Copertina

GPO-V: Jailbreak Diffusion Vision Language Model by Global Probability Optimization

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Pan, Yu, Zhang, Andi, Wang, Yi, Yang, Sibei, Wang, Wenjie
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage
di: Wang, Yu, et al.
Pubblicazione: (2024)

Vision Function Layer in Multimodal LLMs
di: Shi, Cheng, et al.
Pubblicazione: (2025)

Vision Transformers Need More Than Registers
di: Shi, Cheng, et al.
Pubblicazione: (2026)

TAIJI: Textual Anchoring for Immunizing Jailbreak Images in Vision Language Models
di: Yin, Xiangyu, et al.
Pubblicazione: (2025)

JailBound: Jailbreaking Internal Safety Boundaries of Vision-Language Models
di: Song, Jiaxin, et al.
Pubblicazione: (2025)

Simulated Ensemble Attack: Transferring Jailbreaks Across Fine-tuned Vision-Language Models
di: Wang, Ruofan, et al.
Pubblicazione: (2025)

Chart Deep Research in LVLMs via Parallel Relative Policy Optimization
di: Tang, Jiajin, et al.
Pubblicazione: (2026)

Penalizing Boundary Activation for Object Completeness in Diffusion Models
di: Xu, Haoyang, et al.
Pubblicazione: (2025)

IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves
di: Wang, Ruofan, et al.
Pubblicazione: (2024)

DiffV2IR: Visible-to-Infrared Diffusion Model via Vision-Language Understanding
di: Ran, Lingyan, et al.
Pubblicazione: (2025)

The devil is in the object boundary: towards annotation-free instance segmentation using Foundation Models
di: Shi, Cheng, et al.
Pubblicazione: (2024)

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models
di: Jiang, Lei, et al.
Pubblicazione: (2025)

Activation Steering Meets Preference Optimization: Defense Against Jailbreaks in Vision Language Models
di: Wu, Sihao, et al.
Pubblicazione: (2025)

Principled Steering via Null-space Projection for Jailbreak Defense in Vision-Language Models
di: Zhu, Xingyu, et al.
Pubblicazione: (2026)

VLDrive: Vision-Augmented Lightweight MLLMs for Efficient Language-grounded Autonomous Driving
di: Zhang, Ruifei, et al.
Pubblicazione: (2025)

White-box Multimodal Jailbreaks Against Large Vision-Language Models
di: Wang, Ruofan, et al.
Pubblicazione: (2024)

Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks
di: Wang, Han, et al.
Pubblicazione: (2024)

Eyes Wide Open: Ego Proactive Video-LLM for Streaming Video
di: Zhang, Yulin, et al.
Pubblicazione: (2025)

JailbreakZoo: Survey, Landscapes, and Horizons in Jailbreaking Large Language and Vision-Language Models
di: Jin, Haibo, et al.
Pubblicazione: (2024)

Compositional Kronecker Context Optimization for Vision-Language Models
di: Ding, Kun, et al.
Pubblicazione: (2024)

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models
di: Liao, Qilin, et al.
Pubblicazione: (2025)

TransXNet: Learning Both Global and Local Dynamics with a Dual Dynamic Token Mixer for Visual Recognition
di: Lou, Meng, et al.
Pubblicazione: (2023)

Curriculum Point Prompting for Weakly-Supervised Referring Image Segmentation
di: Dai, Qiyuan, et al.
Pubblicazione: (2024)

Free on the Fly: Enhancing Flexibility in Test-Time Adaptation with Online EM
di: Dai, Qiyuan, et al.
Pubblicazione: (2025)

Masked Diffusion Vision-Language Models for Temporal Action Localization
di: Wang, Fengshun, et al.
Pubblicazione: (2026)

Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt
di: Ying, Zonghao, et al.
Pubblicazione: (2024)

WMVLM: Evaluating Diffusion Model Image Watermarking via Vision-Language Models
di: Yang, Zijin, et al.
Pubblicazione: (2026)

OmniFashion: Towards Generalist Fashion Intelligence via Multi-Task Vision-Language Learning
di: Yang, Zhengwei, et al.
Pubblicazione: (2026)

Learning to Detect Unknown Jailbreak Attacks in Large Vision-Language Models
di: Liang, Shuang, et al.
Pubblicazione: (2025)

Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment
di: Yan, Ziang, et al.
Pubblicazione: (2024)

SeqAfford: Sequential 3D Affordance Reasoning via Multimodal Large Language Model
di: Yu, Chunlin, et al.
Pubblicazione: (2024)

WeaveTime: Stream from Earlier Frames into Emergent Memory in VideoLLMs
di: Zhang, Yulin, et al.
Pubblicazione: (2026)

No More Sibling Rivalry: Debiasing Human-Object Interaction Detection
di: Yang, Bin, et al.
Pubblicazione: (2025)

Jailbreaks on Vision Language Model via Multimodal Reasoning
di: Noheria, Aarush, et al.
Pubblicazione: (2026)

Towards Better Optimization For Listwise Preference in Diffusion Models
di: Bai, Jiamu, et al.
Pubblicazione: (2025)

QUAR-VLA: Vision-Language-Action Model for Quadruped Robots
di: Ding, Pengxiang, et al.
Pubblicazione: (2023)

DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models
di: Zeng, Lunbin, et al.
Pubblicazione: (2025)

JaiLIP: Jailbreaking Vision-Language Models via Loss Guided Image Perturbation
di: Mia, Md Jueal, et al.
Pubblicazione: (2025)

Discffusion: Discriminative Diffusion Models as Few-shot Vision and Language Learners
di: He, Xuehai, et al.
Pubblicazione: (2023)

Conceptual Codebook Learning for Vision-Language Models
di: Zhang, Yi, et al.
Pubblicazione: (2024)