Jingwei Yi
8 Papers
2 Citations
Jingwei Yi is an academic researcher. The author has contributed to research in topics: Computer science. The author has an hindex of 1, co-authored 4 publications.
Chat about Author
Papers
Defending ChatGPT against jailbreak attack via self-reminders
Yueqi Xie,Jingwei Yi,Jiawei Shao,Justin Curl,Lingjuan Lyu,Qifeng Chen,Xing Xie,Fangzhao Wu +7 more
TL;DR: This work systematically documents the threats posed by jailbreak attacks, introduces and analyses a dataset for evaluating defensive interventions and proposes the psychologically inspired self-reminder technique that can efficiently and effectively mitigate against jailbreaks without further training.
100
Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark
Wenjun Peng,Jingwei Yi,Fangzhao Wu,Shangxi Wu,Bin Zhu,Lingjuan Lyu,Binxing Jiao,Tongye Xu,Guangzhong Sun,Xing Xie +9 more
- 17 May 2023
TL;DR: Yin et al. as mentioned in this paper proposed an Embedding Watermark method called {pasted macro ‘METHOD’} that implants backdoors on embeddings by selecting a group of moderate-frequency words from a general text corpus to form a trigger set.
Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models
Jingwei Yi,Yueqi Xie,Bin Zhu,Keegan Hines,Emre Kiciman,Guangzhong Sun,Xing Xie,Fangzhao Wu +7 more
TL;DR: This work introduces the first benchmark, BIPIA, to measure the robustness of various LLMs and defenses against indirect prompt injection attacks, and proposes four black-box methods based on prompt learning and a white-box defense methods based on fine-tuning with adversarial training to enable LLMs to distinguish between instructions and external content and ignore instructions in the external content.
Non-IID always Bad? Semi-Supervised Heterogeneous Federated Learning with Local Knowledge Enhancement
Chao Zhang,Fangzhao Wu,Jingwei Yi,Derong Xu,Yang Yu,Jindong Wang,Yidong Wang,Tongjing Xu,Xing Xie,Enhong Chen +9 more
- 21 Oct 2023
TL;DR: This paper proposes a semi-supervised heterogeneous federated learning method with local knowledge enhancement, called FedLoKe, which aims to train an accurate global model from both labeled and unlabeled local data with non-IID distributions.
7
Effective and Efficient Query-aware Snippet Extraction for Web Search
Jingwei Yi,Fangzhao Wu,Chuhan Wu,Xiaolong Huang,Binxing Jiao,Guangzhong Sun,Xing Xie +6 more
- 17 Oct 2022
TL;DR: An efficient version of DeepQSE is proposed, named Ef-DeepQSE, which can improve the inference speed of Deep QSE without affecting its performance, and decompose the query-aware snippet extraction task into two stages, i.e., a coarse-grained candidate sentence selection stage where sentence representations can be cached, and a fine- grained relevance modeling stage.
2