Cover Image

Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cui, Chenhang, Deng, Gelei, Zhang, An, Zheng, Jingnan, Li, Yicong, Gao, Lianli, Zhang, Tianwei, Chua, Tat-Seng
Format:	Preprint
Published:	2024
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment
by: Cui, Chenhang, et al.
Published: (2024)

Do LLMs and VLMs Share Neurons for Inference? Evidence and Mechanisms of Cross-Modal Transfer
by: Cui, Chenhang, et al.
Published: (2026)

Self-Guard: Defending Large Reasoning Models via enhanced self-reflection
by: Zheng, Jingnan, et al.
Published: (2026)

RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguards
by: Zheng, Jingnan, et al.
Published: (2025)

Transport and Merge: Cross-Architecture Merging for Large Language Models
by: Cui, Chenhang, et al.
Published: (2026)

Unsafe Impedance: Safe Languages and Safe by Design Software
by: Barney, Lee, et al.
Published: (2024)

Safe Vision-Language Models via Unsafe Weights Manipulation
by: D'Incà, Moreno, et al.
Published: (2025)

Risky-Bench: Probing Agentic Safety Risks under Real-World Deployment
by: Zheng, Jingnan, et al.
Published: (2026)

SafeNeuron: Neuron-Level Safety Alignment for Large Language Models
by: Wang, Zhaoxin, et al.
Published: (2026)

Safe Semantics, Unsafe Interpretations: Tackling Implicit Reasoning Safety in Large Vision-Language Models
by: Cai, Wei, et al.
Published: (2025)

SafeMLRM: Demystifying Safety in Multi-modal Large Reasoning Models
by: Fang, Junfeng, et al.
Published: (2025)

No Safe Dose: How Training Data Drives Unsafe Image Generation
by: Friedrich, Felix, et al.
Published: (2026)

ClawSafety: "Safe" LLMs, Unsafe Agents
by: Wei, Bowen, et al.
Published: (2026)

SafePTR: Token-Level Jailbreak Defense in Multimodal LLMs via Prune-then-Restore Mechanism
by: Chen, Beitao, et al.
Published: (2025)

SafeFFI: Efficient Sanitization at the Boundary Between Safe and Unsafe Code in Rust and Mixed-Language Applications
by: Braunsdorf, Oliver, et al.
Published: (2025)

Unsafe2Safe: Controllable Image Anonymization for Downstream Utility
by: Dinh, Mih, et al.
Published: (2026)

Safe Inputs but Unsafe Output: Benchmarking Cross-modality Safety Alignment of Large Vision-Language Model
by: Wang, Siyin, et al.
Published: (2024)

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

Can I Trust Your Answer? Visually Grounded Video Question Answering
by: Xiao, Junbin, et al.
Published: (2023)

Disentangling Safe and Unsafe Corruptions via Anisotropy and Locality
by: Muthukumar, Ramchandran, et al.
Published: (2025)

Lingua-SafetyBench: A Benchmark for Safety Evaluation of Multilingual Vision-Language Models
by: Shi, Enyi, et al.
Published: (2026)

Understanding Long Videos via LLM-Powered Entity Relation Graphs
by: Chu, Meng, et al.
Published: (2025)

SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signals
by: Han, Peixuan, et al.
Published: (2025)

Abductive Ego-View Accident Video Understanding for Safe Driving Perception
by: Fang, Jianwu, et al.
Published: (2024)

Safe-Support Q-Learning: Learning without Unsafe Exploration
by: Lim, Yeeun, et al.
Published: (2026)

MSWasm: Soundly Enforcing Memory-Safe Execution of Unsafe Code
by: Michael, Alexandra E., et al.
Published: (2022)

Towards Safe AI Clinicians: A Comprehensive Study on Large Language Model Jailbreaking in Healthcare
by: Zhang, Hang, et al.
Published: (2025)

Image-Based Geolocation Using Large Vision-Language Models
by: Liu, Yi, et al.
Published: (2024)

SafeCFG: Controlling Harmful Features with Dynamic Safe Guidance for Safe Generation
by: Pan, Jiadong, et al.
Published: (2024)

Safe2Harm: Semantic Isomorphism Attacks for Jailbreaking Large Language Models
by: Yang, Fan
Published: (2025)

SafeSteer: Adaptive Subspace Steering for Efficient Jailbreak Defense in Vision-Language Models
by: Zeng, Xiyu, et al.
Published: (2025)

MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots
by: Deng, Gelei, et al.
Published: (2023)

To Be (Safe), or Not to Be (Safe)? A Daily Exploration of Why and When Gig Workers Stay Safe Under Customer Demands
by: Jinghao Zhang, et al.
Published: (2025)

Enhancing Model Defense Against Jailbreaks with Proactive Safety Reasoning
by: Yang, Xianglin, et al.
Published: (2025)

SafeLawBench: Towards Safe Alignment of Large Language Models
by: Cao, Chuxue, et al.
Published: (2025)

Pandora: Jailbreak GPTs by Retrieval Augmented Generation Poisoning
by: Deng, Gelei, et al.
Published: (2024)

Learning Natural Language Constraints for Safe Reinforcement Learning of Language Agents
by: Chua, Jaymari, et al.
Published: (2025)

SafeBehavior: Simulating Human-Like Multistage Reasoning to Mitigate Jailbreak Attacks in Large Language Models
by: Zhao, Qinjian, et al.
Published: (2025)

SafeGuider: Robust and Practical Content Safety Control for Text-to-Image Models
by: Qi, Peigui, et al.
Published: (2025)

Revisiting Safe Exploration in Safe Reinforcement learning
by: Eckel, David, et al.
Published: (2024)