17 citations · 51 across the 7 of their papers we have counts for
7 papers
Towards Understanding the Interplay of Generative Artificial Intelligence and the Internet
Gonzalo Martínez, Lauren Watson, Pedro Reviriego +3
The rapid adoption of generative Artificial Intelligence (AI) tools that can generate realistic images or text, such as DALL-E, MidJourney, or ChatGPT, have put the societal impact…
Combining Generative Artificial Intelligence (AI) and the Internet: Heading towards Evolution or Degradation?
Gonzalo Martínez, Lauren Watson, Pedro Reviriego +3
In the span of a few months, generative Artificial Intelligence (AI) tools that can generate realistic images or text have taken the Internet by storm, making them one of the techn…
Differentially Private Shapley Values for Data Evaluation
Lauren Watson, Rayna Andreeva, Hao-Tsung Yang +1
The Shapley value has been proposed as a solution to many applications in machine learning, including for equitable valuation of data. Shapley values are computationally expensive…
Continual and Sliding Window Release for Private Empirical Risk Minimization
Lauren Watson, Abhirup Ghosh, Benedek Rozemberczki +1
It is difficult to continually update private machine learning models with new data while maintaining privacy. Data incur increasing privacy loss -- as measured by differential pri…
The Shapley Value in Machine Learning
Benedek Rozemberczki, Lauren Watson, Péter Bayer +4
Over the last few years, the Shapley value, a solution concept from cooperative game theory, has found numerous applications in machine learning. In this paper, we first discuss fu…
On the Importance of Difficulty Calibration in Membership Inference Attacks
Lauren Watson, Chuan Guo, Graham Cormode +1
The vulnerability of machine learning models to membership inference attacks has received much attention in recent years. However, existing attacks mostly remain impractical due to…
Stability Enhanced Privacy and Applications in Private Stochastic Gradient Descent
Lauren Watson, Benedek Rozemberczki, Rik Sarkar
Private machine learning involves addition of noise while training, resulting in lower accuracy. Intuitively, greater stability can imply greater privacy and improve this privacy-u…