Related papers: BarrierSteer: LLM Safety via Learning Barrier Steering

BarrierSteer: LLM Safety via Learning Barrier Steering

URL: http://arxiv.org/abs/2602.20102v1
Date: Mon, 23 Feb 2026 18:19:46 GMT
Title: BarrierSteer: LLM Safety via Learning Barrier Steering
Authors: Thanh Q. Tran, Arun Verma, Kiwan Wong, Bryan Kian Hsiang Low, Daniela Rus, Wei Xiao,
Abstract summary: BarrierSteer is a novel framework that formalizes safety by embedding learned non-linear safety constraints directly into the model's latent representation space.<n>We show that BarrierSteer substantially reduces adversarial success rates, decreases unsafe generations, and outperforms existing methods.
Score: 83.12893815611052
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Despite the state-of-the-art performance of large language models (LLMs) across diverse tasks, their susceptibility to adversarial attacks and unsafe content generation remains a major obstacle to deployment, particularly in high-stakes settings. Addressing this challenge requires safety mechanisms that are both practically effective and supported by rigorous theory. We introduce BarrierSteer, a novel framework that formalizes response safety by embedding learned non-linear safety constraints directly into the model's latent representation space. BarrierSteer employs a steering mechanism based on Control Barrier Functions (CBFs) to efficiently detect and prevent unsafe response trajectories during inference with high precision. By enforcing multiple safety constraints through efficient constraint merging, without modifying the underlying LLM parameters, BarrierSteer preserves the model's original capabilities and performance. We provide theoretical results establishing that applying CBFs in latent space offers a principled and computationally efficient approach to enforcing safety. Our experiments across multiple models and datasets show that BarrierSteer substantially reduces adversarial success rates, decreases unsafe generations, and outperforms existing methods.

Related papers

Safe Reinforcement Learning via Recovery-based Shielding with Gaussian Process Dynamics Models [57.006252510102506]
Reinforcement learning (RL) is a powerful framework for optimal decision-making and control but often lacks provable guarantees for safety-critical applications.<n>We introduce a novel recovery-based shielding framework that enables safe RL with a provable safety lower bound for unknown and non-linear continuous dynamical systems.
arXiv Detail & Related papers (2026-02-12T22:03:35Z)
V-OCBF: Learning Safety Filters from Offline Data via Value-Guided Offline Control Barrier Functions [8.042484673796137]
We introduce Value-Guided Offline Control Barrier Functions (V-OCBF)<n>It learns a neural CBF entirely from offline demonstrations.<n>It yields substantially fewer safety violations than baseline methods.
arXiv Detail & Related papers (2025-12-11T17:14:37Z)
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)
Anchoring Refusal Direction: Mitigating Safety Risks in Tuning via Projection Constraint [52.878820730054365]
Instruction Fine-Tuning (IFT) has been widely adopted as an effective post-training strategy to enhance abilities of Large Language Models (LLMs)<n>Recent research into the internal mechanisms of LLMs has identified the refusal direction (r-direction) in the hidden states, which plays a pivotal role in governing refusal behavior.<n>To mitigate such drift, our proposed ProCon method introduces a projection-constrained loss term that regularizes the projection magnitude of each training sample's hidden state onto the r-direction.
arXiv Detail & Related papers (2025-09-08T15:24:33Z)
Efficient Switchable Safety Control in LLMs via Magic-Token-Guided Co-Training [1.5349686675266894]
Current methods for content safety in Large Language Models (LLMs) rely on multi-stage training pipelines.<n>We propose a unified co-training framework that efficiently integrates multiple safety behaviors.<n>We show that our method matches the safety alignment quality of SFT+DPO, with our 8B model notably surpassing DeepSeek-R1 (671B) in safety performance.
arXiv Detail & Related papers (2025-08-12T02:39:33Z)
SafeSteer: Interpretable Safety Steering with Refusal-Evasion in LLMs [7.120986296945107]
This paper investigates an approach called SafeSteer for guiding the outputs of large language models (LLMs)<n>We employ a simple, gradient-free unsupervised method to enhance safety steering while preserving text quality, topic relevance, and without explicit refusal.
arXiv Detail & Related papers (2025-06-01T01:19:37Z)
SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering [56.92068213969036]
Safety alignment is indispensable for Large Language Models (LLMs) to defend threats from malicious instructions.<n>Recent researches reveal safety-aligned LLMs prone to reject benign queries due to the exaggerated safety issue.<n>We propose a Safety-Conscious Activation Steering (SCANS) method to mitigate the exaggerated safety concerns.
arXiv Detail & Related papers (2024-08-21T10:01:34Z)
Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments [84.3830478851369]
We propose a safe reinforcement learning approach that can jointly learn the environment and optimize the control policy. Our approach can effectively enforce hard safety constraints and significantly outperform CMDP-based baseline methods in system safe rate measured via simulations.
arXiv Detail & Related papers (2022-09-29T20:49:25Z)
Lyapunov-based uncertainty-aware safe reinforcement learning [0.0]
InReinforcement learning (RL) has shown a promising performance in learning optimal policies for a variety of sequential decision-making tasks. In many real-world RL problems, besides optimizing the main objectives, the agent is expected to satisfy a certain level of safety. We propose a Lyapunov-based uncertainty-aware safe RL model to address these limitations.
arXiv Detail & Related papers (2021-07-29T13:08:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.