What Makes and Breaks Safety Fine-tuning? A Mechanistic Study

• URL: http://arxiv.org/abs/2407.10264v3
• Date: Wed, 21 Aug 2024 15:12:37 GMT
• Title: What Makes and Breaks Safety Fine-tuning? A Mechanistic Study
• Authors: Samyak Jain, Ekdeep Singh Lubana, Kemal Oksuz, Tom Joy, Philip H. S. Torr, Amartya Sanyal, Puneet K. Dokania,
• Abstract summary: Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. We design a synthetic data generation framework that captures salient aspects of an unsafe input. Using this, we investigate three well-known safety fine-tuning methods.
• Score: 64.9691741899956
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via safety fine-tuning, we design a synthetic data generation framework that captures salient aspects of an unsafe input by modeling the interaction between the task the model is asked to perform (e.g., "design") versus the specific concepts the task is asked to be performed upon (e.g., a "cycle" vs. a "bomb"). Using this, we investigate three well-known safety fine-tuning methods -- supervised safety fine-tuning, direct preference optimization, and unlearning -- and provide significant evidence demonstrating that these methods minimally transform MLP weights to specifically align unsafe inputs into its weights' null space. This yields a clustering of inputs based on whether the model deems them safe or not. Correspondingly, when an adversarial input (e.g., a jailbreak) is provided, its activations are closer to safer samples, leading to the model processing such an input as if it were safe. We validate our findings, wherever possible, on real-world models -- specifically, Llama-2 7B and Llama-3 8B.

Related papers

• SafeRoute: Adaptive Model Selection for Efficient and Accurate Safety Guardrails in Large Language Models [63.63254955809224]
  We propose a binary router that distinguishes hard examples from easy ones. Our method selectively applies the larger safety guard model to the data that the router considers hard, improving efficiency while maintaining accuracy. Experimental results on multiple benchmark datasets demonstrate that our adaptive model selection significantly enhances the trade-off between computational cost and safety performance.
  arXiv  Detail & Related papers  (2025-02-18T02:51:17Z)
• Vulnerability Mitigation for Safety-Aligned Language Models via Debiasing [12.986006070964772]
  Safety alignment is an essential research topic for real-world AI applications. Our study first identified the difficulty of eliminating such vulnerabilities without sacrificing the model's helpfulness. Our method could enhance the model's helpfulness while maintaining safety, thus improving the trade-off-front.
  arXiv  Detail & Related papers  (2025-02-04T09:31:54Z)
• Overriding Safety protections of Open-source Models [4.093963624562595]
  In this paper, we study how much of impact introduction of harmful data in fine-tuning can make. We explore if fine-tuning the model on harmful data makes it less helpful or less trustworthy. For the safe fine-tuned model, ASR decreases by 51.68% as compared to the basemodel.
  arXiv  Detail & Related papers  (2024-09-28T22:53:27Z)
• Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training [67.30423823744506]
  This study addresses a critical gap in safety tuning practices for Large Language Models (LLMs) We introduce a novel approach, Decoupled Refusal Training (DeRTa), designed to empower LLMs to refuse compliance to harmful prompts at any response position. DeRTa incorporates two novel components: (1) Maximum Likelihood Estimation with Harmful Response Prefix, which trains models to recognize and avoid unsafe content by appending a segment of harmful response to the beginning of a safe response, and (2) Reinforced Transition Optimization (RTO), which equips models with the ability to transition from potential harm to safety refusal consistently throughout the harmful
  arXiv  Detail & Related papers  (2024-07-12T09:36:33Z)
• Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation [86.05704141217036]
  Black-box finetuning is an emerging interface for adapting state-of-the-art language models to user needs. We introduce covert malicious finetuning, a method to compromise model safety via finetuning while evading detection.
  arXiv  Detail & Related papers  (2024-06-28T17:05:46Z)
• Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models [65.06446825020578]
  Safety alignment is crucial to ensure that large language models (LLMs) behave in ways that align with human preferences and prevent harmful actions during inference. We aim to measure the risks in finetuning LLMs through navigating the LLM safety landscape.
  arXiv  Detail & Related papers  (2024-05-27T17:31:56Z)
• A safety realignment framework via subspace-oriented model fusion for large language models [22.588716190505963]
  We introduce a safety realignment framework through subspace-oriented model fusion (SOMF) Our approach begins by disentangling all task vectors from the weights of each fine-tuned model. We then identify safety-related regions within these vectors by subspace masking techniques.
  arXiv  Detail & Related papers  (2024-05-15T03:04:05Z)
• Emulated Disalignment: Safety Alignment for Large Language Models May Backfire! [65.06450319194454]
  Large language models (LLMs) undergo safety alignment to ensure safe conversations with humans. This paper introduces a training-free attack method capable of reversing safety alignment. We name this method emulated disalignment (ED) because sampling from this contrastive distribution provably emulates the result of fine-tuning to minimize a safety reward.
  arXiv  Detail & Related papers  (2024-02-19T18:16:51Z)
• Safe MDP Planning by Learning Temporal Patterns of Undesirable Trajectories and Averting Negative Side Effects [27.41101006357176]
  In safe MDP planning, a cost function based on the current state and action is often used to specify safety aspects. operating based on an incomplete model can often produce unintended negative side effects (NSEs)
  arXiv  Detail & Related papers  (2023-04-06T14:03:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.