Antibody: Strengthening Defense Against Harmful Fine-Tuning for Large Language Models via Attenuating Harmful Gradient Influence

• URL: http://arxiv.org/abs/2603.00498v1
• Date: Sat, 28 Feb 2026 06:46:21 GMT
• Title: Antibody: Strengthening Defense Against Harmful Fine-Tuning for Large Language Models via Attenuating Harmful Gradient Influence
• Authors: Quoc Minh Nguyen, Trung Le, Jing Wu, Anh Tuan Bui, Mehrtash Harandi,
• Abstract summary: Fine-tuning-as-a-service introduces a threat to Large Language Models' safety when service providers fine-tune their models on user-submitted datasets.<n>We show that by regularizing the contribution of harmful samples encountered during fine-tuning, we can effectively mitigate the impact of harmful fine-tuning attacks.
• Score: 33.73351876121039
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Fine-tuning-as-a-service introduces a threat to Large Language Models' safety when service providers fine-tune their models on poisoned user-submitted datasets, a process known as harmful fine-tuning attacks. In this work, we show that by regularizing the gradient contribution of harmful samples encountered during fine-tuning, we can effectively mitigate the impact of harmful fine-tuning attacks. To this end, we introduce Antibody, a defense strategy that first ensures robust safety alignment for the model before fine-tuning, and then applies a safety-preservation learning algorithm during fine-tuning. Specifically, in the alignment stage before fine-tuning, we propose optimizing the model to be in a flat loss region with respect to harmful samples, which makes the safety alignment more resilient to subsequent harmful fine-tuning. Then, in the fine-tuning stage, we design a fine-tuning algorithm that applies a weighting scheme to all samples in each training batch to inhibit the model from learning from harmful samples while encouraging learning from benign samples. Experimental results demonstrate that Antibody successfully mitigates harmful fine-tuning attacks while boosting fine-tuning performance on the user-submitted dataset.

Related papers

• Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler [67.24175911858312]
  Harmful fine-tuning poses critical safety risks to fine-tuning-as-a-service for large language models.<n>Bayesian Data Scheduler (BDS) is an adaptive tuning-stage defense strategy with no need for attack simulation.<n>BDS learns the posterior distribution of each data point's safety attribute, conditioned on the fine-tuning and alignment datasets.
  arXiv  Detail & Related papers  (2025-10-31T04:49:37Z)
• Preventing Catastrophic Forgetting: Behavior-Aware Sampling for Safer Language Model Fine-Tuning [8.962376414368846]
  Large language models often lose previously aligned safety behaviors when fine-tuned on benign data.<n>We propose a behavior-aware sampling framework that selects safety examples based on two complementary factors.
  arXiv  Detail & Related papers  (2025-10-23T20:34:52Z)
• Rethinking Safety in LLM Fine-tuning: An Optimization Perspective [56.31306558218838]
  We show that poor optimization choices, rather than inherent trade-offs, often cause safety problems, measured as harmful responses to adversarial prompts.<n>We propose a simple exponential moving average (EMA) momentum technique in parameter space that preserves safety performance.<n>Our experiments on the Llama families across multiple datasets demonstrate that safety problems can largely be avoided without specialized interventions.
  arXiv  Detail & Related papers  (2025-08-17T23:46:36Z)
• Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning [24.176983833455413]
  Text-to-image (T2I) diffusion models have achieved impressive image generation quality and are increasingly fine-tuned for personalized applications.<n>These models often inherit unsafe behaviors from toxic pretraining data, raising growing safety concerns.<n>We propose ResAlign, a safety-driven unlearning framework with enhanced resilience against downstream fine-tuning.
  arXiv  Detail & Related papers  (2025-07-22T07:40:16Z)
• LookAhead Tuning: Safer Language Models via Partial Answer Previews [62.529794567687354]
  Fine-tuning enables large language models to adapt to specific domains, but often compromises their previously established safety alignment.<n>We introduce LookAhead Tuning, a lightweight and effective data-driven approach that preserves safety during fine-tuning.
  arXiv  Detail & Related papers  (2025-03-24T18:11:42Z)
• Fundamental Limitations in Pointwise Defences of LLM Finetuning APIs [56.84338097581665]
  We show that defences of fine-tuning APIs are fundamentally limited in their ability to prevent fine-tuning attacks.<n>We construct 'pointwise-undetectable' attacks that repurpose entropy in benign model outputs to covertly transmit dangerous knowledge.<n>We test our attacks against the OpenAI fine-tuning API, finding they succeed in eliciting answers to harmful multiple-choice questions.
  arXiv  Detail & Related papers  (2025-02-20T18:45:01Z)
• Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation [58.7395356511539]
  Harmful fine-tuning attack introduces significant security risks to the fine-tuning services.<n> Mainstream defenses aim to vaccinate the model such that the later harmful fine-tuning attack is less effective.<n>We propose Panacea, which optimize an adaptive perturbation that will be applied to the model after fine-tuning.
  arXiv  Detail & Related papers  (2025-01-30T02:47:09Z)
• Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation [7.945893812374361]
  Harmful fine-tuning attack poses serious safety concerns for large language models' fine-tuning-as-a-service.<n>In this paper, we show that harmful perturbation over the model weights could be a probable cause of alignment-broken.<n>In order to attenuate the negative impact of harmful perturbation, we propose an alignment-stage solution, dubbed Booster.
  arXiv  Detail & Related papers  (2024-09-03T03:59:22Z)
• Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning [13.201253775115681]
  Large Language Models (LLMs) are vulnerable to harmful fine-tuning attacks.<n>We propose Antidote, a post-fine-tuning stage solution.<n>Antidote relies on the philosophy that by removing the harmful parameters, the harmful model can be recovered from the harmful behaviors.
  arXiv  Detail & Related papers  (2024-08-18T21:45:03Z)
• 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)
• Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment [56.2017039028998]
  Fine-tuning of Language-Model-as-a-Service (LM) introduces new threats, particularly against the Fine-tuning based Jailbreak Attack (FJAttack) We propose the Backdoor Enhanced Safety Alignment method inspired by an analogy with the concept of backdoor attacks. Our comprehensive experiments demonstrate that through the Backdoor Enhanced Safety Alignment with adding as few as 11 safety examples, the maliciously finetuned LLMs will achieve similar safety performance as the original aligned models without harming the benign performance.
  arXiv  Detail & Related papers  (2024-02-22T21:05:18Z)

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.