Cover Image

The Sum Leaks More Than Its Parts: Compositional Privacy Risks and Mitigations in Multi-Agent Collaboration

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Patil, Vaidehi, Stengel-Eskin, Elias, Bansal, Mohit
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

UPCORE: Utility-Preserving Coreset Selection for Balanced Unlearning
by: Patil, Vaidehi, et al.
Published: (2025)

Agent Tools Orchestration Leaks More: Dataset, Benchmark, and Mitigation
by: Qiao, Yuxuan, et al.
Published: (2025)

Generalized Correctness Models: Learning Calibrated and Model-Agnostic Correctness Predictors from Historical Patterns
by: Xiao, Hanqi, et al.
Published: (2025)

Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mind
by: Xiao, Hanqi, et al.
Published: (2026)

MAMM-Refine: A Recipe for Improving Faithfulness in Generation with Multi-Agent Collaboration
by: Wan, David, et al.
Published: (2025)

Searching for Privacy Risks in LLM Agents via Simulation
by: Zhang, Yanzhe, et al.
Published: (2025)

Shadow in the Cache: Unveiling and Mitigating Privacy Risks of KV-cache in LLM Inference
by: Luo, Zhifan, et al.
Published: (2025)

Leaking LoRa: An Evaluation of Password Leaks and Knowledge Storage in Large Language Models
by: Marinelli, Ryan, et al.
Published: (2025)

Safety Alignment Should Be Made More Than Just A Few Attention Heads
by: Huang, Chao, et al.
Published: (2025)

LACIE: Listener-Aware Finetuning for Confidence Calibration in Large Language Models
by: Stengel-Eskin, Elias, et al.
Published: (2024)

Teaching Models to Balance Resisting and Accepting Persuasion
by: Stengel-Eskin, Elias, et al.
Published: (2024)

Language Models Identify Ambiguities and Exploit Loopholes
by: Choi, Jio, et al.
Published: (2025)

LeakDojo: Decoding the Leakage Threats of RAG Systems
by: Zhang, Maosen, et al.
Published: (2026)

Contextualized Privacy Defense for LLM Agents
by: Wen, Yule, et al.
Published: (2026)

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage
by: Nie, Yuzhou, et al.
Published: (2024)

Soft Self-Consistency Improves Language Model Agents
by: Wang, Han, et al.
Published: (2024)

Quantifying Association Capabilities of Large Language Models and Its Implications on Privacy Leakage
by: Shao, Hanyin, et al.
Published: (2023)

ReGAL: Refactoring Programs to Discover Generalizable Abstractions
by: Stengel-Eskin, Elias, et al.
Published: (2024)

Beyond Jailbreaking: Auditing Contextual Privacy in LLM Agents
by: Das, Saswat, et al.
Published: (2025)

NeuroFilter: Privacy Guardrails for Conversational LLM Agents
by: Das, Saswat, et al.
Published: (2026)

DataEnvGym: Data Generation Agents in Teacher Environments with Student Feedback
by: Khan, Zaid, et al.
Published: (2024)

CompLeak: Deep Learning Model Compression Exacerbates Privacy Leakage
by: Li, Na, et al.
Published: (2025)

Privacy in Action: Towards Realistic Privacy Mitigation and Evaluation for LLM-Powered Agents
by: Wang, Shouju, et al.
Published: (2025)

Shadows in the Code: Exploring the Risks and Defenses of LLM-based Multi-Agent Software Development Systems
by: Wang, Xiaoqing, et al.
Published: (2025)

Multi-Attribute Steering of Language Models via Targeted Intervention
by: Nguyen, Duy, et al.
Published: (2025)

Ghost Tool Calls: Issue-Time Privacy for Speculative Agent Tools
by: Mohammadi, Bardia, et al.
Published: (2026)

LoRA-Leak: Membership Inference Attacks Against LoRA Fine-tuned Language Models
by: Ran, Delong, et al.
Published: (2025)

Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agents
by: Ngong, Ivoline, et al.
Published: (2025)

Unveiling Privacy Risks in LLM Agent Memory
by: Wang, Bo, et al.
Published: (2025)

Are language models rational? The case of coherence norms and belief revision
by: Hofweber, Thomas, et al.
Published: (2024)

Retrieval-Augmented Generation with Conflicting Evidence
by: Wang, Han, et al.
Published: (2025)

SplitAgent: A Privacy-Preserving Distributed Architecture for Enterprise-Cloud Agent Collaboration
by: She, Jianshu
Published: (2026)

MRJ-Agent: An Effective Jailbreak Agent for Multi-Round Dialogue
by: Wang, Fengxiang, et al.
Published: (2024)

Privacy-Preserving Retrieval-Augmented Generation with Differential Privacy
by: Koga, Tatsuki, et al.
Published: (2024)

When RAG Chatbots Expose Their Backend: An Anonymized Case Study of Privacy and Security Risks in Patient-Facing Medical AI
by: Madrid-García, Alfredo, et al.
Published: (2026)

Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models
by: Prasad, Archiki, et al.
Published: (2023)

PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action
by: Shao, Yijia, et al.
Published: (2024)

SoK: Honeypots & LLMs, More Than the Sum of Their Parts?
by: Bridges, Robert A., et al.
Published: (2025)

When Agents "Misremember" Collectively: Exploring the Mandela Effect in LLM-based Multi-Agent Systems
by: Xu, Naen, et al.
Published: (2026)

Toward a Safer Web: Multilingual Multi-Agent LLMs for Mitigating Adversarial Misinformation Attacks
by: Aldahoul, Nouar, et al.
Published: (2025)