Personalized Privacy Control in LLMs via Attention Head Intervention
Making AI respect different people's privacy wishes, not just general rules
Large language models trained to follow generic privacy rules ignore individual user preferences more than half the time. Researchers built a benchmark to test personalized privacy (where different users have different comfort levels with sharing information) and developed a method that adjusts how the AI's internal attention mechanisms work at inference time, significantly improving compliance with each user's specific privacy boundaries.
As AI systems gain access to personal data through email, calendars, and messaging apps, a one-size-fits-all privacy approach fails—some users are comfortable sharing health information while others aren't. This work provides both a way to measure whether AI respects individual privacy preferences and a practical fix that works without retraining the model, making it feasible to deploy personalized privacy controls in real AI assistants today.