Yansong Gao

The paper evaluates multi-LLM strategies for secure code generation, finding that hybrid pipelines combining ensembling, static analysis, and patching achieve the strongest security performance, outperforming single models and purely collaborative systems.

ArmSSL is a novel watermarking framework that provides robust, black-box ownership verification for self-supervised learning encoders while maintaining high utility and resisting adversarial attacks.

This paper repurposes the statistical signals from data-poisoning backdoor attacks on contrastive learning (CL) models to create a multi-level, effective watermarking scheme for dataset intellectual property (IP) protection.