S3LoRA: Safe Spectral Sharpness-Guided Pruning in Adaptation of Agent Planner

• URL: http://arxiv.org/abs/2508.15068v1
• Date: Wed, 20 Aug 2025 21:08:29 GMT
• Title: S3LoRA: Safe Spectral Sharpness-Guided Pruning in Adaptation of Agent Planner
• Authors: Shuang Ao, Gopal Rumchurn,
• Abstract summary: Adapting Large Language Models (LLMs) using parameter-efficient fine-tuning techniques such as LoRA has enabled powerful capabilities in LLM-based agents.<n>Existing safety-aware adaptation methods often require access to both base and instruction-tuned model checkpoints.<n>We propose S3LoRA, a lightweight, data-free, and model-independent framework that mitigates safety risks in LoRA-adapted models by inspecting only the fine-tuned weight updates.
• Score: 1.6114012813668932
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Adapting Large Language Models (LLMs) using parameter-efficient fine-tuning (PEFT) techniques such as LoRA has enabled powerful capabilities in LLM-based agents. However, these adaptations can unintentionally compromise safety alignment, leading to unsafe or unstable behaviors, particularly in agent planning tasks. Existing safety-aware adaptation methods often require access to both base and instruction-tuned model checkpoints, which are frequently unavailable in practice, limiting their applicability. We propose S3LoRA (Safe Spectral Sharpness-Guided Pruning LoRA), a lightweight, data-free, and model-independent framework that mitigates safety risks in LoRA-adapted models by inspecting only the fine-tuned weight updates. We first introduce Magnitude-Aware Spherically Normalized SVD (MAS-SVD), which robustly analyzes the structural properties of LoRA updates while preserving global magnitude information. We then design the Spectral Sharpness Index (SSI), a sharpness-aware metric to detect layers with highly concentrated and potentially unsafe updates. These layers are pruned post-hoc to reduce risk without sacrificing task performance. Extensive experiments and ablation studies across agent planning and language generation tasks show that S3LoRA consistently improves safety metrics while maintaining or improving utility metrics and significantly reducing inference cost. These results establish S3LoRA as a practical and scalable solution for safely deploying LLM-based agents in real-world, resource-constrained, and safety-critical environments.

Related papers

• UpSafe$^\circ$C: Upcycling for Controllable Safety in Large Language Models [67.91151588917396]
  Large Language Models (LLMs) have achieved remarkable progress across a wide range of tasks, but remain vulnerable to safety risks such as harmful content generation and jailbreak attacks.<n>We propose UpSafe$circ$C, a unified framework for enhancing LLM safety through safety-aware upcycling.<n>Our results highlight a new direction for LLM safety: moving from static alignment toward dynamic, modular, and inference-aware control.
  arXiv  Detail & Related papers  (2025-10-02T16:43:33Z)
• zkLoRA: Fine-Tuning Large Language Models with Verifiable Security via Zero-Knowledge Proofs [44.0362091911335]
  We introduce zkLoRA, the first framework to integrate LoRA fine-tuning with zero-knowledge proofs (ZKPs)<n> zkLoRA employs advanced cryptographic techniques to verify both arithmetic and non-arithmetic operations in Transformer-based architectures.<n> zkLoRA demonstrates practicality and efficiency through experimental validation on open-source LLMs like LLaMA, scaling up to 13 billion parameters.
  arXiv  Detail & Related papers  (2025-08-29T08:14:38Z)
• 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)
• LoRA is All You Need for Safety Alignment of Reasoning LLMs [30.616817385956754]
  We show that using LoRA for SFT on refusal datasets effectively aligns the model for safety without harming its reasoning capabilities.<n>This is because restricting the safety weight updates to a low-rank space minimizes the interference with the reasoning weights.<n>Our experiments show that this approach produces highly safe LLMs--with safety levels comparable to full-model fine-tuning--without compromising their reasoning abilities.
  arXiv  Detail & Related papers  (2025-07-22T23:25:16Z)
• Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs [4.580092836731863]
  Fine-tuning Large Language Models (LLMs) with Low-Rank Adaptation (LoRA) enhances adaptability while reducing computational costs.<n>Existing safety alignment methods struggle to capture complex parameter shifts, leading to suboptimal safety-utility trade-offs.<n>We propose Safe Pruning LoRA (SPLoRA), a novel pruning-based approach that selectively removes LoRA layers that weaken safety alignment.
  arXiv  Detail & Related papers  (2025-06-21T14:59:54Z)
• 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)
• Reshaping Representation Space to Balance the Safety and Over-rejection in Large Audio Language Models [50.89022445197919]
  Large Audio Language Models (LALMs) have extended the capabilities of Large Language Models (LLMs)<n>Recent research has revealed that LALMs remain vulnerable to harmful queries due to insufficient safety-alignment.
  arXiv  Detail & Related papers  (2025-05-26T08:25:25Z)
• 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)
• SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation [41.91948079316541]
  Recent studies have raised concerns that LoRA fine-tuning could potentially compromise the safety alignment in large language models.<n>In this paper, we propose Safety-alignment preserved Low-Rank Adaptation (SaLoRA)<n>Unlike previous LoRA methods and their variants, SaLoRA enables targeted modifications to LLMs without disrupting their original alignments.<n>Our experiments show that SaLoRA outperforms various adapters-based approaches across various evaluation metrics in different fine-tuning tasks.
  arXiv  Detail & Related papers  (2025-01-03T11:34:28Z)
• Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models [51.20476412037321]
  We propose Safe LoRA, a simple one-liner patch to the original LoRA implementation by introducing the projection of LoRA weights from selected layers to the safety-aligned subspace.<n>Our experiments demonstrate that when fine-tuning on purely malicious data, Safe LoRA retains similar safety performance as the original aligned model.
  arXiv  Detail & Related papers  (2024-05-27T05:04:05Z)
• 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.