Image de couverture de livre

ConceptGuard: Proactive Safety in Text-and-Image-to-Video Generation through Multimodal Risk Detection

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ma, Ruize, Cai, Minghong, Jiang, Yilei, Han, Jiaming, Feng, Yi, Tan, Yingshui, Zhu, Xiaoyong, Zhang, Bo, Zheng, Bo, Yue, Xiangyu
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

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

MSR-Align: Policy-Grounded Multimodal Alignment for Safety-Aware Reasoning in Vision-Language Models
par: Xia, Yinan, et autres
Publié: (2025)

HiddenDetect: Detecting Jailbreak Attacks against Large Vision-Language Models via Monitoring Hidden States
par: Jiang, Yilei, et autres
Publié: (2025)

Guarding the Gate: ConceptGuard Battles Concept-Level Backdoors in Concept Bottleneck Models
par: Lai, Songning, et autres
Publié: (2024)

ConceptGuard: Continual Personalized Text-to-Image Generation with Forgetting and Confusion Mitigation
par: Guo, Zirun, et autres
Publié: (2025)

ConceptGuard: Neuro-Symbolic Safety Guardrails via Sparse Interpretable Jailbreak Concepts
par: Aswal, Darpan, et autres
Publié: (2025)

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment
par: Liu, Zhendong, et autres
Publié: (2024)

QuadSentinel: Sequent Safety for Machine-Checkable Control in Multi-agent Systems
par: Yang, Yiliu, et autres
Publié: (2025)

Equilibrate RLHF: Towards Balancing Helpfulness-Safety Trade-off in Large Language Models
par: Tan, Yingshui, et autres
Publié: (2025)

FairGen: Enhancing Fairness in Text-to-Image Diffusion Models via Self-Discovering Latent Directions
par: Jiang, Yilei, et autres
Publié: (2024)

Safety Alignment for Vision Language Models
par: Liu, Zhendong, et autres
Publié: (2024)

A Review of Detection, Evolution, and Data Reconstruction Strategies for False Data Injection Attacks in Power Cyber-Physical Systems
par: Bo, Xiaoyong
Publié: (2025)

FailureMem: A Failure-Aware Multimodal Framework for Autonomous Software Repair
par: Ma, Ruize, et autres
Publié: (2026)

ProGuard: Towards Proactive Multimodal Safeguard
par: Yu, Shaohan, et autres
Publié: (2025)

Multimodal Long Video Modeling Based on Temporal Dynamic Context
par: Hao, Haoran, et autres
Publié: (2025)

In-Context Audio Control of Video Diffusion Transformers
par: Liu, Wenze, et autres
Publié: (2025)

SafeDream: Safety World Model for Proactive Early Jailbreak Detection
par: Yan, Bo, et autres
Publié: (2026)

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models
par: Zheng, Baolin, et autres
Publié: (2025)

AlignGuard: Scalable Safety Alignment for Text-to-Image Generation
par: Liu, Runtao, et autres
Publié: (2024)

When Safety Collides: Resolving Multi-Category Harmful Conflicts in Text-to-Image Diffusion via Adaptive Safety Guidance
par: Xiang, Yongli, et autres
Publié: (2026)

ScreenCoder: Advancing Visual-to-Code Generation for Front-End Automation via Modular Multimodal Agents
par: Jiang, Yilei, et autres
Publié: (2025)

OpenGame: Open Agentic Coding for Games
par: Jiang, Yilei, et autres
Publié: (2026)

VR-Thinker: Boosting Video Reward Models through Thinking-with-Image Reasoning
par: Wang, Qunzhong, et autres
Publié: (2025)

Enhancing Weakly Supervised Multimodal Video Anomaly Detection through Text Guidance
par: Sun, Shengyang, et autres
Publié: (2026)

Beyond Safe Answers: A Benchmark for Evaluating True Risk Awareness in Large Reasoning Models
par: Zheng, Baihui, et autres
Publié: (2025)

AudioGuard: Toward Comprehensive Audio Safety Protection Across Diverse Threat Models
par: Kang, Mintong, et autres
Publié: (2026)

RAP: Retrieval-Augmented Personalization for Multimodal Large Language Models
par: Hao, Haoran, et autres
Publié: (2024)

OneThinker: All-in-one Reasoning Model for Image and Video
par: Feng, Kaituo, et autres
Publié: (2025)

DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models
par: Liu, Jianyu, et autres
Publié: (2025)

Unlearning Concepts from Text-to-Video Diffusion Models
par: Liu, Shiqi, et autres
Publié: (2024)

COVD: Continual Open-Vocabulary Object Detection with Novel Concept Injection
par: Zhang, Yupeng, et autres
Publié: (2026)

SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation
par: Yoon, Jaehong, et autres
Publié: (2024)

A-MemGuard: A Proactive Defense Framework for LLM-Based Agent Memory
par: Wei, Qianshan, et autres
Publié: (2025)

PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models
par: Yuan, Lingzhi, et autres
Publié: (2025)

Multimodal Magic Elevating Depression Detection with a Fusion of Text and Audio Intelligence
par: Gan, Lindy, et autres
Publié: (2025)

GuardReasoner-Omni: A Reasoning-based Multi-modal Guardrail for Text, Image, Video, and Audio
par: Zhu, Zhenhao, et autres
Publié: (2026)

DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation
par: Cai, Minghong, et autres
Publié: (2024)

DistillGuard: Evaluating Defenses Against LLM Knowledge Distillation
par: Jiang, Bo
Publié: (2026)

DiffGuard: Text-Based Safety Checker for Diffusion Models
par: Khader, Massine El, et autres
Publié: (2024)

Latent Guard: a Safety Framework for Text-to-image Generation
par: Liu, Runtao, et autres
Publié: (2024)