Jun Li
7 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces SET, a robust input-level backdoor detection framework that detects hidden malicious triggers in text-to-image diffusion models by analyzing systematic differences in how benign and backdoor inputs respond to controlled cross-attention scaling perturbations.
The paper introduces TICoE, a text-image collaborative framework that achieves precise and faithful concept removal from text-to-image generative models, surpassing existing methods in both precision and content fidelity.
This study analyzes over 20,000 real-world coding sessions to show that AI coding agents frequently fail users through subtle misalignment, requiring constant manual correction even when major system damage is avoided.
This study analyzes over 20,000 real-world coding sessions to show that AI coding agents frequently fail users through subtle misalignment, requiring constant manual correction even when major system damage is avoided.
This paper proposes a standardized task specification language and rulebook for EEG datasets to enable reusable and auditable benchmarking infrastructure.
This paper introduces DiStash, a disaggregated transactional key-value store that enables an application to use a single transaction to manage key-value pairs across different pools of stashes, preventing race conditions and data loss.
A post-retrieval defense, GuardRAG, is proposed to mitigate corpus poisoning attacks on Large Language Models.
Papers
GuardRAG: A Post-Retrieval Defense against Poisoning Attacks in Retrieval-Augmented Generation
Linghui Jiao, Kang Wei, Fushuo Huo, Ruijie Zhao +4 more
A post-retrieval defense, GuardRAG, is proposed to mitigate corpus poisoning attacks on Large Language Models.