Cover Image

Mind the Third Eye! Benchmarking Privacy Awareness in MLLM-powered Smartphone Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lin, Zhixin, Li, Jungang, Pan, Shidong, Shi, Yibo, Yao, Yue, Xu, Dongliang
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Mobile GUI Agent Privacy Personalization with Trajectory Induced Preference Optimization
by: Lin, Zhixin, et al.
Published: (2026)

Technical Report for ICML 2024 TiFA Workshop MLLM Attack Challenge: Suffix Injection and Projected Gradient Descent Can Easily Fool An MLLM
by: Guo, Yangyang, et al.
Published: (2024)

Understanding User Privacy Perceptions of GenAI Smartphones
by: Jin, Ran, et al.
Published: (2026)

MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance
by: Pi, Renjie, et al.
Published: (2024)

Backdoor Cleaning without External Guidance in MLLM Fine-tuning
by: Rong, Xuankun, et al.
Published: (2025)

TwoHamsters: Benchmarking Multi-Concept Compositional Unsafety in Text-to-Image Models
by: Zhang, Chaoshuo, et al.
Published: (2026)

SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents
by: Ying, Zonghao, et al.
Published: (2025)

MultiPriv: Benchmarking Individual-Level Privacy Reasoning in Vision-Language Models
by: Sun, Xiongtao, et al.
Published: (2025)

PrivHAR-Bench: A Graduated Privacy Benchmark Dataset for Video-Based Action Recognition
by: Ansari, Samar
Published: (2026)

QualitEye: Public and Privacy-preserving Gaze Data Quality Verification
by: Elfares, Mayar, et al.
Published: (2025)

BodhiPromptShield: Pre-Inference Prompt Mediation for Suppressing Privacy Propagation in LLM/VLM Agents
by: Ma, Bo, et al.
Published: (2026)

Pura: An Efficient Privacy-Preserving Solution for Face Recognition
by: Xu, Guotao, et al.
Published: (2025)

GUIGuard-Bench: Toward a General Evaluation for Privacy-Preserving GUI Agents
by: Wang, Yanxi, et al.
Published: (2026)

ComPrivDet: Efficient Privacy Object Detection in Compressed Domains Through Inference Reuse
by: Yao, Yunhao, et al.
Published: (2026)

Relax DARTS: Relaxing the Constraints of Differentiable Architecture Search for Eye Movement Recognition
by: Zhu, Hongyu, et al.
Published: (2024)

Shaking the Fake: Detecting Deepfake Videos in Real Time via Active Probes
by: Xie, Zhixin, et al.
Published: (2024)

Video Signature: Implicit Watermarking for Video Diffusion Models
by: Huang, Yu, et al.
Published: (2025)

Neighbor-Aware Localized Concept Erasure in Text-to-Image Diffusion Models
by: Shi, Zhuan, et al.
Published: (2026)

FedFG: Privacy-Preserving and Robust Federated Learning via Flow-Matching Generation
by: Wang, Ruiyang, et al.
Published: (2026)

Privacy-Aware Federated nnU-Net for ECG Page Digitization
by: Nemati, Nader
Published: (2025)

Six-CD: Benchmarking Concept Removals for Benign Text-to-image Diffusion Models
by: Ren, Jie, et al.
Published: (2024)

Privacy-Preserving Iris Recognition: Performance Challenges and Outlook
by: Karakosta, Christina, et al.
Published: (2026)

Privacy-preserving Preselection for Face Identification Based on Packing
by: Xin, Rundong, et al.
Published: (2025)

Privacy-Preserving Semantic Segmentation without Key Management
by: Hirose, Mare, et al.
Published: (2026)

Temporal Persistence and Intercorrelation of Embeddings Learned by an End-to-End Deep Learning Eye Movement-driven Biometrics Pipeline
by: Raju, Mehedi Hasan, et al.
Published: (2024)

Revisiting the Privacy Risks of Split Inference: A GAN-Based Data Reconstruction Attack via Progressive Feature Optimization
by: Qiu, Yixiang, et al.
Published: (2025)

SAP-DIFF: Semantic Adversarial Patch Generation for Black-Box Face Recognition Models via Diffusion Models
by: Wang, Mingsi, et al.
Published: (2025)

UnlearnShield: Shielding Forgotten Privacy against Unlearning Inversion
by: Xue, Lulu, et al.
Published: (2026)

Enhancing Privacy in Face Analytics Using Fully Homomorphic Encryption
by: Yalavarthi, Bharat, et al.
Published: (2024)

Controllable Adversarial Makeup for Privacy via Text-Guided Diffusion
by: Kwon, Youngjin, et al.
Published: (2025)

Multimodal Privacy-Preserving Entity Resolution with Fully Homomorphic Encryption
by: Roy, Susim, et al.
Published: (2026)

Deep Learning with Data Privacy via Residual Perturbation
by: Tao, Wenqi, et al.
Published: (2024)

Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion Models
by: Zhang, Lei, et al.
Published: (2025)

SemDP: Semantic-level Differential Privacy Protection for Face Datasets
by: Zhang, Xiaoting, et al.
Published: (2024)

MIBench: A Comprehensive Framework for Benchmarking Model Inversion Attack and Defense
by: Qiu, Yixiang, et al.
Published: (2024)

A Privacy-Preserving Semantic-Segmentation Method Using Domain-Adaptation Technique
by: Sueyoshi, Homare, et al.
Published: (2025)

DiffProtect: Generate Adversarial Examples with Diffusion Models for Facial Privacy Protection
by: Liu, Jiang, et al.
Published: (2023)

AI-Driven Secure Data Sharing: A Trustworthy and Privacy-Preserving Approach
by: Amin, Al, et al.
Published: (2025)

Privacy-Preserving Clothing Classification using Vision Transformer for Thermal Comfort Estimation
by: Chuman, Tatsuya, et al.
Published: (2026)

A First Look at Privacy Risks of Android Task-executable Voice Assistant Applications
by: Pan, Shidong, et al.
Published: (2025)