Imagen de Portada

MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Gu, Tianle, Zhou, Zeyang, Huang, Kexin, Liang, Dandan, Wang, Yixu, Zhao, Haiquan, Yao, Yuanqi, Qiao, Xingge, Wang, Keqing, Yang, Yujiu, Teng, Yan, Qiao, Yu, Wang, Yingchun
Formato:	Preprint
Publicado:	2024
Materias:	Computation and Language Artificial Intelligence Cryptography and Security
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Probing the Robustness of Large Language Models Safety to Latent Perturbations
por: Gu, Tianle, et al.
Publicado: (2025)

HoneypotNet: Backdoor Attacks Against Model Extraction
por: Wang, Yixu, et al.
Publicado: (2025)

Invisible Entropy: Towards Safe and Efficient Low-Entropy LLM Watermarking
por: Gu, Tianle, et al.
Publicado: (2025)

OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMs
por: Wang, Xin, et al.
Publicado: (2026)

StolenLoRA: Exploring LoRA Extraction Attacks via Synthetic Data
por: Wang, Yixu, et al.
Publicado: (2025)

MorphMark: Flexible Adaptive Watermarking for Large Language Models
por: Wang, Zongqi, et al.
Publicado: (2025)

Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs
por: Chen, Yunhao, et al.
Publicado: (2025)

A Mousetrap: Fooling Large Reasoning Models for Jailbreak with Chain of Iterative Chaos
por: Yao, Yang, et al.
Publicado: (2025)

Contrastive Learning for Continuous Touch-Based Authentication
por: Qiao, Mengyu, et al.
Publicado: (2025)

DETOUR: A Practical Backdoor Attack against Object Detection
por: Liu, Dazhuang, et al.
Publicado: (2026)

Agent Safety Alignment via Reinforcement Learning
por: Sha, Zeyang, et al.
Publicado: (2025)

SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models
por: Ying, Zonghao, et al.
Publicado: (2024)

Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift Correction
por: Guo, Jiahe, et al.
Publicado: (2026)

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models
por: Zheng, Baolin, et al.
Publicado: (2025)

ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety
por: Wang, Kun, et al.
Publicado: (2026)

UniMark: Artificial Intelligence Generated Content Identification Toolkit
por: Li, Meilin, et al.
Publicado: (2025)

Graph Learning Across Data Silos
por: Zhang, Xiang, et al.
Publicado: (2023)

ProvX: Generating Counterfactual-Driven Attack Explanations for Provenance-Based Detection
por: Wu, Weiheng, et al.
Publicado: (2025)

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG
por: Li, Junchen, et al.
Publicado: (2026)

SmartInv: Multimodal Learning for Smart Contract Invariant Inference
por: Wang, Sally Junsong, et al.
Publicado: (2024)

The Shadow of Fraud: The Emerging Danger of AI-powered Social Engineering and its Possible Cure
por: Yu, Jingru, et al.
Publicado: (2024)

Evaluating Selective Encryption Against Gradient Inversion Attacks
por: Gu, Jiajun, et al.
Publicado: (2025)

Fine-Grained Privacy Extraction from Retrieval-Augmented Generation Systems via Knowledge Asymmetry Exploitation
por: Chen, Yufei, et al.
Publicado: (2025)

TAPFixer: Automatic Detection and Repair of Home Automation Vulnerabilities based on Negated-property Reasoning
por: Yu, Yinbo, et al.
Publicado: (2024)

Can MLLMs Detect Phishing? A Comprehensive Security Benchmark Suite Focusing on Dynamic Threats and Multimodal Evaluation in Academic Environments
por: Zhou, Jingzhuo
Publicado: (2025)

Black-Box Guardrail Reverse-engineering Attack
por: Yao, Hongwei, et al.
Publicado: (2025)

Slot: Provenance-Driven APT Detection through Graph Reinforcement Learning
por: Qiao, Wei, et al.
Publicado: (2024)

SCAFFOLD-CEGIS: Preventing Latent Security Degradation in LLM-Driven Iterative Code Refinement
por: Chen, Yi, et al.
Publicado: (2026)

GhostEI-Bench: Do Mobile Agents Resilience to Environmental Injection in Dynamic On-Device Environments?
por: Chen, Chiyu, et al.
Publicado: (2025)

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms
por: He, Sinan, et al.
Publicado: (2025)

On the Necessity of Pre-agreed Secrets for Thwarting Last-minute Coercion: Vulnerabilities and Lessons From the Loki E-voting Protocol
por: Qiao, Jingxin, et al.
Publicado: (2026)

VeilAudit: Breaking the Deadlock Between Privacy and Accountability Across Blockchains
por: Qiao, Minhao, et al.
Publicado: (2025)

Building Intelligence Identification System via Large Language Model Watermarking: A Survey and Beyond
por: Wang, Xuhong, et al.
Publicado: (2024)

HarmChip: Evaluating Hardware Security Centric LLM Safety via Jailbreak Benchmarking
por: Wang, Zeng, et al.
Publicado: (2026)

PraxiMLP: A Threshold-based Framework for Efficient Three-Party MLP with Practical Security
por: Tao, Tianle, et al.
Publicado: (2025)

Behavioral Authentication for Security and Safety
por: Wang, Cheng, et al.
Publicado: (2023)

Prompt Stealing Attacks Against Large Language Models
por: Sha, Zeyang, et al.
Publicado: (2024)

Demystifying Progressive Web Application Permission Systems
por: Wang, Mengxiao, et al.
Publicado: (2025)

GuardianPWA: Enhancing Security Throughout the Progressive Web App Installation Lifecycle
por: Wang, Mengxiao, et al.
Publicado: (2025)

MEOW: MEMOry Supervised LLM Unlearning Via Inverted Facts
por: Gu, Tianle, et al.
Publicado: (2024)