🆕 Presenting at PETS'26
Professor Shvartzshnaider presented the paper co-authored with Vasisht Duddu on "Privacy Bias in Language Models: A Contextual Integrity-based Auditing Metric" at the annual Privacy Enhancing Technologies Symposium (PETS) in Calgary! Abstract: As large language models (LLMs) are integrated into sociotechnical systems, it is crucial to examine the privacy biases they exhibit. We define privacy bias […]