Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hao, Shuyang, Hooi, Bryan, Liu, Jun, Chang, Kai-Wei, Huang, Zi, Cai, Yujun
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Making Every Step Effective: Jailbreaking Large Vision-Language Models Through Hierarchical KV Equalization
by: Hao, Shuyang, et al.
Published: (2025)

Tit-for-Tat: Safeguarding Large Vision-Language Models Against Jailbreak Attacks via Adversarial Defense
by: Hao, Shuyang, et al.
Published: (2025)

Text Speaks Louder than Vision: ASCII Art Reveals Textual Biases in Vision-Language Models
by: Wang, Zhaochen, et al.
Published: (2025)

How does Watermarking Affect Visual Language Models in Document Understanding?
by: Xu, Chunxue, et al.
Published: (2025)

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

Seeing is Believing: Mitigating Hallucination in Large Vision-Language Models via CLIP-Guided Decoding
by: Deng, Ailin, et al.
Published: (2024)

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

Cure or Poison? Embedding Instructions Visually Alters Hallucination in Vision-Language Models
by: Wang, Zhaochen, et al.
Published: (2025)

MAA: Meticulous Adversarial Attack against Vision-Language Pre-trained Models
by: Zhang, Peng-Fei, et al.
Published: (2025)

Words or Vision: Do Vision-Language Models Have Blind Faith in Text?
by: Deng, Ailin, et al.
Published: (2025)

Vision Language Models Map Logos to Text via Semantic Entanglement in the Visual Projector
by: Li, Sifan, et al.
Published: (2025)

Lost in Edits? A $λ$-Compass for AIGC Provenance
by: You, Wenhao, et al.
Published: (2025)

Jailbreaking Vision-Language Models Through the Visual Modality
by: Azulay, Aharon, et al.
Published: (2026)

Revealing Physical-World Semantic Vulnerabilities: Universal Adversarial Patches for Infrared Vision-Language Models
by: Hu, Chengyin, et al.
Published: (2026)

GRPO-TTA: Test-Time Visual Tuning for Vision-Language Models via GRPO-Driven Reinforcement Learning
by: Li, Yujun, et al.
Published: (2026)

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

FrameMind: Frame-Interleaved Video Reasoning via Reinforcement Learning
by: Ge, Haonan, et al.
Published: (2025)

Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models
by: Li, Yifan, et al.
Published: (2024)

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

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

Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-Language Models
by: Wu, Jiaying, et al.
Published: (2025)

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

When Text and Images Don't Mix: Bias-Correcting Language-Image Similarity Scores for Anomaly Detection
by: Goodge, Adam, et al.
Published: (2024)

Universal Adversarial Perturbations for Vision-Language Pre-trained Models
by: Zhang, Peng-Fei, et al.
Published: (2024)

Visual Adversarial Attack on Vision-Language Models for Autonomous Driving
by: Zhang, Tianyuan, et al.
Published: (2024)

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

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

SemVink: Advancing VLMs' Semantic Understanding of Optical Illusions via Visual Global Thinking
by: Li, Sifan, et al.
Published: (2025)

Dataset Distillation via Vision-Language Category Prototype
by: Zou, Yawen, et al.
Published: (2025)

VRSA: Jailbreaking Multimodal Large Language Models through Visual Reasoning Sequential Attack
by: Zhao, Shiji, et al.
Published: (2025)

Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning
by: Lu, Fan, et al.
Published: (2024)

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

SegDebias: Test-Time Bias Mitigation for ViT-Based CLIP via Segmentation
by: Wu, Fangyu, et al.
Published: (2025)

Spatio-Temporal Foundation Models: Vision, Challenges, and Opportunities
by: Goodge, Adam, et al.
Published: (2025)

PruneVid: Visual Token Pruning for Efficient Video Large Language Models
by: Huang, Xiaohu, et al.
Published: (2024)

LLMs are Good Action Recognizers
by: Qu, Haoxuan, et al.
Published: (2024)

TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification
by: Liu, Qinying, et al.
Published: (2023)

MMT-ARD: Multimodal Multi-Teacher Adversarial Distillation for Robust Vision-Language Models
by: Li, Yuqi, et al.
Published: (2025)

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

When Lighting Deceives: Exposing Vision-Language Models' Illumination Vulnerability Through Illumination Transformation Attack
by: Liu, Hanqing, et al.
Published: (2025)