4 papers
On the MIA Vulnerability Gap Between Private GANs and Diffusion Models
Ilana Sebag, Jean-Yves Franceschi, Alain Rakotomamonjy +2
Generative Adversarial Networks (GANs) and diffusion models have emerged as leading approaches for high-quality image synthesis. While both can be trained under differential privac…
Differentially Private Gradient Flow based on the Sliced Wasserstein Distance
Ilana Sebag, Muni Sreenivas Pydi, Jean-Yves Franceschi +4
Safeguarding privacy in sensitive training data is paramount, particularly in the context of generative modeling. This can be achieved through either differentially private stochas…
Adversarial Conversational Shaping for Intelligent Agents
Piotr Tarasiewicz, Sultan Kenjeyev, Ilana Sebag +1
The recent emergence of deep learning methods has enabled the research community to achieve state-of-the art results in several domains including natural language processing. Howev…
On Combining Expert Demonstrations in Imitation Learning via Optimal Transport
Ilana Sebag, Samuel Cohen, Marc Peter Deisenroth
Imitation learning (IL) seeks to teach agents specific tasks through expert demonstrations. One of the key approaches to IL is to define a distance between agent and expert and to…