Imagen de Portada

Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Patil, Vaidehi, Sung, Yi-Lin, Hase, Peter, Peng, Jie, Chen, Tianlong, Bansal, Mohit
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Hierarchy-Aware Multimodal Unlearning for Medical AI
por: Wu, Fengli, et al.
Publicado: (2025)

UPCORE: Utility-Preserving Coreset Selection for Balanced Unlearning
por: Patil, Vaidehi, et al.
Publicado: (2025)

ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models
por: Sung, Yi-Lin, et al.
Publicado: (2023)

Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents
por: Lin, Han, et al.
Publicado: (2025)

RotBench: Evaluating Multimodal Large Language Models on Identifying Image Rotation
por: Niu, Tianyi, et al.
Publicado: (2025)

CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion
por: Yu, Shoubin, et al.
Publicado: (2024)

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey
por: Liu, Xuannan, et al.
Publicado: (2024)

SELMA: Learning and Merging Skill-Specific Text-to-Image Experts with Auto-Generated Data
por: Li, Jialu, et al.
Publicado: (2024)

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs
por: Nguyen, Duy, et al.
Publicado: (2025)

Training-free Guidance in Text-to-Video Generation via Multimodal Planning and Structured Noise Initialization
por: Li, Jialu, et al.
Publicado: (2025)

Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generation
por: Kim, Minkyoung, et al.
Publicado: (2024)

DAM: Dynamic Adapter Merging for Continual Video QA Learning
por: Cheng, Feng, et al.
Publicado: (2024)

MERRIN: A Benchmark for Multimodal Evidence Retrieval and Reasoning in Noisy Web Environments
por: Wang, Han, et al.
Publicado: (2026)

SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation
por: Yoon, Jaehong, et al.
Publicado: (2024)

MEXA: Towards General Multimodal Reasoning with Dynamic Multi-Expert Aggregation
por: Yu, Shoubin, et al.
Publicado: (2025)

CLaMR: Contextualized Late-Interaction for Multimodal Content Retrieval
por: Wan, David, et al.
Publicado: (2025)

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting
por: Pothiraj, Atin, et al.
Publicado: (2025)

The Sum Leaks More Than Its Parts: Compositional Privacy Risks and Mitigations in Multi-Agent Collaboration
por: Patil, Vaidehi, et al.
Publicado: (2025)

Multimodal Fact-Level Attribution for Verifiable Reasoning
por: Wan, David, et al.
Publicado: (2026)

Knowledge-Aware Reasoning over Multimodal Semi-structured Tables
por: Mathur, Suyash Vardhan, et al.
Publicado: (2024)

MIA-Bench: Towards Better Instruction Following Evaluation of Multimodal LLMs
por: Qian, Yusu, et al.
Publicado: (2024)

RACCooN: A Versatile Instructional Video Editing Framework with Auto-Generated Narratives
por: Yoon, Jaehong, et al.
Publicado: (2024)

Iteratively Prompting Multimodal LLMs to Reproduce Natural and AI-Generated Images
por: Naseh, Ali, et al.
Publicado: (2024)

IV-Bench: A Benchmark for Image-Grounded Video Perception and Reasoning in Multimodal LLMs
por: Ma, David, et al.
Publicado: (2025)

ShredBench: Evaluating the Semantic Reasoning Capabilities of Multimodal LLMs in Document Reconstruction
por: Guo, Zichun, et al.
Publicado: (2026)

EmbodiedEval: Evaluate Multimodal LLMs as Embodied Agents
por: Cheng, Zhili, et al.
Publicado: (2025)

DreamRunner: Fine-Grained Compositional Story-to-Video Generation with Retrieval-Augmented Motion Adaptation
por: Wang, Zun, et al.
Publicado: (2024)

GSR-BENCH: A Benchmark for Grounded Spatial Reasoning Evaluation via Multimodal LLMs
por: Rajabi, Navid, et al.
Publicado: (2024)

GAOKAO-MM: A Chinese Human-Level Benchmark for Multimodal Models Evaluation
por: Zong, Yi, et al.
Publicado: (2024)

DiagrammerGPT: Generating Open-Domain, Open-Platform Diagrams via LLM Planning
por: Zala, Abhay, et al.
Publicado: (2023)

VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning
por: Lin, Han, et al.
Publicado: (2023)

UNIKIE-BENCH: Benchmarking Large Multimodal Models for Key Information Extraction in Visual Documents
por: Ji, Yifan, et al.
Publicado: (2026)

Self-Correcting Text-to-Video Generation with Misalignment Detection and Localized Refinement
por: Lee, Daeun, et al.
Publicado: (2024)

VLN-Video: Utilizing Driving Videos for Outdoor Vision-and-Language Navigation
por: Li, Jialu, et al.
Publicado: (2024)

Video-Skill-CoT: Skill-based Chain-of-Thoughts for Domain-Adaptive Video Reasoning
por: Lee, Daeun, et al.
Publicado: (2025)

Diagnostic Benchmark and Iterative Inpainting for Layout-Guided Image Generation
por: Cho, Jaemin, et al.
Publicado: (2023)

Evaluating Linguistic Capabilities of Multimodal LLMs in the Lens of Few-Shot Learning
por: Dogan, Mustafa, et al.
Publicado: (2024)

DART: Leveraging Multi-Agent Disagreement for Tool Recruitment in Multimodal Reasoning
por: Sivakumaran, Nithin, et al.
Publicado: (2025)

Beyond Superficial Unlearning: Sharpness-Aware Robust Erasure of Hallucinations in Multimodal LLMs
por: Fang, Xianya, et al.
Publicado: (2026)

MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMs
por: Fu, Chaoyou, et al.
Publicado: (2024)