the 8 of their papers we have counts for
Showing 2026 · cs.SEShow all
3 papers · 2 filters
cs.SE2026
RAISE: Reinforcing Access Control Policy Synthesis in LLMs via Symbolic Evaluation
Yingming Zhou, Adarsh Vatsa, William Eiers
Translating natural-language access-control requirements into policies requires careful reasoning about permissions, constraints, and exceptions, and even frontier LLMs often produ…
cs.SE2026
AutoCedar: An Agentic Framework for Verifier-Guided Access Control Policy Synthesis
Adarsh Vatsa, Sachi Shome, Yingming Zhou +1
Large Language Models are increasingly used to turn natural-language requirements into code. In access control, that shortcut is dangerous: a generated policy can compile and read…
cs.SE2026
Neurosymbolic Auditing of Natural-Language Software Requirements
Bethel Hall, William Eiers
Natural-language software requirements are often ambiguous, inconsistent, and underspecified; in safety-critical domains, these defects propagate into formal models that verify the…