{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/towards-secure-tuning-mitigating-security","title":"Towards Secure Tuning: Mitigating Security Risks Arising from Benign Instruction Fine-Tuning","arxiv_id":"2410.04524","date":"2024-10-06","proceeding":null,"authors":["Yanrui Du","Sendong Zhao","Jiawei Cao","Ming Ma","Danyang Zhao","Fenglei Fan","Ting Liu","Bing Qin"],"abstract":"Instruction Fine-Tuning (IFT) has become an essential method for adapting base Large Language Models (LLMs) into variants for professional and private use. However, researchers have raised concerns over a significant decrease in LLMs' security following IFT, even when the IFT process involves entirely benign instructions (termed Benign IFT). Our study represents a pioneering effort to mitigate the security risks arising from Benign IFT. Specifically, we conduct a Module Robustness Analysis, aiming to investigate how LLMs' internal modules contribute to their security. Based on our analysis, we propose a novel IFT strategy, called the Modular Layer-wise Learning Rate (ML-LR) strategy. In our analysis, we implement a simple security feature classifier that serves as a proxy to measure the robustness of modules (e.g. $Q$/$K$/$V$, etc.). Our findings reveal that the module robustness shows clear patterns, varying regularly with the module type and the layer depth. Leveraging these insights, we develop a proxy-guided search algorithm to identify a robust subset of modules, termed Mods$_{Robust}$. During IFT, the ML-LR strategy employs differentiated learning rates for Mods$_{Robust}$ and the rest modules. Our experimental results show that in security assessments, the application of our ML-LR strategy significantly mitigates the rise in harmfulness of LLMs following Benign IFT. Notably, our ML-LR strategy has little impact on the usability or expertise of LLMs following Benign IFT. Furthermore, we have conducted comprehensive analyses to verify the soundness and flexibility of our ML-LR strategy.","url_abs":"https://arxiv.org/abs/2410.04524v1","url_pdf":"https://arxiv.org/pdf/2410.04524v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"towards-secure-tuning-mitigating-security","repo_url":"https://github.com/dyr1/mogu","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.04524","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}