Imagen de Portada

ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Kun, Qian, Cheng, Yu, Miao, Peng, Lilan, Lin, Liang, Zhang, Jiaming, Zhang, Tianyu, Cheng, Yu, Wang, Yang
Formato:	Preprint
Publicado:	2026
Materias:	Cryptography and Security Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

The Security Threat of Compressed Projectors in Large Vision-Language Models
por: Zhang, Yudong, et al.
Publicado: (2025)

Dataset Ownership in the Era of Large Language Models
por: Li, Kun, et al.
Publicado: (2025)

G-Safeguard: A Topology-Guided Security Lens and Treatment on LLM-based Multi-agent Systems
por: Wang, Shilong, et al.
Publicado: (2025)

AutoIoT: Automated IoT Platform Using Large Language Models
por: Cheng, Ye, et al.
Publicado: (2024)

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit
por: He, Zeqing, et al.
Publicado: (2024)

On the Role of Attention Heads in Large Language Model Safety
por: Zhou, Zhenhong, et al.
Publicado: (2024)

Psyzkaller: Learning from Historical and On-the-Fly Execution Data for Smarter Seed Generation in OS kernel Fuzzing
por: Liu, Boyu, et al.
Publicado: (2025)

Unveiling the Bandwidth Nightmare: CDN Compression Format Conversion Attacks
por: Lin, Ziyu, et al.
Publicado: (2024)

Profiling for Pennies: Unveiling the Privacy Iceberg of LLM Agents
por: Chen, Jiahao, et al.
Publicado: (2026)

A Trajectory-Based Safety Audit of Clawdbot (OpenClaw)
por: Chen, Tianyu, et al.
Publicado: (2026)

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

Optimizing seed inputs in fuzzing with machine learning
por: Cheng, Liang, et al.
Publicado: (2019)

Unveiling Security Weaknesses in Autonomous Driving Systems: An In-Depth Empirical Study
por: Cheng, Wenyuan, et al.
Publicado: (2025)

Privacy-Preserving Socialized Recommendation based on Multi-View Clustering in a Cloud Environment
por: Guo, Cheng, et al.
Publicado: (2025)

Toward a Principled Framework for Agent Safety Measurement
por: Lin, Shuyi, et al.
Publicado: (2026)

Automatic Generation of a Cryptography Misuse Taxonomy Using Large Language Models
por: Zhang, Yang, et al.
Publicado: (2025)

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

BADTV: Unveiling Backdoor Threats in Third-Party Task Vectors
por: Hsu, Chia-Yi, et al.
Publicado: (2025)

CompVPD: Iteratively Identifying Vulnerability Patches Based on Human Validation Results with a Precise Context
por: Chen, Tianyu, et al.
Publicado: (2023)

MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models
por: Gu, Tianle, et al.
Publicado: (2024)

Feature-Oriented IoT Malware Analysis: Extraction, Classification, and Future Directions
por: Qian, Zhuoyun, et al.
Publicado: (2025)

Starfish: Rebalancing Multi-Party Off-Chain Payment Channels
por: Xu, Minghui, et al.
Publicado: (2025)

LIFT: Automating Symbolic Execution Optimization with Large Language Models for AI Networks
por: Wang, Ruoxi, et al.
Publicado: (2025)

NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Models
por: Zhang, Chuhan, et al.
Publicado: (2025)

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives
por: Wang, Nan, et al.
Publicado: (2025)

"MCP Does Not Stand for Misuse Cryptography Protocol": Uncovering Cryptographic Misuse in Model Context Protocol at Scale
por: Yan, Biwei, et al.
Publicado: (2025)

AutoJailbreak: Exploring Jailbreak Attacks and Defenses through a Dependency Lens
por: Lu, Lin, et al.
Publicado: (2024)

VENOMREC: Cross-Modal Interactive Poisoning for Targeted Promotion in Multimodal LLM Recommender Systems
por: Guan, Guowei, et al.
Publicado: (2026)

Beyond Jailbreak: Unveiling Risks in LLM Applications Arising from Blurred Capability Boundaries
por: Zhang, Yunyi, et al.
Publicado: (2025)

Unveiling Malware Patterns: A Self-analysis Perspective
por: Zhong, Fangtian, et al.
Publicado: (2025)

Supply Chain Network Security Investment Strategies Based on Nonlinear Budget Constraints: The Moderating Roles of Market Share and Attack Risk
por: Cheng, Jiajie, et al.
Publicado: (2025)

MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
por: Xu, Chejian, et al.
Publicado: (2025)

On Protecting the Data Privacy of Large Language Models (LLMs): A Survey
por: Yan, Biwei, et al.
Publicado: (2024)

EGNInfoLeaker: Unveiling the Risks of Public Key Reuse and User Identity Leakage in Blockchain
por: Li, Chenyu, et al.
Publicado: (2025)

Safeguarding Multimodal Knowledge Copyright in the RAG-as-a-Service Environment
por: Chen, Tianyu, et al.
Publicado: (2025)

VulLibGen: Generating Names of Vulnerability-Affected Packages via a Large Language Model
por: Chen, Tianyu, et al.
Publicado: (2023)

UpSafe$^\circ$C: Upcycling for Controllable Safety in Large Language Models
por: Sun, Yuhao, et al.
Publicado: (2025)

Unveiling the Unseen: Exploring Whitebox Membership Inference through the Lens of Explainability
por: Li, Chenxi, et al.
Publicado: (2024)

A Model for Assessing Network Asset Vulnerability Using QPSO-LightGBM
por: Li, Xinyu, et al.
Publicado: (2024)

SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs
por: Xia, Hongfei, et al.
Publicado: (2025)