Prevalence of Security and Privacy Risk-Inducing Usage of AI-based Conversational Agents
Authors: K Grosse, N Ebert
Published: 2025
Publication: ARXIV
A survey of 3,270 UK adults reveals significant security and privacy risks in AI conversational agent usage, with a third engaging in risky behavior enabling attacks and many unaware of how their data are used or opting out.
Methods: Representative survey conducted via Prolific platform targeting UK adults, focusing on usage behaviors of AI conversational agents.
Key Findings: User behaviors related to security and privacy risks, data sanitization practices, attempts to jailbreak AI models, and awareness of data usage policies.
Limitations: Findings are self-reported and may not account for all security practices. Limited to UK adults and the specific AI tools surveyed, potentially underrepresenting other populations globally.
Institution: IBM Research, ZHAW
Research Area: Security and privacy risks, LLM, human–AI interaction, AI Safety
Discipline: Computer Science
Sample Size: 3270 participants