Jin Song Dong

ARuleCon is an agentic framework that autonomously and accurately converts security rules across heterogeneous SIEM platforms, significantly outperforming baseline LLMs in fidelity.

FunPoison introduces a functionality-preserving poisoning technique that injects small, compilable weak-use fragments into code datasets to prevent unauthorized use of CodeLLMs without breaking the code's functionality.

The paper introduces POLARIS, a novel framework that systematically generates comprehensive and verifiable safety tests for LLMs by formalizing natural language policies into First-Order Logic and exploring the resulting Semantic Policy Graph.

The paper introduces BITE, a black-box adversarial framework that exploits stylistic biases in LLM judges by adaptively generating semantically equivalent edits to artificially inflate assigned scores.