The Sum Leaks More Than Its Parts: Compositional Privacy Risks and Mitigations in Multi-Agent Collaboration
Abstract
Research identifies compositional privacy leakage in multi-agent LLM systems and evaluates defense strategies to mitigate it, finding that collaborative consensus defense offers the best balance between privacy and utility.
As large language models (LLMs) become integral to multi-agent systems, new privacy risks emerge that extend beyond memorization, direct inference, or single-turn evaluations. In particular, seemingly innocuous responses, when composed across interactions, can cumulatively enable adversaries to recover sensitive information, a phenomenon we term compositional privacy leakage. We present the first systematic study of such compositional privacy leaks and possible mitigation methods in multi-agent LLM systems. First, we develop a framework that models how auxiliary knowledge and agent interactions jointly amplify privacy risks, even when each response is benign in isolation. Next, to mitigate this, we propose and evaluate two defense strategies: (1) Theory-of-Mind defense (ToM), where defender agents infer a questioner's intent by anticipating how their outputs may be exploited by adversaries, and (2) Collaborative Consensus Defense (CoDef), where responder agents collaborate with peers who vote based on a shared aggregated state to restrict sensitive information spread. Crucially, we balance our evaluation across compositions that expose sensitive information and compositions that yield benign inferences. Our experiments quantify how these defense strategies differ in balancing the privacy-utility trade-off. We find that while chain-of-thought alone offers limited protection to leakage (~39% sensitive blocking rate), our ToM defense substantially improves sensitive query blocking (up to 97%) but can reduce benign task success. CoDef achieves the best balance, yielding the highest Balanced Outcome (79.8%), highlighting the benefit of combining explicit reasoning with defender collaboration. Together, our results expose a new class of risks in collaborative LLM deployments and provide actionable insights for designing safeguards against compositional, context-driven privacy leakage.
Community
Paper on compositional privacy leakage and mitigations in distributed multi-agent LLM systems
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- 1-2-3 Check: Enhancing Contextual Privacy in LLM via Multi-Agent Reasoning (2025)
- Searching for Privacy Risks in LLM Agents via Simulation (2025)
- Network-Level Prompt and Trait Leakage in Local Research Agents (2025)
- Enterprise AI Must Enforce Participant-Aware Access Control (2025)
- PromptSleuth: Detecting Prompt Injection via Semantic Intent Invariance (2025)
- Privacy-Aware Decoding: Mitigating Privacy Leakage of Large Language Models in Retrieval-Augmented Generation (2025)
- Beyond Data Privacy: New Privacy Risks for Large Language Models (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper