Image de couverture de livre

Anyone Can Jailbreak: Prompt-Based Attacks on LLMs and T2Is

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Mustafa, Ahmed B, Ye, Zihan, Lu, Yang, Pound, Michael P, Gowda, Shreyank N
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Low-Effort Jailbreak Attacks Against Text-to-Image Safety Filters
par: Mustafa, Ahmed B, et autres
Publié: (2026)

Compression as an Adversarial Amplifier Through Decision Space Reduction
par: Evans, Lewis, et autres
Publié: (2026)

ZeroDiff++: Substantial Unseen Visual-semantic Correlation in Zero-shot Learning
par: Ye, Zihan, et autres
Publié: (2026)

Is Temporal Prompting All We Need For Limited Labeled Action Recognition?
par: Gowda, Shreyank N, et autres
Publié: (2025)

CC-SAM: SAM with Cross-feature Attention and Context for Ultrasound Image Segmentation
par: Gowda, Shreyank N, et autres
Publié: (2024)

Masks and Manuscripts: Advancing Medical Pre-training with End-to-End Masking and Narrative Structuring
par: Gowda, Shreyank N, et autres
Publié: (2024)

Telling Stories for Common Sense Zero-Shot Action Recognition
par: Gowda, Shreyank N, et autres
Publié: (2023)

Distribution-Based Masked Medical Vision-Language Model Using Structured Reports
par: Gowda, Shreyank N, et autres
Publié: (2025)

Interpretable Zero-shot Learning with Infinite Class Concepts
par: Ye, Zihan, et autres
Publié: (2025)

Adversarial Robustness in Zero-Shot Learning:An Empirical Study on Class and Concept-Level Vulnerabilities
par: Peng, Zhiyuan, et autres
Publié: (2025)

Prototype-Enhanced Confidence Modeling for Cross-Modal Medical Image-Report Retrieval
par: Gowda, Shreyank N, et autres
Publié: (2025)

Reimagining Reality: A Comprehensive Survey of Video Inpainting Techniques
par: Gowda, Shreyank N, et autres
Publié: (2024)

FATE: A Prompt-Tuning-Based Semi-Supervised Learning Framework for Extremely Limited Labeled Data
par: Liu, Hezhao, et autres
Publié: (2025)

FE-Adapter: Adapting Image-based Emotion Classifiers to Videos
par: Gowda, Shreyank N, et autres
Publié: (2024)

Continual Learning Improves Zero-Shot Action Recognition
par: Gowda, Shreyank N, et autres
Publié: (2024)

Adaptive Data Dropout: Towards Self-Regulated Learning in Deep Neural Networks
par: Gahir, Amar, et autres
Publié: (2026)

CAPT: Class-Aware Prompt Tuning for Federated Long-Tailed Learning with Vision-Language Model
par: Hou, Shihao, et autres
Publié: (2025)

Twin Trigger Generative Networks for Backdoor Attacks against Object Detection
par: Li, Zhiying, et autres
Publié: (2024)

ZeroDiff: Solidified Visual-Semantic Correlation in Zero-Shot Learning
par: Ye, Zihan, et autres
Publié: (2024)

Adversarial Augmentation Training Makes Action Recognition Models More Robust to Realistic Video Distribution Shifts
par: Kim, Kiyoon, et autres
Publié: (2024)

SECOS: Semantic Capture for Rigorous Classification in Open-World Semi-Supervised Learning
par: Liu, Hezhao, et autres
Publié: (2026)

Watt For What: Rethinking Deep Learning's Energy-Performance Relationship
par: Gowda, Shreyank N, et autres
Publié: (2023)

T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak Attacks
par: Liu, Jiayang, et autres
Publié: (2025)

Principles of Visual Tokens for Efficient Video Understanding
par: Hao, Xinyue, et autres
Publié: (2024)

Progressive Data Dropout: An Embarrassingly Simple Approach to Faster Training
par: Sathiyanarayanan, Shriram M, et autres
Publié: (2025)

Bridging the Projection Gap: Overcoming Projection Bias Through Parameterized Distance Learning
par: Zhang, Chong, et autres
Publié: (2023)

Performance is not All You Need: Sustainability Considerations for Algorithms
par: Li, Xiang, et autres
Publié: (2025)

Replace Anyone in Videos
par: Wang, Xiang, et autres
Publié: (2024)

Reading Between the Pixels: An Inscriptive Jailbreak Attack on Text-to-Image Models
par: Ying, Zonghao, et autres
Publié: (2026)

Securing Vision-Language Models with a Robust Encoder Against Jailbreak and Adversarial Attacks
par: Hossain, Md Zarif, et autres
Publié: (2024)

When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Models
par: Hou, Jiacheng, et autres
Publié: (2026)

Learning To See But Forgetting To Follow: Visual Instruction Tuning Makes LLMs More Prone To Jailbreak Attacks
par: Pantazopoulos, Georgios, et autres
Publié: (2024)

MatAnyone 2: Scaling Video Matting via a Learned Quality Evaluator
par: Yang, Peiqing, et autres
Publié: (2025)

Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks
par: Zhou, Andy, et autres
Publié: (2024)

Simulated Ensemble Attack: Transferring Jailbreaks Across Fine-tuned Vision-Language Models
par: Wang, Ruofan, et autres
Publié: (2025)

MatAnyone: Stable Video Matting with Consistent Memory Propagation
par: Yang, Peiqing, et autres
Publié: (2025)

ComposeAnyone: Controllable Layout-to-Human Generation with Decoupled Multimodal Conditions
par: Zhang, Shiyue, et autres
Publié: (2025)

ARtVista: Gateway To Empower Anyone Into Artist
par: Hoang, Trong-Vu, et autres
Publié: (2024)

HTS-Attack: Heuristic Token Search for Jailbreaking Text-to-Image Models
par: Gao, Sensen, et autres
Publié: (2024)

Animate Anyone 2: High-Fidelity Character Image Animation with Environment Affordance
par: Hu, Li, et autres
Publié: (2025)