388 citations · 1.5k across the 94 of their papers we have counts for
5 papers · 1 filter
Three Variants of Differential Privacy: Lossless Conversion and Applications
Shahab Asoodeh, Jiachun Liao, Flavio P. Calmon +2
We consider three different variants of differential privacy (DP), namely approximate DP, Rényi DP (RDP), and hypothesis test DP. In the first part, we develop a machinery for opti…
On the alpha-loss Landscape in the Logistic Model
Tyler Sypherd, Mario Diaz, Lalitha Sankar +1
We analyze the optimization landscape of a recently introduced tunable class of loss functions called -loss, , in the logistic model. This family encapsulates t…
Reliability Makes It Difficult for False Data Injection Attacks to Cause Physical Consequences
Zhigang Chu, Jiazi Zhang, Oliver Kosut +1
This paper demonstrates that false data injection (FDI) attacks are extremely limited in their ability to cause physical consequences on reliable power systems operating with…
Detecting Load Redistribution Attacks via Support Vector Models
Zhigang Chu, Oliver Kosut, Lalitha Sankar
A machine learning-based detection framework is proposed to detect a class of cyber-attacks that redistribute loads by modifying measurements. The detection framework consists of a…
A Better Bound Gives a Hundred Rounds: Enhanced Privacy Guarantees via -Divergences
Shahab Asoodeh, Jiachun Liao, Flavio P. Calmon +2
We derive the optimal differential privacy (DP) parameters of a mechanism that satisfies a given level of Rényi differential privacy (RDP). Our result is based on the joint range o…