Papers
arxiv:2508.10880

Searching for Privacy Risks in LLM Agents via Simulation

Published on Aug 14
Authors:
,

Abstract

A search-based framework using LLMs simulates attacker-defender interactions to discover and evolve sophisticated privacy attack and defense strategies in multi-turn dialogues.

AI-generated summary

The widespread deployment of LLM-based agents is likely to introduce a critical privacy threat: malicious agents that proactively engage others in multi-turn interactions to extract sensitive information. These dynamic dialogues enable adaptive attack strategies that can cause severe privacy violations, yet their evolving nature makes it difficult to anticipate and discover sophisticated vulnerabilities manually. To tackle this problem, we present a search-based framework that alternates between improving attacker and defender instructions by simulating privacy-critical agent interactions. Each simulation involves three roles: data subject, data sender, and data recipient. While the data subject's behavior is fixed, the attacker (data recipient) attempts to extract sensitive information from the defender (data sender) through persistent and interactive exchanges. To explore this interaction space efficiently, our search algorithm employs LLMs as optimizers, using parallel search with multiple threads and cross-thread propagation to analyze simulation trajectories and iteratively propose new instructions. Through this process, we find that attack strategies escalate from simple direct requests to sophisticated multi-turn tactics such as impersonation and consent forgery, while defenses advance from rule-based constraints to identity-verification state machines. The discovered attacks and defenses transfer across diverse scenarios and backbone models, demonstrating strong practical utility for building privacy-aware agents.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2508.10880 in a model README.md to link it from this page.

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2508.10880 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.