Deep Learning
Recovering Private Textin Federated Learningof Language Models
"The", "cat", "chases", "dogs", "lie", "mouse", "sleeping", "the", "."}. Table3showsthat attackerwho isabletoreco (roughly 5 sentences) (recall).
ManifoldTopologyDivergence:aFrameworkfor ComparingDataManifolds
We develop a framework for comparing data manifolds, aimed, in particular, towards the evaluation of deep generative models.
Handcrafted Backdoorsin Deep Neural Networks
In25nd Annual Networkand Distributed System Security Symposium, NDSS 2018, San Diego, California, USA, February 18-221, 2018.
AreMultipleInstanceLearningAlgorithms LearnableforInstances?
Our analysis exposes significant gaps between current Deep MIL algorithms, highlighting thetheoretical conditions that must besatisfied by MIL algorithms to ensure instance-level learnability.
