paper-with-me

홈 › Papers

Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack

2024-02-02 · Tiansheng Huang, Sihao Hu, Ling Liu

The new paradigm of finetuning-as-a-service introduces a new attack surface for Large Language Models (LLMs): a few harmful data uploaded by users can easily trick the finetuning to produce an alignment-broken model. We conduct an empirical analysis and uncover a \textit{harmful embedding drift} phenomenon, showing a probable cause of the alignment-broken effect. Inspired by our findings, we propose Vaccine, a perturbation-aware alignment technique to mitigate the security risk of users finetuning. The core idea of Vaccine is to produce invariant hidden embeddings by progressively adding crafted perturbation to them in the alignment phase. This enables the embeddings to withstand harmful perturbation from un-sanitized user data in the finetuning phase. Our results on open source mainstream LLMs (e.g., Llama2, Opt, Vicuna) demonstrate that Vaccine can boost the robustness of alignment against harmful prompts induced embedding drift while reserving reasoning ability towards benign prompts. Our code is available at \url{https://github.com/git-disl/Vaccine}.

📄 PDF Abstract BibTeX arXiv:2402.01109

Code (1)

git-disl/vaccine 공식 구현 pytorch

Tasks

Language ModellingLarge Language Model

Similar Papers 제목 키워드 기반

Targeted Vaccine: Safety Alignment for Large Language Models against Harmful Fine-Tuning via Layer-wise Perturbation

2024-10-13 · Guozhi Liu, Weiwei Lin, Tiansheng Huang, Ruichao Mo 외

Harmful fine-tuning attack poses a serious threat to the online fine-tuning service. Vaccine, a recent alignment-stage defense, applies uniform perturbation to all layers of embedding to make the model robust to the simu…

Safety AlignmentTAR

Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation

2024-09-03 · Tiansheng Huang, Sihao Hu, Fatih Ilhan, Selim Furkan Tekin 외

Harmful fine-tuning issue \citep{qi2023fine} poses serious safety concerns for Large language models' fine-tuning-as-a-service. While existing defenses \citep{huang2024vaccine,rosati2024representation} have been proposed…

Utilising Large Language Models for Generating Effective Counter Arguments to Anti-Vaccine Tweets

2025-10-18 · Utsav Dhanuka, Soham Poddar, Saptarshi Ghosh arxiv

In an era where public health is increasingly influenced by information shared on social media, combatting vaccine skepticism and misinformation has become a critical societal goal. Misleading narratives around vaccinati…

Pharmacist: Safety Alignment Data Curation for Large Language Models against Harmful Fine-tuning

2025-10-11 · Guozhi Liu, Qi Mu, Tiansheng Huang, Xinhua Wang 외 arxiv

Harmful fine-tuning issues present significant safety challenges for fine-tuning-as-a-service in large language models. Existing alignment-stage defenses, e.g., Vaccine, Repnoise, Booster, and T-Vaccine, mitigate harmful…

Computational Efficiency

Classifying vaccine sentiment tweets by modelling domain-specific representation and commonsense knowledge into context-aware attentive GRU

2021-06-17 · Usman Naseem, Matloob Khushi, Jinman Kim, Adam G. Dunn

Vaccines are an important public health measure, but vaccine hesitancy and refusal can create clusters of low vaccine coverage and reduce the effectiveness of vaccination programs. Social media provides an opportunity to…