paper-with-me

홈 › Papers

Badllama 3: removing safety finetuning from Llama 3 in minutes

2024-07-01 · Dmitrii Volkov

We show that extensive LLM safety fine-tuning is easily subverted when an attacker has access to model weights. We evaluate three state-of-the-art fine-tuning methods-QLoRA, ReFT, and Ortho-and show how algorithmic advances enable constant jailbreaking performance with cuts in FLOPs and optimisation power. We strip safety fine-tuning from Llama 3 8B in one minute and Llama 3 70B in 30 minutes on a single GPU, and sketch ways to reduce this further.

📄 PDF Abstract BibTeX arXiv:2407.01376

Code (0)

등록된 구현이 없습니다.

Tasks

GPU

Methods 이 논문이 사용한 방법론

LLaMA LLaMA is a collection of foundation language models ranging from 7B to 65B parameters. It is based on the transformer architecture with various improvements that were…

Similar Papers 제목 키워드 기반

BadLlama: cheaply removing safety fine-tuning from Llama 2-Chat 13B

2023-10-31 · Pranav Gade, Simon Lermen, Charlie Rogers-Smith, Jeffrey Ladish

Llama 2-Chat is a collection of large language models that Meta developed and released to the public. While Meta fine-tuned Llama 2-Chat to refuse to output harmful content, we hypothesize that public access to model wei…

InSaAF: Incorporating Safety through Accuracy and Fairness | Are LLMs ready for the Indian Legal Domain?

2024-02-16 · Yogesh Tripathi, Raghav Donakanti, Sahil Girhepuje, Ishan Kavathekar 외

Recent advancements in language technology and Artificial Intelligence have resulted in numerous Language Models being proposed to perform various tasks in the legal domain ranging from predicting judgments to generating…

Fairness

GradShield: Alignment Preserving Finetuning

2026-05-13 · Zhanhao Hu, Xiao Huang, Patrick Mendoza, Emad A. Alghamdi 외 arxiv

Large Language Models (LLMs) pose a significant risk of safety misalignment after finetuning, as models can be compromised by both explicitly and implicitly harmful data. Even some seemingly benign data can inadvertently…

Label Supervised LLaMA Finetuning

2023-10-02 · Zongxi Li, Xianming Li, Yuzhang Liu, Haoran Xie 외

The recent success of Large Language Models (LLMs) has gained significant attention in both academia and industry. Substantial efforts have been made to enhance the zero- and few-shot generalization capabilities of open-…

GPUnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+7

Invisible Safety Threat: Malicious Finetuning for LLM via Steganography

2026-03-09 · Guangnian Wan, Xinyin Ma, Gongfan Fang, Xinchao Wang arxiv

Understanding and addressing potential safety alignment risks in large language models (LLMs) is critical for ensuring their safe and trustworthy deployment. In this paper, we highlight an insidious safety threat: a comp…