AI Snitches Get Glitches: Towards Evading Agentic Surveillance
This paper addresses the emerging risk of AI agents being used for user surveillance, which is a critical problem for privacy and user autonomy.
The paper introduces and formalizes the problem of agentic surveillance, where AI agents can analyze data and report on users. The authors create SurveilBench to evaluate surveillance capabilities and find that some models exhibit emergent surveillance tendencies. They develop three evasion techniques using prompt injections to hide from, deceive, or induce over-escalation in surveillance agents.
To better assist users with completing challenging tasks, AI agents mediate communications, access data, and interact with different APIs. Many employers (and even nation-states) already provide their users with this technology. However, widespread adoption of AI agents creates a new risk to abuse access to user data for another goal: surveilling users. These users might not even have the ability or permission to control the actions and data accesses of the surveilling agents. We introduce and formalize the problem of agentic surveillance: the ability of an AI agent to analyze available information, craft a report, and send it out using available tools. To evaluate surveillance capabilities across different models, we create SurveilBench, a dataset of various reporting scenarios focusing on three domains: corporate, education, and police. We find that some models exhibit emergent (i.e., unprompted) tendencies to help surveillance, but they also report the attempts to surveil users to the government. Finally, we repurpose prompt injections for evading surveillance and develop three evasion techniques that hide from, deceive, or induce over-escalation in surveillance agents. We conclude that agentic surveillance can already be easily implemented and, therefore, call for a comprehensive technical, ethical, and legislative framework to protect users.