Image de couverture de livre

Watch Out Your Album! On the Inadvertent Privacy Memorization in Multi-Modal Large Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ju, Tianjie, Hua, Yi, Fei, Hao, Shao, Zhenyu, Zheng, Yubin, Zhao, Haodong, Lee, Mong-Li, Hsu, Wynne, Zhang, Zhuosheng, Liu, Gongshen
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Probing then Editing Response Personality of Large Language Models
par: Ju, Tianjie, et autres
Publié: (2025)

On the Adaptive Psychological Persuasion of Large Language Models
par: Ju, Tianjie, et autres
Publié: (2025)

When Disagreements Elicit Robustness: Investigating Self-Repair Capabilities under LLM Multi-Agent Disagreements
par: Ju, Tianjie, et autres
Publié: (2025)

Investigating Multi-Hop Factual Shortcuts in Knowledge Editing of Large Language Models
par: Ju, Tianjie, et autres
Publié: (2024)

Disagreements in Reasoning: How a Model's Thinking Process Dictates Persuasion in Multi-Agent Systems
par: Zhao, Haodong, et autres
Publié: (2025)

SNIFFER: Multimodal Large Language Model for Explainable Out-of-Context Misinformation Detection
par: Qi, Peng, et autres
Publié: (2024)

Smoothing Grounding and Reasoning for MLLM-Powered GUI Agents with Query-Oriented Pivot Tasks
par: Wu, Zongru, et autres
Publié: (2025)

Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection
par: Yan, Zehong, et autres
Publié: (2025)

TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models
par: Cheng, Pengzhou, et autres
Publié: (2024)

Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI Agents
par: Cheng, Pengzhou, et autres
Publié: (2025)

NSmark: Null Space Based Black-box Watermarking Defense Framework for Language Models
par: Zhao, Haodong, et autres
Publié: (2024)

Flooding Spread of Manipulated Knowledge in LLM-Based Multi-Agent Communities
par: Ju, Tianjie, et autres
Publié: (2024)

Thinking in a Crowd: How Auxiliary Information Shapes LLM Reasoning
par: Zhao, Haodong, et autres
Publié: (2025)

How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study
par: Ju, Tianjie, et autres
Publié: (2024)

Multi-Part Object Representations via Graph Structures and Co-Part Discovery
par: Foo, Alex, et autres
Publié: (2025)

LEAF-Mamba: Local Emphatic and Adaptive Fusion State Space Model for RGB-D Salient Object Detection
par: Wu, Lanhu, et autres
Publié: (2025)

ChronoFact: Timeline-based Temporal Fact Verification
par: Barik, Anab Maulana, et autres
Publié: (2024)

Faithful Logical Reasoning via Symbolic Chain-of-Thought
par: Xu, Jundong, et autres
Publié: (2024)

See, Think, Act: Teaching Multimodal Agents to Effectively Interact with GUI by Identifying Toggles
par: Wu, Zongru, et autres
Publié: (2025)

On the Robustness of Editing Large Language Models
par: Ma, Xinbei, et autres
Publié: (2024)

Training High-Level Schedulers with Execution-Feedback Reinforcement Learning for Long-Horizon GUI Automation
par: Deng, Zehao, et autres
Publié: (2025)

Transferring Backdoors between Large Language Models by Knowledge Distillation
par: Cheng, Pengzhou, et autres
Publié: (2024)

FormFactory: An Interactive Benchmarking Suite for Multimodal Form-Filling Agents
par: Li, Bobo, et autres
Publié: (2025)

Do Latent Tokens Think? A Causal and Adversarial Analysis of Chain-of-Continuous-Thought
par: Zhang, Yuyi, et autres
Publié: (2025)

TRUST-VL: An Explainable News Assistant for General Multimodal Misinformation Detection
par: Yan, Zehong, et autres
Publié: (2025)

Orthogonal Spatial-temporal Distributional Transfer for 4D Generation
par: Liu, Wei, et autres
Publié: (2026)

Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining
par: Wu, Zongru, et autres
Publié: (2024)

From Personas to Talks: Revisiting the Impact of Personas on LLM-Synthesized Emotional Support Conversations
par: Wu, Shenghan, et autres
Publié: (2025)

Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment
par: Li, Bobo, et autres
Publié: (2026)

Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space
par: Wu, Zongru, et autres
Publié: (2024)

Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition
par: Fei, Hao, et autres
Publié: (2024)

Multi-Modal Continual Learning via Cross-Modality Adapters and Representation Alignment with Knowledge Preservation
par: Chee, Evelyn, et autres
Publié: (2025)

Watch Out for Your Guidance on Generation! Exploring Conditional Backdoor Attacks against Large Language Models
par: He, Jiaming, et autres
Publié: (2024)

Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Grounding
par: Luo, Meng, et autres
Publié: (2025)

Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
par: Yang, Wenkai, et autres
Publié: (2024)

LogicReward: Incentivizing LLM Reasoning via Step-Wise Logical Supervision
par: Xu, Jundong, et autres
Publié: (2025)

Aristotle: Mastering Logical Reasoning with A Logic-Complete Decompose-Search-Resolve Framework
par: Xu, Jundong, et autres
Publié: (2024)

Federated Semi-supervised Learning for Medical Image Segmentation with intra-client and inter-client Consistency
par: Zheng, Yubin, et autres
Publié: (2024)

Cross-Domain Feature Augmentation for Domain Generalization
par: Liu, Yingnan, et autres
Publié: (2024)

PanoSent: A Panoptic Sextuple Extraction Benchmark for Multimodal Conversational Aspect-based Sentiment Analysis
par: Luo, Meng, et autres
Publié: (2024)