Image de couverture de livre

Kelp: A Streaming Safeguard for Large Models via Latent Dynamics-Guided Risk Detection

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Xiaodan, Wu, Mengjie, Zhu, Yao, Lv, Yunna, Chen, YueFeng, Chen, Cen, Guo, Jianmei, Xue, Hui
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency
par: Zhao, Shiji, et autres
Publié: (2025)

Dynamic Guided and Domain Applicable Safeguards for Enhanced Security in Large Language Models
par: Luo, Weidi, et autres
Publié: (2024)

ConsisGuard: Aligning Safety Deliberation with Policy Enforcement in LLM Guardrails
par: Wang, Yan, et autres
Publié: (2026)

LGD-Net: Latent-Guided Dual-Stream Network for HER2 Scoring with Task-Specific Domain Knowledge
par: Zhu, Peide, et autres
Publié: (2026)

GATES: Cost-aware Dynamic Workflow Scheduling via Graph Attention Networks and Evolution Strategy
par: Shen, Ya, et autres
Publié: (2025)

MRJ-Agent: An Effective Jailbreak Agent for Multi-Round Dialogue
par: Wang, Fengxiang, et autres
Publié: (2024)

Video Anomaly Detection and Explanation via Large Language Models
par: Lv, Hui, et autres
Publié: (2024)

Low‐cost and easy‐to‐embed 7‐bit 360° phase shifter with transitions for large‐scale phased arrays
par: MeiCheng Liu, et autres
Publié: (2024)

Prediction of Unmanned Surface Vessel Motion Attitude Based on CEEMDAN-PSO-SVM
par: Geng, Zhuoya, et autres
Publié: (2024)

Inference on Dynamic Spatial Autoregressive Models with Change Point Detection
par: Cen, Zetai, et autres
Publié: (2024)

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator
par: Zhou, Xueyang, et autres
Publié: (2025)

Make the Most of Everything: Further Considerations on Disrupting Diffusion-based Customization
par: Tang, Long, et autres
Publié: (2025)

SentinelNet: Safeguarding Multi-Agent Collaboration Through Credit-Based Dynamic Threat Detection
par: Feng, Yang, et autres
Publié: (2025)

StreamUni: Achieving Streaming Speech Translation with a Unified Large Speech-Language Model
par: Guo, Shoutao, et autres
Publié: (2025)

DyEdgeGAT: Dynamic Edge via Graph Attention for Early Fault Detection in IIoT Systems
par: Zhao, Mengjie, et autres
Publié: (2023)

TraceMark-LDM: Authenticatable Watermarking for Latent Diffusion Models via Binary-Guided Rearrangement
par: Luo, Wenhao, et autres
Publié: (2025)

Comprehensive Assessment and Analysis for NSFW Content Erasure in Text-to-Image Diffusion Models
par: Chen, Die, et autres
Publié: (2025)

SARSteer: Safeguarding Large Audio-Language Models via Safe-Ablated Refusal Steering
par: Lin, Weilin, et autres
Publié: (2025)

NExT-Guard: Training-Free Streaming Safeguard without Token-Level Labels
par: Fang, Junfeng, et autres
Publié: (2026)

Merging Beyond: Streaming LLM Updates via Activation-Guided Rotations
par: Yao, Yuxuan, et autres
Publié: (2026)

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting
par: Jiang, Yilei, et autres
Publié: (2024)

Kelp temperature tolerance
par: Wright, Luka Seamus
Publié: (2023)

Safety-Critical Traffic Simulation with Guided Latent Diffusion Model
par: Peng, Mingxing, et autres
Publié: (2025)

Towards Generalizable PDE Dynamics Forecasting via Physics-Guided Invariant Learning
par: Li, Siyang, et autres
Publié: (2025)

Cost-Aware Dynamic Cloud Workflow Scheduling using Self-Attention and Evolutionary Reinforcement Learning
par: Shen, Ya, et autres
Publié: (2024)

Learning Symbolic Model-Agnostic Loss Functions via Meta-Learning
par: Raymond, Christian, et autres
Publié: (2022)

Reward Guided Latent Consistency Distillation
par: Li, Jiachen, et autres
Publié: (2024)

Take Fake as Real: Realistic-like Robust Black-box Adversarial Attack to Evade AIGC Detection
par: Xie, Caiyun, et autres
Publié: (2024)

CORA: Conformal Risk-Controlled Agents for Safeguarded Mobile GUI Automation
par: Feng, Yushi, et autres
Publié: (2026)

JLT: Clean-Latent Prediction in Latent Diffusion Transformers
par: Fu, Funing, et autres
Publié: (2026)

Label-Guided Prompt for Multi-label Few-shot Aspect Category Detection
par: Guan, ChaoFeng, et autres
Publié: (2024)

SALLIE: Safeguarding Against Latent Language & Image Exploits
par: Azov, Guy, et autres
Publié: (2026)

Libra: Large Chinese-based Safeguard for AI Content
par: Chen, Ziyang, et autres
Publié: (2025)

Computer Security-Risks, Threats, and Safeguards.
par: Ekhaml, Leticia
Publié: (2001)

Harnessing Sunshine: A Dynamic Spillover Analysis of the Diversification Effects of China's Photovoltaic Weather Index
par: Yu Wei, et autres
Publié: (2026)

Mechanisms underlining Kelp (Saccharina japonica) adaptation to relative high seawater temperature.
par: Guo, Li, et autres
Publié: (2025)

Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy
par: Tang, Xiangru, et autres
Publié: (2024)

Evaluating Chinese Large Language Models: The Influence of Persona Assignment on Stereotypes and Safeguards
par: Liu, Geng, et autres
Publié: (2025)

Refiner: Data Refining against Gradient Leakage Attacks in Federated Learning
par: Fan, Mingyuan, et autres
Publié: (2022)

Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and Flatness
par: Fan, Mingyuan, et autres
Publié: (2023)