Imagen de Portada

LatentGuard: Controllable Latent Steering for Robust Refusal of Attacks and Reliable Response Generation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Shu, Huizhen, Li, Xuying, Li, Zhuo
Formato:	Preprint
Publicado:	2025
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

The Resurgence of GCG Adversarial Attacks on Large Language Models
por: Tan, Yuting, et al.
Publicado: (2025)

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation
por: Shu, Huizhen, et al.
Publicado: (2025)

Latent-space Attacks for Refusal Evasion in Language Models
por: Piras, Giorgio, et al.
Publicado: (2026)

LatentRefusal: Latent-Signal Refusal for Unanswerable Text-to-SQL Queries
por: Ren, Xuancheng, et al.
Publicado: (2026)

From Refusal Tokens to Refusal Control: Discovering and Steering Category-Specific Refusal Directions
por: Alagharu, Rishab, et al.
Publicado: (2026)

Tracing the Dynamics of Refusal: Exploiting Latent Refusal Trajectories for Robust Jailbreak Detection
por: Hu, Xulin, et al.
Publicado: (2026)

Exploring the Personality Traits of LLMs through Latent Features Steering
por: Yang, Shu, et al.
Publicado: (2024)

Unveiling and Steering Connectome Organization with Interpretable Latent Variables
por: Li, Yubin, et al.
Publicado: (2025)

Refusal Steering: Fine-grained Control over LLM Refusal Behaviour for Sensitive Topics
por: García-Ferrero, Iker, et al.
Publicado: (2025)

Targeting the Core: A Simple and Effective Method to Attack RAG-based Agents via Direct LLM Manipulation
por: Li, Xuying, et al.
Publicado: (2024)

Steer LLM Latents for Hallucination Detection
por: Park, Seongheon, et al.
Publicado: (2025)

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

RISER: Orchestrating Latent Reasoning Skills for Adaptive Activation Steering
por: Ye, Wencheng, et al.
Publicado: (2026)

Programming Refusal with Conditional Activation Steering
por: Lee, Bruce W., et al.
Publicado: (2024)

Feature-Guided SAE Steering for Refusal-Rate Control using Contrasting Prompts
por: Bhargav, Samaksh, et al.
Publicado: (2025)

Controllable Mathematical Reasoning via Self-Optimizing Thought Vectors
por: LI, Xuying
Publicado: (2025)

Latent Space Disentanglement via Activation Steering for Interpretable Attribute Control in Symbolic Music Generation
por: Prokopiou, Ioannis, et al.
Publicado: (2026)

Transferable Latent-to-Latent Locomotion Policy for Efficient and Versatile Motion Control of Diverse Legged Robots
por: Zheng, Ziang, et al.
Publicado: (2025)

AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint
por: Sheng, Leheng, et al.
Publicado: (2025)

Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs
por: Li, Jiakang, et al.
Publicado: (2026)

Output Length Effect on DeepSeek-R1's Safety in Forced Thinking
por: Li, Xuying, et al.
Publicado: (2025)

Learn to Refuse: Making Large Language Models More Controllable and Reliable through Knowledge Scope Limitation and Refusal Mechanism
por: Cao, Lang
Publicado: (2023)

Preemptive Detection and Steering of LLM Misalignment via Latent Reachability
por: Karnik, Sathwik, et al.
Publicado: (2025)

On Effects of Steering Latent Representation for Large Language Model Unlearning
por: Huu-Tien, Dang, et al.
Publicado: (2024)

Spatial-Aware Latent Initialization for Controllable Image Generation
por: Sun, Wenqiang, et al.
Publicado: (2024)

RepIt: Steering Language Models with Concept-Specific Refusal Vectors
por: Siu, Vincent, et al.
Publicado: (2025)

What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal
por: Cheng, Stephen, et al.
Publicado: (2026)

Latent Action Control for Reasoning-Guided Unified Image Generation
por: Zhai, Fuxiang, et al.
Publicado: (2026)

Controllable and Stealthy Shilling Attacks via Dispersive Latent Diffusion
por: Qiao, Shutong, et al.
Publicado: (2025)

Beyond a Single Direction: Chain-of-Thought Disrupts Simple Steering of Refusal
por: Yang, Kia-Jüng, et al.
Publicado: (2026)

Latent Policy Steering with Embodiment-Agnostic Pretrained World Models
por: Wang, Yiqi, et al.
Publicado: (2025)

Learning Latent Dynamic Robust Representations for World Models
por: Sun, Ruixiang, et al.
Publicado: (2024)

Amortized Latent Steering: Low-Cost Alternative to Test-Time Optimization
por: Egbuna, Nathan, et al.
Publicado: (2025)

Memory Inception: Latent-Space KV Cache Manipulation for Steering LLMs
por: Liu, Andy Zeyi, et al.
Publicado: (2026)

FlowGuard: Towards Lightweight In-Generation Safety Detection for Diffusion Models via Linear Latent Decoding
por: Yang, Jinghan, et al.
Publicado: (2026)

In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering
por: Liu, Sheng, et al.
Publicado: (2023)

Beyond Explicit Refusals: Soft-Failure Attacks on Retrieval-Augmented Generation
por: Zhang, Wentao, et al.
Publicado: (2026)

Steering to Say No: Configurable Refusal via Activation Steering in Vision Language Models
por: Yang, Jiaxi, et al.
Publicado: (2026)

Precision Knowledge Editing: Enhancing Safety in Large Language Models
por: Li, Xuying, et al.
Publicado: (2024)

Robust Latent Matters: Boosting Image Generation with Sampling Error Synthesis
por: Qiu, Kai, et al.
Publicado: (2025)