Canonical URL: [https://www.taislab.co.kr/](https://www.taislab.co.kr/) # Trust AI & Security Lab, TAIS We study security with LLMs and security for LLMs, grounded in secure software engineering and federated learning security. [Explore our research](/research/) [View publications](/publications/) ## News Jun 06, 2026 — “PI-FD: Property Inference Attacks on Federated Learning With Distillation via Synthetic Data Generation” was published in [*IEEE Access*](https://doi.org/10.1109/ACCESS.2026.3700259). May 11, 2026 — “VulScope: Software Vulnerability Detection via Local Context Analysis and Verification” was accepted for publication in [*Empirical Software Engineering*](/publications/#kim2026vulscope). Apr 15, 2026 — Our study, “Rethinking the Capability of Fine-Tuned Language Models for Automated Vulnerability Repair,” was presented in the [ICSE 2026 Research Track](https://conf.researchr.org/details/icse-2026/icse-2026-research-track/125/Rethinking-the-Capability-of-Fine-Tuned-Language-Models-for-Automated-Vulnerability-R). The work introduces execution-based evaluation for learning-based vulnerability repair.