Cover Image

DualTAP: A Dual-Task Adversarial Protector for Mobile MLLM Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Fuyao, Zhang, Jiaming, Wang, Che, Sun, Xiongtao, Hao, Yurong, Guan, Guowei, Li, Wenjie, Huang, Longtao, Lim, Wei Yang Bryan
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

Verifiably Forgotten? Gradient Differences Still Enable Data Reconstruction in Federated Unlearning
by: Zhang, Fuyao, et al.
Published: (2025)

ICON: Indirect Prompt Injection Defense for Agents based on Inference-Time Correction
by: Wang, Che, et al.
Published: (2026)

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

Oblivionis: A Lightweight Learning and Unlearning Framework for Federated Large Language Models
by: Zhang, Fuyao, et al.
Published: (2025)

DUAP: Dual-task Universal Adversarial Perturbations Against Voice Control Systems
by: Sun, Suyang, et al.
Published: (2026)

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

IDT: Dual-Task Adversarial Attacks for Privacy Protection
by: Faustini, Pedro, et al.
Published: (2024)

Dynamic Dual-level Defense Routing for Continual Adversarial Training
by: Wang, Wenxuan, et al.
Published: (2025)

Privacy on the Fly: A Predictive Adversarial Transformation Network for Mobile Sensor Data
by: Song, Tianle, et al.
Published: (2025)

AdapTools: Adaptive Tool-based Indirect Prompt Injection Attacks on Agentic LLMs
by: Wang, Che, et al.
Published: (2026)

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels
by: Du, Chenghao, et al.
Published: (2025)

Adversary-Aware DPO: Enhancing Safety Alignment in Vision Language Models via Adversarial Training
by: Weng, Fenghua, et al.
Published: (2025)

CCFC: Core & Core-Full-Core Dual-Track Defense for LLM Jailbreak Protection
by: Hu, Jiaming, et al.
Published: (2025)

Dual-Guard: Dual-Channel Latent Watermarking for Provenance and Tamper Localization in Diffusion Images
by: Xie, JinFeng, et al.
Published: (2026)

Enhancing Security and Privacy in Federated Learning using Low-Dimensional Update Representation and Proximity-Based Defense
by: Li, Wenjie, et al.
Published: (2024)

ALRPHFS: Adversarially Learned Risk Patterns with Hierarchical Fast \& Slow Reasoning for Robust Agent Defense
by: Xiang, Shiyu, et al.
Published: (2025)

A Dual-Level Cancelable Framework for Palmprint Verification and Hack-Proof Data Storage
by: Yang, Ziyuan, et al.
Published: (2024)

Securing LLM Agents Need Intent-to-Execution Integrity
by: Qu, Wenjie, et al.
Published: (2026)

FraudBench: A Multimodal Benchmark for Detecting AI-Generated Fraudulent Refund Evidence
by: Yan, Xinyu, et al.
Published: (2026)

Robust Reversible Watermarking in Encrypted Images Based on Dual-MSBs Spiral Embedding
by: Shen, Haoyu, et al.
Published: (2026)

Data and Decision Traceability for SDA TAP Lab's Prototype Battle Management System
by: Pratti, Latha, et al.
Published: (2025)

Enhanced MLLM Black-Box Jailbreaking Attacks and Defenses
by: Zhong, Xingwei, et al.
Published: (2025)

Towards Understanding Dual BN In Hybrid Adversarial Training
by: Zhang, Chenshuang, et al.
Published: (2024)

The Surprising Harmfulness of Benign Overfitting for Adversarial Robustness
by: Hao, Yifan, et al.
Published: (2024)

Don't Trust Your Upstream: Exploiting LLM Multi-Agent System via Topology-Guided Adversarial Propagation
by: Liang, Ruichao, et al.
Published: (2025)

Tit-for-Tat: Safeguarding Large Vision-Language Models Against Jailbreak Attacks via Adversarial Defense
by: Hao, Shuyang, et al.
Published: (2025)

PGD-Imp: Rethinking and Unleashing Potential of Classic PGD with Dual Strategies for Imperceptible Adversarial Attacks
by: Li, Jin, et al.
Published: (2024)

DualGuard: Dual-stream Large Language Model Watermarking Defense against Paraphrase and Spoofing Attack
by: Li, Hao, et al.
Published: (2025)

Towards Code Watermarking with Dual-Channel Transformations
by: Yang, Borui, et al.
Published: (2023)

Systematic Categorization, Construction and Evaluation of New Attacks against Multi-modal Mobile GUI Agents
by: Yang, Yulong, et al.
Published: (2024)

Poisoning Behavioral-based Worker Selection in Mobile Crowdsensing using Generative Adversarial Networks
by: Nasser, Ruba, et al.
Published: (2025)

Adversarial Attacks on Reinforcement Learning Agents for Command and Control
by: Dabholkar, Ahaan, et al.
Published: (2024)

NCCR: to Evaluate the Robustness of Neural Networks and Adversarial Examples
by: Pu, Shi, et al.
Published: (2025)

Enhancing Adversarial Resistance in LLMs with Recursion
by: Li, Bryan, et al.
Published: (2024)

DualSentinel: A Lightweight Framework for Detecting Targeted Attacks in Black-box LLM via Dual Entropy Lull Pattern
by: Pang, Xiaoyi, et al.
Published: (2026)

WARD: Adversarially Robust Defense of Web Agents Against Prompt Injections
by: Cao, Tri, et al.
Published: (2026)

ExDoS: Expert-Guided Dual-Focus Cross-Modal Distillation for Smart Contract Vulnerability Detection
by: Tian, Ye, et al.
Published: (2025)

"Are Adversarial Phishing Webpages a Threat in Reality?" Understanding the Users' Perception of Adversarial Webpages
by: Yuan, Ying, et al.
Published: (2024)

Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attacks
by: Xue, Lulu, et al.
Published: (2024)