Papers by Danyang Zhao
Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning (2026.acl-long)
Copied to clipboard
Yanrui Du, Fenglei Fan, Sendong Zhao, Jiawei Cao, Ming Ma, Danyang Zhao, Shuren Qi, Ting Liu, Bing Qin
| Challenge: | Instruction Fine-Tuning (IFT) has emerged as a critical technique for customizing Large Language Models (LLMs) however, recent studies have revealed that IFT can compromise the built-in security mechanisms of LLMs, posing significant security risks. |
| Approach: | They propose a method that shifts learning burden onto security-robust parameters and propose 'warm-up' phase that preferentially trains Mods_Rob to learn low-level features with minimal security risk. |
| Outcome: | The proposed method reduces security risks without sacrificing performance gains across knowledge-intensive datasets. |
WebSRC: A Dataset for Web-Based Structural Reading Comprehension (2021.emnlp-main)
Copied to clipboard
| Challenge: | Using a web page and a question, a machine can't understand the contents of web pages. |
| Approach: | They propose a novel dataset for web-based structural reading comprehension that consists of 400K question-answer pairs and a dataset of 6.4K web pages. |
| Outcome: | The proposed dataset consists of 400K question-answer pairs, collected from 6.4K web pages with corresponding HTML source code, screenshots, and metadata. |