Cover Image

A Guardrail for Safety Preservation: When Safety-Sensitive Subspace Meets Harmful-Resistant Null-Space

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Bingjie, Yang, Yibo, Ren, Zhe, Guo, Dandan, Gu, Jindong, Torr, Philip, Ghanem, Bernard
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Purifying Task Vectors in Knowledge-Aware Subspace for Model Merging
by: An, Bang, et al.
Published: (2025)

Unforgotten Safety: Preserving Safety Alignment of Large Language Models with Continual Learning
by: Alssum, Lama, et al.
Published: (2025)

Reimagining Safety Alignment with An Image
by: Xia, Yifan, et al.
Published: (2025)

Bag of Tricks for Subverting Reasoning-based Safety Guardrails
by: Chen, Shuo, et al.
Published: (2025)

Latent Guard: a Safety Framework for Text-to-image Generation
by: Liu, Runtao, et al.
Published: (2024)

Rethinking Safety in LLM Fine-tuning: An Optimization Perspective
by: Kim, Minseon, et al.
Published: (2025)

Model Merging and Safety Alignment: One Bad Model Spoils the Bunch
by: Hammoud, Hasan Abed Al Kader, et al.
Published: (2024)

Safety Guardrails for LLM-Enabled Robots
by: Ravichandran, Zachary, et al.
Published: (2025)

Stop Reasoning! When Multimodal LLM with Chain-of-Thought Reasoning Meets Adversarial Image
by: Wang, Zefeng, et al.
Published: (2024)

SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety
by: Liu, Zhe, et al.
Published: (2026)

AlignGuard: Scalable Safety Alignment for Text-to-Image Generation
by: Liu, Runtao, et al.
Published: (2024)

PSG-Agent: Personality-Aware Safety Guardrail for LLM-based Agents
by: Wu, Yaozu, et al.
Published: (2025)

Test-Time Training Undermines Safety Guardrails
by: Antonelli, Simone, et al.
Published: (2026)

A Lightweight Explainable Guardrail for Prompt Safety
by: Islam, Md Asiful, et al.
Published: (2026)

SAVeS: Steering Safety Judgments in Vision-Language Models via Semantic Cues
by: Hinojosa, Carlos, et al.
Published: (2026)

Deep Research with Open-Domain Evaluation and Multi-Stage Guardrails for Safety
by: Huang, Wei-Chieh, et al.
Published: (2025)

Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need?
by: Yu, Junchi, et al.
Published: (2025)

Building Effective Safety Guardrails in AI Education Tools
by: Clark, Hannah-Beth, et al.
Published: (2025)

Dynamic Context-oriented Decomposition for Task-aware Low-rank Adaptation with Less Forgetting and Faster Convergence
by: Yang, Yibo, et al.
Published: (2025)

Why Do Safety Guardrails Degrade Across Languages?
by: Zhang, Max, et al.
Published: (2026)

Breaking the Safety-Capability Tradeoff: Reinforcement Learning with Verifiable Rewards Maintains Safety Guardrails in LLMs
by: Cho, Dongkyu Derek, et al.
Published: (2025)

Safety Through Reasoning: An Empirical Study of Reasoning Guardrail Models
by: Sreedhar, Makesh Narsimhan, et al.
Published: (2025)

Bridging the Safety Gap: A Guardrail Pipeline for Trustworthy LLM Inferences
by: Han, Shanshan, et al.
Published: (2025)

AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection
by: Luo, Weidi, et al.
Published: (2025)

Enhancing Online Continual Learning with Plug-and-Play State Space Model and Class-Conditional Mixture of Discretization
by: Liu, Sihao, et al.
Published: (2024)

CR4T: Rewrite-Based Guardrails for Adolescent LLM Safety
by: An, Heajun, et al.
Published: (2026)

SGuard-v1: Safety Guardrail for Large Language Models
by: Lee, JoonHo, et al.
Published: (2025)

Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models
by: Zhang, Wenxuan, et al.
Published: (2024)

SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents
by: Jia, Xiaojun, et al.
Published: (2026)

Multimodal Safety Evaluation in Generative Agent Social Simulations
by: Vera, Alhim, et al.
Published: (2025)

DiffCLIP: Differential Attention Meets CLIP
by: Hammoud, Hasan Abed Al Kader, et al.
Published: (2025)

Noise Injection Systemically Degrades Large Language Model Safety Guardrails
by: Shahani, Prithviraj Singh, et al.
Published: (2025)

Benchmarking Open-ended Audio Dialogue Understanding for Large Audio-Language Models
by: Gao, Kuofeng, et al.
Published: (2024)

Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection
by: Shairah, Harethah Abu, et al.
Published: (2025)

AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
by: Liu, Dongrui, et al.
Published: (2026)

LLM Jailbreak Detection for (Almost) Free!
by: Chen, Guorui, et al.
Published: (2025)

Lightweight Safety Guardrails via Synthetic Data and RL-guided Adversarial Training
by: Ilin, Aleksei, et al.
Published: (2025)

Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment
by: Krishna, Kundan, et al.
Published: (2025)

LSSF: Safety Alignment for Large Language Models through Low-Rank Safety Subspace Fusion
by: Zhou, Guanghao, et al.
Published: (2026)

OOD-MMSafe: Advancing MLLM Safety from Harmful Intent to Hidden Consequences
by: Wen, Ming, et al.
Published: (2026)