Image de couverture de livre

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Lyu, Xingyu, He, Jianfeng, Wang, Ning, Hu, Yidan, Li, Tao, Chen, Danjue, Li, Shixiong, Chen, Yimin
Format:	Preprint
Publié:	2026
Sujets:	Cryptography and Security Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Buffer is All You Need: Defending Federated Learning against Backdoor Attacks under Non-iids via Buffering
par: Lyu, Xingyu, et autres
Publié: (2025)

ALDEN: Boosting Private Data Extraction from Retrieval-Augmented Generation Systems via Active Learning and Distribution Estimation
par: Lyu, Xingyu, et autres
Publié: (2026)

AudAgent: Automated Auditing of Privacy Policy Compliance in AI Agents
par: Zheng, Ye, et autres
Publié: (2025)

External Data Extraction Attacks against Retrieval-Augmented Large Language Models
par: He, Yu, et autres
Publié: (2025)

PrivScope: Task-scoped Disclosure Control for Hybrid Agentic Systems
par: Seeam, Shafizur Rahman, et autres
Publié: (2026)

Query Provenance Analysis: Efficient and Robust Defense against Query-based Black-box Attacks
par: Li, Shaofei, et autres
Publié: (2024)

MIRAGE: Misleading Retrieval-Augmented Generation via Black-box and Query-agnostic Poisoning Attacks
par: Chen, Tailun, et autres
Publié: (2025)

ModelShield: Adaptive and Robust Watermark against Model Extraction Attack
par: Pang, Kaiyi, et autres
Publié: (2024)

BoBa: Boosting Backdoor Detection through Data Distribution Inference in Federated Learning
par: Jiang, Zhengyuan, et autres
Publié: (2024)

CheatAgent: Attacking LLM-Empowered Recommender Systems via LLM Agent
par: Ning, Liang-bo, et autres
Publié: (2025)

A Portable and Stealthy Inaudible Voice Attack Based on Acoustic Metamaterials
par: Ning, Zhiyuan, et autres
Publié: (2025)

Two Heads Are Better than One: Model-Weight and Latent-Space Analysis for Federated Learning on Non-iid Data against Poisoning Attacks
par: Lyu, Xingyu, et autres
Publié: (2025)

Collaborative Shadows: Distributed Backdoor Attacks in LLM-Based Multi-Agent Systems
par: Zhu, Pengyu, et autres
Publié: (2025)

MRMMIA: Membership Inference Attacks on Memory in Chat Agents
par: Chen, Kai, et autres
Publié: (2026)

"Someone Hid It": Query-Agnostic Black-Box Attacks on LLM-Based Retrieval
par: Li, Jiate, et autres
Publié: (2026)

Is Difficulty Calibration All We Need? Towards More Practical Membership Inference Attacks
par: He, Yu, et autres
Publié: (2024)

Evolving Skill-Structured Attack Memory Enhances LLM Jailbreaking
par: Zhang, Junke, et autres
Publié: (2026)

A Systematic Study of Model Extraction Attacks on Graph Foundation Models
par: Xu, Haoyan, et autres
Publié: (2025)

ATOM: A Framework of Detecting Query-Based Model Extraction Attacks for Graph Neural Networks
par: Cheng, Zhan, et autres
Publié: (2025)

Frequency Estimation of Correlated Multi-attribute Data under Local Differential Privacy
par: Seeam, Shafizur Rahman, et autres
Publié: (2025)

TopicAttack: An Indirect Prompt Injection Attack via Topic Transition
par: Chen, Yulin, et autres
Publié: (2025)

TraCS: Trajectory Collection in Continuous Space under Local Differential Privacy
par: Zheng, Ye, et autres
Publié: (2024)

Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspective
par: Wu, Baoyuan, et autres
Publié: (2023)

Memory Scraping Attack on Xilinx FPGAs: Private Data Extraction from Terminated Processes
par: Madabhushi, Bharadwaj, et autres
Publié: (2024)

Black-Box Membership Inference Attack for LVLMs via Prior Knowledge-Calibrated Memory Probing
par: Yin, Jinhua, et autres
Publié: (2025)

WebAgentGuard: A Reasoning-Driven Guard Model for Detecting Prompt Injection Attacks in Web Agents
par: Chen, Yulin, et autres
Publié: (2026)

Five Queries Are Enough: Query-Efficient and Surrogate-Free Membership Inference Attacks on RAG via Entailment
par: Nguyen, Nguyen Linh Bao, et autres
Publié: (2026)

MalTool: Malicious Tool Attacks on LLM Agents
par: Hu, Yuepeng, et autres
Publié: (2026)

Exploration on Real World Assets and Tokenization
par: Xia, Ning, et autres
Publié: (2025)

Data Extraction Attacks in Retrieval-Augmented Generation via Backdoors
par: Peng, Yuefeng, et autres
Publié: (2024)

Adaptive Domain Inference Attack with Concept Hierarchy
par: Gu, Yuechun, et autres
Publié: (2023)

Hijacking Agent Memory: Stealthy Trojan Attacks Through Conversational Interaction
par: Wang, Hongtao, et autres
Publié: (2026)

MemoPhishAgent: Memory-Augmented Multi-Modal LLM Agent for Phishing URL Detection
par: Chen, Xuan, et autres
Publié: (2026)

Systematic Categorization, Construction and Evaluation of New Attacks against Multi-modal Mobile GUI Agents
par: Yang, Yulong, et autres
Publié: (2024)

Data Reconstruction Attacks and Defenses: A Systematic Evaluation
par: Liu, Sheng, et autres
Publié: (2024)

From Storage to Steering: Memory Control Flow Attacks on LLM Agents
par: Xu, Zhenlin, et autres
Publié: (2026)

AgentGuard: A Multi-Agent Framework for Robust Package Confusion Detection via Hybrid Search and Metadata-Content Fusion
par: Li, Yu, et autres
Publié: (2026)

Towards Model Extraction Attacks in GAN-Based Image Translation via Domain Shift Mitigation
par: Mi, Di, et autres
Publié: (2024)

PINA: Prompt Injection Attack against Navigation Agents
par: Liu, Jiani, et autres
Publié: (2026)

ProvAgent: Threat Detection Based on Identity-Behavior Binding and Multi-Agent Collaborative Attack Investigation
par: Yan, Wenhao, et autres
Publié: (2026)