6 citations · 38 across the 31 of their papers we have counts for
5 papers · 1 filter
When Not to Classify: Detection of Reverse Engineering Attacks on DNN Image Classifiers
Yujia Wang, David J. Miller, George Kesidis
This paper addresses detection of a reverse engineering (RE) attack targeting a deep neural network (DNN) image classifier; by querying, RE's aim is to discover the classifier's de…
A Mixture Model Based Defense for Data Poisoning Attacks Against Naive Bayes Spam Filters
David J. Miller, Xinyi Hu, Zhen Xiang +1
Naive Bayes spam filters are highly susceptible to data poisoning attacks. Here, known spam sources/blacklisted IPs exploit the fact that their received emails will be treated as (…
Heterogeneous MacroTasking (HeMT) for Parallel Processing in the Public Cloud
Yuquan Shan, George Kesidis, Bhuvan Urgaonkar +3
Using tiny, equal-sized tasks (Homogeneous microTasking, HomT) has long been regarded an effective way of load balancing in parallel computing systems. When combined with nodes pul…
Relative Age of Information: Maintaining Freshness while Considering the Most Recently Generated Information
George Kesidis, Takis Konstantopoulos, Michael Zazanis
A queueing system handling a sequence of message arrivals is considered where each message obsoletes all previous messages. The objective is to assess the freshness of the latest m…
Online Scheduling of Spark Workloads with Mesos using Different Fair Allocation Algorithms
Yuquan Shan, Aman Jain, George Kesidis +3
In the following, we present example illustrative and experimental results comparing fair schedulers allocating resources from multiple servers to distributed application framework…