Sensitive information, such as knowledge about an individual's personality, can be can be misused to influence behavior (e.g., via personalized messaging). To assess to what extent an individual's personality can be inferred from user interactions with LLM-based conversational agents (CAs), we analyze and quantify related privacy risks of using CAs. We collected actual ChatGPT logs from N=668 participants, containing 62,090 individual chats, and report statistics about the different types of shared data and use cases. We fine-tuned RoBERTa-base text classification models to infer personality traits from CA interactions. The findings show that these models achieve trait inference with accuracy (ternary classification) better than random in multiple cases. For example, for extraversion, accuracy improves by +44% relative to the baseline on interactions for relationships and personal reflection. This research highlights how interactions with CAs pose privacy risks and provides fine-grained insights into the level of risk associated with different types of interactions.

翻译：敏感信息（例如关于个人人格的知识）可能被滥用以影响行为（例如通过个性化消息）。为了评估个体人格特征能在多大程度上从用户与基于LLM的对话代理（CA）的交互中被推断出来，我们分析并量化了使用CA的相关隐私风险。我们收集了N=668名参与者的实际ChatGPT日志，包含62,090次独立对话，并报告了不同类型共享数据及使用场景的统计数据。我们微调了基于RoBERTa-base的文本分类模型，以从CA交互中推断人格特质。研究结果表明，这些模型在多种情况下实现了优于随机的特质推断准确率（三分类）。例如，在外向性方面，针对涉及人际关系与自我反思的交互场景，模型准确率相比基线提升了+44%。这项研究强调了与CA的交互如何构成隐私风险，并提供了关于不同交互类型相关风险等级的细粒度洞察。