Cover Image

Towards Effective MLLM Jailbreaking Through Balanced On-Topicness and OOD-Intensity

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Zuoou, Zhang, Weitong, Wang, Jingyuan, Zhang, Shuyuan, Bai, Wenjia, Kainz, Bernhard, Qiao, Mengyun
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Wasserstein Equilibrium Decoding for Reliable Medical Visual Question Answering
by: Hagen, Luca, et al.
Published: (2026)

Graph Conditioned Diffusion for Controllable Histopathology Image Generation
by: Cechnicka, Sarah, et al.
Published: (2025)

Hard to Read, Easy to Jailbreak: How Visual Degradation Bypasses MLLM Safety Alignment
by: Song, Zhixue, et al.
Published: (2026)

Resource-efficient Medical Image Analysis with Self-adapting Forward-Forward Networks
by: Müller, Johanna P., et al.
Published: (2024)

Uncovering Hidden Subspaces in Video Diffusion Models Using Re-Identification
by: Dombrowski, Mischa, et al.
Published: (2024)

Multi-Agent Reasoning for Cardiovascular Imaging Phenotype Analysis
by: Zhang, Weitong, et al.
Published: (2025)

ShapeCraft: LLM Agents for Structured, Textured and Interactive 3D Modeling
by: Zhang, Shuyuan, et al.
Published: (2025)

Retrieval-Augmented Prompt for OOD Detection
by: Han, Ruisong, et al.
Published: (2025)

Geometry-Aware Uncertainty Coresets for Robust Visual In-Context Learning in Histopathology
by: Erick, Franciskus Xaverius, et al.
Published: (2026)

CTFlow: Video-Inspired Latent Flow Matching for 3D CT Synthesis
by: Wang, Jiayi, et al.
Published: (2025)

Data-Efficient Generation for Dataset Distillation
by: Li, Zhe, et al.
Published: (2024)

Proto-OOD: Enhancing OOD Object Detection with Prototype Feature Similarity
by: Chen, Junkun, et al.
Published: (2024)

BalCapRL: A Balanced Framework for RL-Based MLLM Image Captioning
by: Ye, Shaokai, et al.
Published: (2026)

GTMA: Dynamic Representation Optimization for OOD Vision-Language Models
by: Zhang, Jensen, et al.
Published: (2025)

No Need For Real Anomaly: MLLM Empowered Zero-Shot Video Anomaly Detection
by: Dai, Zunkai, et al.
Published: (2026)

LIME: Less Is More for MLLM Evaluation
by: Zhu, King, et al.
Published: (2024)

Image Generation Diversity Issues and How to Tame Them
by: Dombrowski, Mischa, et al.
Published: (2024)

Free-Lunch Long Video Generation via Layer-Adaptive O.O.D Correction
by: Tian, Jiahao, et al.
Published: (2026)

IPCV: Information-Preserving Compression for MLLM Visual Encoders
by: Chen, Yuan, et al.
Published: (2025)

Wasserstein-Aligned Localisation for VLM-Based Distributional OOD Detection in Medical Imaging
by: Kainz, Bernhard, et al.
Published: (2026)

Leveraging MLLM Embeddings and Attribute Smoothing for Compositional Zero-Shot Learning
by: Yan, Xudong, et al.
Published: (2024)

A Bayesian Approach to OOD Robustness in Image Classification
by: Kaushik, Prakhar, et al.
Published: (2024)

MDF-MLLM: Deep Fusion Through Cross-Modal Feature Alignment for Contextually Aware Fundoscopic Image Classification
by: Jordan, Jason, et al.
Published: (2025)

MIDAS: Multi-Image Dispersion and Semantic Reconstruction for Jailbreaking MLLMs
by: Liu, Yilian, et al.
Published: (2026)

UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning
by: Gu, Tiancheng, et al.
Published: (2025)

AIC MLLM: Autonomous Interactive Correction MLLM for Robust Robotic Manipulation
by: Xiong, Chuyan, et al.
Published: (2024)

AdaNeg: Adaptive Negative Proxy Guided OOD Detection with Vision-Language Models
by: Zhang, Yabin, et al.
Published: (2024)

Toward High-Fidelity Visual Reconstruction: From EEG-Based Conditioned Generation to Joint-Modal Guided Rebuilding
by: Gong, Zhijian, et al.
Published: (2026)

HEIE: MLLM-Based Hierarchical Explainable AIGC Image Implausibility Evaluator
by: Yang, Fan, et al.
Published: (2024)

Dog-IQA: Standard-guided Zero-shot MLLM for Mix-grained Image Quality Assessment
by: Liu, Kai, et al.
Published: (2024)

MPerS: Dynamic MLLM MixExperts Perception-Guided Remote Sensing Scene Segmentation
by: Wang, Ziyi, et al.
Published: (2026)

Towards Balanced Multi-Modal Learning in 3D Human Pose Estimation
by: Qi, Mengshi, et al.
Published: (2025)

Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD Generalization
by: Zang, Yuhang, et al.
Published: (2024)

Leveraging Text-Driven Semantic Variation for Robust OOD Segmentation
by: Song, Seungheon, et al.
Published: (2025)

SMART: Shot-Aware Multimodal Video Moment Retrieval with Audio-Enhanced MLLM
by: Yu, An, et al.
Published: (2025)

SafeEditor: Unified MLLM for Efficient Post-hoc T2I Safety Editing
by: Zhang, Ruiyang, et al.
Published: (2025)

Understanding and Defending VLM Jailbreaks via Jailbreak-Related Representation Shift
by: Wei, Zhihua, et al.
Published: (2026)

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

MLLM-based Textual Explanations for Face Comparison
by: Sony, Redwan, et al.
Published: (2026)

From Inheritance to Saturation: Disentangling the Evolution of Visual Redundancy for Architecture-Aware MLLM Inference Acceleration
by: Shi, Jiaqi, et al.
Published: (2026)