Buchumschlag

BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Zhao, Yunhan, Zheng, Xiang, Luo, Lin, Li, Yige, Ma, Xingjun, Jiang, Yu-Gang
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Defense-to-Attack: Bypassing Weak Defenses Enables Stronger Jailbreaks in Vision-Language Models
von: Zhao, Yunhan, et al.
Veröffentlicht: (2025)

AttackVLA: Benchmarking Adversarial and Backdoor Attacks on Vision-Language-Action Models
von: Li, Jiayu, et al.
Veröffentlicht: (2025)

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

Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models
von: Cui, Kaiyuan, et al.
Veröffentlicht: (2026)

BackdoorVLM: A Benchmark for Backdoor Attacks on Vision-Language Models
von: Li, Juncheng, et al.
Veröffentlicht: (2025)

Downstream Transfer Attack: Adversarial Attacks on Downstream Models with Pre-trained Vision Transformers
von: Zheng, Weijie, et al.
Veröffentlicht: (2024)

Adversarial Prompt Distillation for Vision-Language Models
von: Luo, Lin, et al.
Veröffentlicht: (2024)

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

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

FedAPT: Federated Adversarial Prompt Tuning for Vision-Language Models
von: Zhai, Kun, et al.
Veröffentlicht: (2025)

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

RedDiffuser: Auditing Multimodal Safety Failures in Vision-Language Models via Reinforced Diffusion
von: Wang, Ruofan, et al.
Veröffentlicht: (2025)

AIM: Additional Image Guided Generation of Transferable Adversarial Attacks
von: Li, Teng, et al.
Veröffentlicht: (2025)

DropVLA: An Action-Level Backdoor Attack on Vision-Language-Action Models
von: Xu, Zonghuan, et al.
Veröffentlicht: (2025)

Securing Vision-Language Models with a Robust Encoder Against Jailbreak and Adversarial Attacks
von: Hossain, Md Zarif, et al.
Veröffentlicht: (2024)

FreezeVLA: Action-Freezing Attacks against Vision-Language-Action Models
von: Wang, Xin, et al.
Veröffentlicht: (2025)

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

Adversarial Prompt Tuning for Vision-Language Models
von: Zhang, Jiaming, et al.
Veröffentlicht: (2023)

X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP
von: Huang, Hanxun, et al.
Veröffentlicht: (2025)

HoneypotNet: Backdoor Attacks Against Model Extraction
von: Wang, Yixu, et al.
Veröffentlicht: (2025)

NAP-Tuning: Neural Augmented Prompt Tuning for Adversarially Robust Vision-Language Models
von: Zhang, Jiaming, et al.
Veröffentlicht: (2025)

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

TrojVLM: Backdoor Attack Against Vision Language Models
von: Lyu, Weimin, et al.
Veröffentlicht: (2024)

BadPatch: Diffusion-Based Generation of Physical Adversarial Patches
von: Wang, Zhixiang, et al.
Veröffentlicht: (2024)

Detecting Backdoor Samples in Contrastive Language Image Pretraining
von: Huang, Hanxun, et al.
Veröffentlicht: (2025)

TAME: Test-Time Adversarial Prompt Tuning via Mixture-of-Experts for Vision-Language Models
von: Wang, Xin, et al.
Veröffentlicht: (2026)

Text is All You Need for Vision-Language Model Jailbreaking
von: Chen, Yihang, et al.
Veröffentlicht: (2026)

AdvQDet: Detecting Query-Based Adversarial Attacks with Adversarial Contrastive Prompt Tuning
von: Wang, Xin, et al.
Veröffentlicht: (2024)

Benchmarking Gaslighting Negation Attacks Against Reasoning Models
von: Zhu, Bin, et al.
Veröffentlicht: (2025)

BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models
von: Li, Yige, et al.
Veröffentlicht: (2024)

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

SAMA: Towards Multi-Turn Referential Grounded Video Chat with Large Language Models
von: Sun, Ye, et al.
Veröffentlicht: (2025)

Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks
von: Zhou, Andy, et al.
Veröffentlicht: (2024)

Jailbreaking Attack against Multimodal Large Language Model
von: Niu, Zhenxing, et al.
Veröffentlicht: (2024)

TrajShield: Trajectory-Level Safety Mediation for Defending Text-to-Video Models Against Jailbreak Attacks
von: Zou, Quanchen, et al.
Veröffentlicht: (2026)

Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks
von: Xie, Peng, et al.
Veröffentlicht: (2024)

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

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

Extracting Training Data from Unconditional Diffusion Models
von: Chen, Yunhao, et al.
Veröffentlicht: (2024)

Low-Effort Jailbreak Attacks Against Text-to-Image Safety Filters
von: Mustafa, Ahmed B, et al.
Veröffentlicht: (2026)