Scholar
Jingwei Yi
Google Scholar ID: BPnONGoAAAAJ
University of Science and Technology of China
Citations & Impact
Citations
859
H-index
10
i10-index
10
Publications
15
Co-authors
8
list available
Publications
Resume (English only)
Academic Achievements
- Published 'Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models' at KDD 2023
- Published 'Self-Reminders: Defending ChatGPT against Jailbreak Attack via Self-Reminders' in Nature Machine Intelligence 2023
- Published 'Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark' at ACL 2023, awarded Area Chair Award of NLP Application Track
- Published 'On the Vulnerability of Value Alignment in Open-Access LLMs' in ACL 2024 Findings
- Published 'Non-IID always Bad? Semi-Supervised Heterogeneous Federated Learning with Local Knowledge Enhancement' at CIKM 2023
- Published 'UA-FedRec: Untargeted Attack on Federated News Recommendation' at KDD 2023
- Released 'Control Risk for Potential Misuse of Artificial Intelligence in Science' on arXiv 2023, proposing the SciGuard system to mitigate AI misuse risks in scientific contexts
- Released 'ImageRef-VL: Enabling Contextual Image Referencing in Vision-Language Models' on arXiv 2024
