Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency

• URL: http://arxiv.org/abs/2506.17209v1
• Date: Fri, 20 Jun 2025 17:57:12 GMT
• Title: Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency
• Authors: Kathleen C. Fraser, Hillary Dawkins, Isar Nejadgholi, Svetlana Kiritchenko,
• Abstract summary: Fine-tuning a general-purpose large language model (LLM) for a specific domain or task has become a routine procedure for ordinary users.<n>We consider this to be a critical failure mode of LLMs due to the widespread uptake of fine-tuning, combined with the benign nature of the "attack"<n>Our experiments expose surprising variance in the results of the safety evaluation, even when seemingly inconsequential changes are made to the fine-tuning setup.
• Score: 17.57889200051214
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Fine-tuning a general-purpose large language model (LLM) for a specific domain or task has become a routine procedure for ordinary users. However, fine-tuning is known to remove the safety alignment features of the model, even when the fine-tuning data does not contain any harmful content. We consider this to be a critical failure mode of LLMs due to the widespread uptake of fine-tuning, combined with the benign nature of the "attack". Most well-intentioned developers are likely unaware that they are deploying an LLM with reduced safety. On the other hand, this known vulnerability can be easily exploited by malicious actors intending to bypass safety guardrails. To make any meaningful progress in mitigating this issue, we first need reliable and reproducible safety evaluations. In this work, we investigate how robust a safety benchmark is to trivial variations in the experimental procedure, and the stochastic nature of LLMs. Our initial experiments expose surprising variance in the results of the safety evaluation, even when seemingly inconsequential changes are made to the fine-tuning setup. Our observations have serious implications for how researchers in this field should report results to enable meaningful comparisons in the future.

Related papers

• Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment [24.364891513019444]
  In this paper, we show that fine-tuning datasets often contain samples with safety-degrading features that are not easily identifiable on the surface.<n>We propose LARF, a Layer-Aware Representation Filtering method.<n> Experimental results demonstrate that LARF can effectively identify benign data with safety-degrading features.
  arXiv  Detail & Related papers  (2025-07-24T17:59:24Z)
• LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning [61.594212398272184]
  Low-Rank Extrapolation (LoX) improves robustness against benign and malicious fine-tuning attacks.<n>LoX leads to 11% to 54% absolute reductions in attack success rates.
  arXiv  Detail & Related papers  (2025-06-18T16:30:02Z)
• Shape it Up! Restoring LLM Safety during Finetuning [66.46166656543761]
  Finetuning large language models (LLMs) enables user-specific customization but introduces critical safety risks.<n>We propose dynamic safety shaping (DSS), a framework that uses fine-grained safety signals to reinforce learning from safe segments of a response while suppressing unsafe content.<n>We present STAR-DSS, guided by STAR scores, that robustly mitigates finetuning risks and delivers substantial safety improvements across diverse threats, datasets, and model families.
  arXiv  Detail & Related papers  (2025-05-22T18:05:16Z)
• Mitigating Fine-tuning Risks in LLMs via Safety-Aware Probing Optimization [7.1060720569792215]
  Fine-tuning large language models (LLMs) can inadvertently compromise their safety.<n>We introduce a safety-aware probing (SAP) framework designed to mitigate the safety risks.<n>Our experimental results demonstrate that SAP effectively reduces harmfulness below the original fine-tuned model.
  arXiv  Detail & Related papers  (2025-05-22T14:52:10Z)
• How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study [90.34190170330481]
  Large Reasoning Models (LRMs) have achieved remarkable success on reasoning-intensive tasks such as mathematics and programming.<n>However, their enhanced reasoning capabilities do not necessarily translate to improved safety performance.<n>We present a comprehensive empirical study on how to enhance the safety of LRMs through Supervised Fine-Tuning.
  arXiv  Detail & Related papers  (2025-05-21T11:45:29Z)
• Safe Vision-Language Models via Unsafe Weights Manipulation [75.04426753720551]
  We revise safety evaluation by introducing Safe-Ground, a new set of metrics that evaluate safety at different levels of granularity.<n>We take a different direction and explore whether it is possible to make a model safer without training, introducing Unsafe Weights Manipulation (UWM)<n>UWM uses a calibration set of safe and unsafe instances to compare activations between safe and unsafe content, identifying the most important parameters for processing the latter.
  arXiv  Detail & Related papers  (2025-03-14T17:00:22Z)
• STAIR: Improving Safety Alignment with Introspective Reasoning [44.780098674618614]
  We propose STAIR, a framework that integrates SafeTy Alignment with Itrospective Reasoning.<n>We show that STAIR effectively mitigates harmful outputs while better preserving helpfulness, compared to instinctive alignment strategies.<n>With test-time scaling, STAIR achieves a safety performance comparable to Claude-3.5 against popular jailbreak attacks.
  arXiv  Detail & Related papers  (2025-02-04T15:02:55Z)
• Picky LLMs and Unreliable RMs: An Empirical Study on Safety Alignment after Instruction Tuning [39.48925539103229]
  Fine-tuning large language models (LLMs) can inadvertently degrade their safety alignment.<n>This phenomenon makes models more susceptible to providing inappropriate responses.<n>Our work highlights the complexities of maintaining safety alignment during fine-tuning.
  arXiv  Detail & Related papers  (2025-02-03T07:09:09Z)
• SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signals [50.463399903987245]
  Large language models (LLMs) exhibit exceptional capabilities across various tasks but also pose risks by generating harmful content.<n>We show that LLMs can similarly perform internal assessments about safety in their internal states.<n>We propose SafeSwitch, a framework that regulates unsafe outputs by utilizing the prober-based internal state monitor.
  arXiv  Detail & Related papers  (2025-02-03T04:23:33Z)
• Safety Layers in Aligned Large Language Models: The Key to LLM Security [43.805905164456846]
  Internal parameters in aligned LLMs can be vulnerable to security degradation when subjected to fine-tuning attacks.<n>Our work uncovers the mechanism behind security in aligned LLMs at the parameter level, identifying a small set of contiguous layers in the middle of the model.<n>We propose a novel fine-tuning approach, Safely Partial- Fine-Tuning (SPPFT), that fixes the gradient of the safety layers during fine-tuning to address the security degradation.
  arXiv  Detail & Related papers  (2024-08-30T04:35:59Z)
• What Makes and Breaks Safety Fine-tuning? A Mechanistic Study [64.9691741899956]
  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.
  arXiv  Detail & Related papers  (2024-07-14T16:12:57Z)
• Fake Alignment: Are LLMs Really Aligned Well? [91.26543768665778]
  This study investigates the substantial discrepancy in performance between multiple-choice questions and open-ended questions. Inspired by research on jailbreak attack patterns, we argue this is caused by mismatched generalization.
  arXiv  Detail & Related papers  (2023-11-10T08:01:23Z)
• Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To! [88.90694413503614]
  We find that the safety alignment of LLMs can be compromised by fine-tuning. We jailbreak GPT-3.5 Turbo's safety guardrails by fine-tuning it on only 10 such examples. We advocate for further research efforts toward reinforcing safety protocols for the custom fine-tuning of aligned LLMs.
  arXiv  Detail & Related papers  (2023-10-05T17:12:17Z)

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.