Cover Image

Topology Matters: Measuring Memory Leakage in Multi-Agent LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Jinbo, Cao, Defu, Wei, Yifei, Su, Tianyao, Liang, Yuan, Dong, Yushun, Liu, Yan, Zhao, Yue, Hu, Xiyang
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

S-Leak: Leakage-Abuse Attack Against Efficient Conjunctive SSE via s-term Leakage
by: Su, Yue, et al.
Published: (2025)

"Someone Hid It": Query-Agnostic Black-Box Attacks on LLM-Based Retrieval
by: Li, Jiate, et al.
Published: (2026)

MemoPhishAgent: Memory-Augmented Multi-Modal LLM Agent for Phishing URL Detection
by: Chen, Xuan, et al.
Published: (2026)

"Training robust watermarking model may hurt authentication!'' Exploring and Mitigating the Identity Leakage in Robust Watermarking
by: Zhang, Xinyu, et al.
Published: (2026)

Red-Teaming LLM Multi-Agent Systems via Communication Attacks
by: He, Pengfei, et al.
Published: (2025)

AEGIS: No Tool Call Left Unchecked -- A Pre-Execution Firewall and Audit Layer for AI Agents
by: Yuan, Aojie, et al.
Published: (2026)

Zebrafix: Mitigating Memory-Centric Side-Channel Leakage via Interleaving
by: Pätschke, Anna, et al.
Published: (2025)

ProvAgent: Threat Detection Based on Identity-Behavior Binding and Multi-Agent Collaborative Attack Investigation
by: Yan, Wenhao, et al.
Published: (2026)

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

d-DSE: Distinct Dynamic Searchable Encryption Resisting Volume Leakage in Encrypted Databases
by: Liu, Dongli, et al.
Published: (2024)

PII Jailbreaking in LLMs via Activation Steering Reveals Personal Information Leakage
by: Nakka, Krishna Kanth, et al.
Published: (2025)

Argus: A Multi-Agent Sensitive Information Leakage Detection Framework Based on Hierarchical Reference Relationships
by: Wang, Bin, et al.
Published: (2025)

Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models
by: Luo, Weidi, et al.
Published: (2025)

Observable Channels, Not Just Storage: Evaluating Privacy Leakage in LLM Agent Pipelines
by: Huang, Tao, et al.
Published: (2026)

Shell or Nothing: Real-World Benchmarks and Memory-Activated Agents for Automated Penetration Testing
by: Mai, Wuyuao, et al.
Published: (2025)

EdgeLeakage: Membership Information Leakage in Distributed Edge Intelligence Systems
by: Chen, Kongyang, et al.
Published: (2024)

Leakage-abuse Attack Against Substring-SSE with Partially Known Dataset
by: Ba, Xijie, et al.
Published: (2025)

VortexPIA: Indirect Prompt Injection Attack against LLMs for Efficient Extraction of User Privacy
by: Cui, Yu, et al.
Published: (2025)

Can LLMs Threaten Human Survival? Benchmarking Potential Existential Threats from LLMs via Prefix Completion
by: Cui, Yu, et al.
Published: (2025)

The Inevitability of Side-Channel Leakage in Encrypted Traffic
by: Liu, Guangjie, et al.
Published: (2026)

You Told Me to Do It: Measuring Instructional Text-induced Private Data Leakage in LLM Agents
by: Kao, Ching-Yu, et al.
Published: (2026)

GEO-Bench: Benchmarking Ranking Manipulation in Generative Engine Optimization
by: Nimase, Ojas, et al.
Published: (2026)

AgentDID: Trustless Identity Authentication for AI Agents
by: Xu, Minghui, et al.
Published: (2026)

CRFU: Compressive Representation Forgetting Against Privacy Leakage on Machine Unlearning
by: Wang, Weiqi, et al.
Published: (2025)

WebAgentGuard: A Reasoning-Driven Guard Model for Detecting Prompt Injection Attacks in Web Agents
by: Chen, Yulin, et al.
Published: (2026)

The Impact of Train-Test Leakage on Machine Learning-based Android Malware Detection
by: Liu, Guojun, et al.
Published: (2024)

Enabling Regulatory Multi-Agent Collaboration: Architecture, Challenges, and Solutions
by: Hu, Qinnan, et al.
Published: (2025)

Shesha: Multi-head Microarchitectural Leakage Discovery in new-generation Intel Processors
by: Chakraborty, Anirban, et al.
Published: (2024)

CoopGuard: Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Round Attacks
by: Li, Siyuan, et al.
Published: (2026)

Credential Leakage in LLM Agent Skills: A Large-Scale Empirical Study
by: Chen, Zhihao, et al.
Published: (2026)

You Can't Steal Nothing: Mitigating Prompt Leakages in LLMs via System Vectors
by: Cao, Bochuan, et al.
Published: (2025)

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

Bilevel Optimization for Covert Memory Tampering in Heterogeneous Multi-Agent Architectures (XAMT)
by: Sharma, Akhil, et al.
Published: (2025)

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

Revisiting Privacy Leakage in Machine Unlearning: Membership Inference Beyond the Forgotten Set
by: Fu, Jie, et al.
Published: (2026)

Rethinking Side-Channel Analysis: Automated Discovery and Analysis of Side-Channel Leakage with LLM-Assisted Agents
by: Xu, Zhen, et al.
Published: (2026)

Quantifying Privacy Leakage in Split Inference via Fisher-Approximated Shannon Information Analysis
by: Deng, Ruijun, et al.
Published: (2025)

ContextLeak: Auditing Leakage in Private In-Context Learning Methods
by: Choi, Jacob, et al.
Published: (2025)

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models
by: Cheng, Xueqi, et al.
Published: (2025)

Certified Defense on the Fairness of Graph Neural Networks
by: Dong, Yushun, et al.
Published: (2023)