Imagen de Portada

SafeVision: Efficient Image Guardrail with Robust Policy Adherence and Explainability

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xu, Peiyang, Pan, Minzhou, Chen, Zhaorun, Yang, Shuang, Xiao, Chaowei, Li, Bo
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence Cryptography and Security
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanations
por: Chen, Zhaorun, et al.
Publicado: (2024)

Poly-Guard: Massive Multi-Domain Safety Policy-Grounded Guardrail Dataset
por: Kang, Mintong, et al.
Publicado: (2025)

Natural Language Induced Adversarial Images
por: Zhu, Xiaopei, et al.
Publicado: (2024)

SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization
por: Rong, Xuankun, et al.
Publicado: (2025)

VLM-Guard: Safeguarding Vision-Language Models via Fulfilling Safety Alignment Gap
por: Liu, Qin, et al.
Publicado: (2025)

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models
por: Zhang, Rui, et al.
Publicado: (2025)

Robust Provably Secure Image Steganography via Latent Iterative Optimization
por: Li, Yanan, et al.
Publicado: (2026)

HomeSafe-Bench: Evaluating Vision-Language Models on Unsafe Action Detection for Embodied Agents in Household Scenarios
por: Pu, Jiayue, et al.
Publicado: (2026)

Robustness of Vision Foundation Models to Common Perturbations
por: Liu, Hongbin, et al.
Publicado: (2026)

Pura: An Efficient Privacy-Preserving Solution for Face Recognition
por: Xu, Guotao, et al.
Publicado: (2025)

A Cross-Modal Prompt Injection Attack against Large Vision-Language Models with Image-Only Perturbation
por: Yang, Hao, et al.
Publicado: (2026)

SafeText: Safe Text-to-image Models via Aligning the Text Encoder
por: Hu, Yuepeng, et al.
Publicado: (2025)

Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images
por: Gao, Kuofeng, et al.
Publicado: (2024)

Improving Adversarial Transferability on Vision Transformers via Forward Propagation Refinement
por: Ren, Yuchen, et al.
Publicado: (2025)

BadBlocks: Low-Cost and Stealthy Backdoor Attacks Tailored for Text-to-Image Diffusion Models
por: Wu, Jia, et al.
Publicado: (2025)

FreqCross: A Multi-Modal Frequency-Spatial Fusion Network for Robust Detection of Stable Diffusion 3.5 Generated Images
por: Yang, Guang
Publicado: (2025)

Espresso: Robust Concept Filtering in Text-to-Image Models
por: Das, Anudeep, et al.
Publicado: (2024)

Robust and Transferable Backdoor Attacks Against Deep Image Compression With Selective Frequency Prior
por: Yu, Yi, et al.
Publicado: (2024)

PromptSmooth: Certifying Robustness of Medical Vision-Language Models via Prompt Learning
por: Hussein, Noor, et al.
Publicado: (2024)

Light as Deception: GPT-driven Natural Relighting Against Vision-Language Pre-training Models
por: Yang, Ying, et al.
Publicado: (2025)

LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails
por: Li, Nanxi, et al.
Publicado: (2026)

A Lightweight and Effective Image Tampering Localization Network with Vision Mamba
por: Guo, Kun, et al.
Publicado: (2025)

FIDAVL: Fake Image Detection and Attribution using Vision-Language Model
por: Keita, Mamadou, et al.
Publicado: (2024)

TarPro: Targeted Protection against Malicious Image Editing
por: Shen, Kaixin, et al.
Publicado: (2025)

GuardSplat: Efficient and Robust Watermarking for 3D Gaussian Splatting
por: Chen, Zixuan, et al.
Publicado: (2024)

PRISM: Programmatic Reasoning with Image Sequence Manipulation for LVLM Jailbreaking
por: Zou, Quanchen, et al.
Publicado: (2025)

ZeroPur: Succinct Training-Free Adversarial Purification
por: Liu, Erhu, et al.
Publicado: (2024)

Secure and Robust Watermarking for AI-generated Images: A Comprehensive Survey
por: Cao, Jie, et al.
Publicado: (2025)

Toward Reliable, Safe, and Secure LLMs for Scientific Applications
por: Chaturvedi, Saket Sanjeev, et al.
Publicado: (2026)

A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations
por: Ye, Mang, et al.
Publicado: (2025)

Image Corruption-Inspired Membership Inference Attacks against Large Vision-Language Models
por: Wu, Zongyu, et al.
Publicado: (2025)

Robust Image Classification: Defensive Strategies against FGSM and PGD Adversarial Attacks
por: Waghela, Hetvi, et al.
Publicado: (2024)

Exploring Multi-view Pixel Contrast for General and Robust Image Forgery Localization
por: Lou, Zijie, et al.
Publicado: (2024)

Frequency Bias Matters: Diving into Robust and Generalized Deep Image Forgery Detection
por: Liu, Chi, et al.
Publicado: (2025)

Test-Time Attention Purification for Backdoored Large Vision Language Models
por: Zhang, Zhifang, et al.
Publicado: (2026)

Bodhi VLM: Privacy-Alignment Modeling for Hierarchical Visual Representations in Vision Backbones and VLM Encoders via Bottom-Up and Top-Down Feature Search
por: Ma, Bo, et al.
Publicado: (2026)

Towards Robust GAN-generated Image Detection: a Multi-view Completion Representation
por: Liu, Chi, et al.
Publicado: (2023)

Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion Models
por: Zhang, Lei, et al.
Publicado: (2025)

Are Vision-Language Models Safe in the Wild? A Meme-Based Benchmark Study
por: Lee, DongGeon, et al.
Publicado: (2025)

Learning to Detect Unseen Jailbreak Attacks in Large Vision-Language Models
por: Liang, Shuang, et al.
Publicado: (2025)