SafeRoute: Adaptive Model Selection for Efficient and Accurate Safety Guardrails in Large Language Models

• URL: http://arxiv.org/abs/2502.12464v1
• Date: Tue, 18 Feb 2025 02:51:17 GMT
• Title: SafeRoute: Adaptive Model Selection for Efficient and Accurate Safety Guardrails in Large Language Models
• Authors: Seanie Lee, Dong Bok Lee, Dominik Wagner, Minki Kang, Haebin Seong, Tobias Bocklet, Juho Lee, Sung Ju Hwang,
• Abstract summary: 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.
• Score: 63.63254955809224
• License:
• Abstract: Deploying large language models (LLMs) in real-world applications requires robust safety guard models to detect and block harmful user prompts. While large safety guard models achieve strong performance, their computational cost is substantial. To mitigate this, smaller distilled models are used, but they often underperform on "hard" examples where the larger model provides accurate predictions. We observe that many inputs can be reliably handled by the smaller model, while only a small fraction require the larger model's capacity. Motivated by this, we propose SafeRoute, 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 compared to solely using the larger safety guard model. Experimental results on multiple benchmark datasets demonstrate that our adaptive model selection significantly enhances the trade-off between computational cost and safety performance, outperforming relevant baselines.

Related papers

• DELMAN: Dynamic Defense Against Large Language Model Jailbreaking with Model Editing [62.43110639295449]
  Large Language Models (LLMs) are widely applied in decision making, but their deployment is threatened by jailbreak attacks. Delman is a novel approach leveraging direct model editing for precise, dynamic protection against jailbreak attacks. Delman directly updates a minimal set of relevant parameters to neutralize harmful behaviors while preserving the model's utility.
  arXiv  Detail & Related papers  (2025-02-17T10:39:21Z)
• Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models [25.606641582511106]
  We propose a novel dataset that integrates multi-image inputs with safety Chain-of-Thought (CoT) labels as fine-grained reasoning logic to improve model performance. Our experiments demonstrate that fine-tuning InternVL2.5-8B with MIS significantly outperforms both powerful open-source models and API-based models in challenging multi-image tasks.
  arXiv  Detail & Related papers  (2025-01-30T17:59:45Z)
• Enhancing AI Safety Through the Fusion of Low Rank Adapters [7.384556630042846]
  Low-Rank Adapter Fusion mitigates harmful responses when faced with malicious prompts. We show a 42% reduction in the harmfulness rate by leveraging LoRA fusion between a task adapter and a safety adapter. We also observe exaggerated safety behaviour, where the model rejects safe prompts that closely resemble unsafe ones.
  arXiv  Detail & Related papers  (2024-12-30T13:12:27Z)
• 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)
• 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)
• Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models [112.48136829374741]
  In this paper, we unveil a new vulnerability: the privacy backdoor attack. When a victim fine-tunes a backdoored model, their training data will be leaked at a significantly higher rate than if they had fine-tuned a typical model. Our findings highlight a critical privacy concern within the machine learning community and call for a reevaluation of safety protocols in the use of open-source pre-trained models.
  arXiv  Detail & Related papers  (2024-04-01T16:50:54Z)
• Predicting on the Edge: Identifying Where a Larger Model Does Better [61.793778186198864]
  We show that large models have the largest improvement on examples where the small model is most uncertain. We show that a switcher model which defers examples to a larger model when a small model is uncertain can achieve striking improvements in performance and resource usage.
  arXiv  Detail & Related papers  (2022-02-15T18:53:14Z)
• When in Doubt, Summon the Titans: Efficient Inference with Large Models [80.2673230098021]
  We propose a two-stage framework based on distillation that realizes the modelling benefits of large models. We use the large teacher models to guide the lightweight student models to only make correct predictions on a subset of "easy" examples. Our proposed use of distillation to only handle easy instances allows for a more aggressive trade-off in the student size, thereby reducing the amortized cost of inference.
  arXiv  Detail & Related papers  (2021-10-19T22:56:49Z)
• Revisiting Ensembles in an Adversarial Context: Improving Natural Accuracy [5.482532589225552]
  There is still a significant gap in natural accuracy between robust and non-robust models. We consider a number of ensemble methods designed to mitigate this performance difference. We consider two schemes, one that combines predictions from several randomly robust models, and the other that fuses features from robust and standard models.
  arXiv  Detail & Related papers  (2020-02-26T15:45:58Z)

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.