CLIOPATRA: Extracting Private Information from LLM Insights

As AI assistants become widely used, privacy-aware platforms like Anthropic's Clio have been introduced to generate insights from real-world AI use. Clio's privacy protections rely on layering multiple heuristic techniques together, including PII redaction, clustering, filtering, and LLM-based...

Breaking the Illusion: Automated Reasoning of GDPR Consent Violations

Recent privacy regulations such as the General Data Protection Regulation GDPR and the California Consumer Privacy Act CCPA have established legal requirements for obtaining user consent regarding the collection, use, and sharing of personal data. These regulations emphasize that consent must be...

Optimizing Canaries for Privacy Auditing with Metagradient Descent

In this work we study black-box privacy auditing, where the goal is to lower bound the privacy parameter of a differentially private learning algorithm using only the algorithm's outputs i.e., final trained model. For DP-SGD the most successful method for training differentially private deep...

Membership Inference Attacks on Sequence Models

Sequence models, such as Large Language Models LLMs and autoregressive image generators, have a tendency to memorize and inadvertently leak sensitive information. While this tendency has critical legal implications, existing tools are insufficient to audit the resulting risks. We hypothesize that...