DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning

• URL: http://arxiv.org/abs/2606.00160v1
• Date: Fri, 29 May 2026 09:04:27 GMT
• Title: DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning
• Abstract summary: Large language models (LLMs) suffer from degraded safety capabilities even when fine-tuned with benign datasets.<n>Existing methods for identifying safety-degrading samples in benign datasets suffer from high computational costs and significant noise issues.<n>We propose DataShield to efficiently and effectively identify potential safety-degrading samples.
• Score: 21.57697098714205
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) suffer from degraded safety capabilities even when fine-tuned with benign datasets. However, existing methods for identifying safety-degrading samples in benign datasets suffer from high computational costs and significant noise issues. In this paper, we propose DataShield to efficiently and effectively identify potential safety-degrading samples. Our key intuition is based on the observation that benign fine-tuning increases the overall response compliance of LLMs. DataShield's key technical insight is to quantify each sample's contribution to the model's compliance behavior as its safety degradation score. DataShield consists of three core components: (1) Compliance Vector Extraction, which captures the LLM's compliance behavior tendency; (2) a novel Compliance-Aware Score (CAS), which automatically identifies the optimal safety-critical layer; and (3) Safety-degrading Sample Filtering, which quantifies the projection shift of training data along the compliance direction. Extensive experimental evaluation on Llama3-8B, Llama3.1-8B, and Qwen2.5-7B using the Alpaca and Dolly benign datasets validates our method's effectiveness in identifying high-risk and low-risk data subsets. We also observe that open-ended question answering is more likely to trigger safety degradation, and corresponding responses tend to be longer. We hope this work can provide new insights into data-centric defense methods. The source code is available at: https://github.com/ZJunBo/DataShield.

Related papers

• DataRx: Missingness-Aware Sampling for Safer Large Language Model Task-Specific Fine-Tuning [23.890337519636986]
  Task-specific fine-tuning can weaken the safety guardrails of aligned large language models.<n>We propose DataRx, a missingness-aware sampling method for selecting safety-critical examples.
  arXiv  Detail & Related papers  (2026-08-05T01:05:13Z)
• DataShield: Uncovering Risky Fine-Tuning Data Across LLMs Through Consensus Subspace Alignment [39.84367227792296]
  Even fine-tuning on benign task-specific data can substantially weaken the safety capabilities of large language models (LLMs)<n>We propose DataShield, a data assessment framework that identifies risky fine-tuning samples and response segments through consensus subspace alignment.<n>Compared with state-of-the-art filtering and masking baselines, DataShield reduces ASR by 14.6% with sample filtering and 32.3% with segment masking.
  arXiv  Detail & Related papers  (2026-07-16T14:51:42Z)
• GradShield: Alignment Preserving Finetuning [14.841149847814796]
  GradShield is a principled filtering method that safeguards Large Language Models (LLMs) during finetuning.<n>It removes potentially harmful data by computing a Finetuning Implicit Harmfulness Score (FIHS) for each data point.<n>It consistently maintains an Attack Success Rate (ASR) below $6%$ while preserving utility performance.
  arXiv  Detail & Related papers  (2026-05-13T23:19:55Z)
• Token-level Data Selection for Safe LLM Fine-tuning [15.039068315115372]
  Fine-tuning large language models (LLMs) on custom datasets has become a standard approach for adapting these models to specific domains and applications.<n>Recent studies have shown that such fine-tuning can lead to significant degradation in the model's safety.<n>We propose a novel framework that quantifies the safety risk of each token by measuring the loss difference between a safety-degraded model and a utility-oriented model.
  arXiv  Detail & Related papers  (2026-03-01T16:52:05Z)
• 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)
• 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)
• 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)
• Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation [70.62656296780074]
  We propose AIDSAFE: Agentic Iterative Deliberation for Safety Reasoning, a novel data generation recipe.<n>A data refiner stage in AIDSAFE ensures high-quality outputs by eliminating repetitive, redundant, and deceptive thoughts.<n>Our evaluations demonstrate that AIDSAFE-generated CoTs achieve superior policy adherence and reasoning quality.
  arXiv  Detail & Related papers  (2025-05-27T21:34:40Z)
• 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)
• Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning [72.97229770329214]
  We introduce a general approach for seeking high dimensional non-linear optimization problems in which maintaining safety during learning is crucial. Our approach called LBSGD is based on applying a logarithmic barrier approximation with a carefully chosen step size. We demonstrate the effectiveness of our approach on minimizing violation in policy tasks in safe reinforcement learning.
  arXiv  Detail & Related papers  (2022-07-21T11:14:47Z)
• Open-Set Semi-Supervised Learning for 3D Point Cloud Understanding [62.17020485045456]
  It is commonly assumed in semi-supervised learning (SSL) that the unlabeled data are drawn from the same distribution as that of the labeled ones. We propose to selectively utilize unlabeled data through sample weighting, so that only conducive unlabeled data would be prioritized.
  arXiv  Detail & Related papers  (2022-05-02T16:09:17Z)

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.