George Kesidis

research

∙ 08/30/2022

Analysis of Distributed Deep Learning in the Cloud

We aim to resolve this problem by introducing a comprehensive distribute...

0 Aakash Sharma, et al. ∙

research

∙ 07/11/2022

IaaS Procurement by Simulated Annealing

Considering the problem of resource allocation for potentially complex a...

0 Nader Alfares, et al. ∙

research

∙ 05/13/2022

Universal Post-Training Backdoor Detection

A Backdoor attack (BA) is an important type of adversarial attack agains...

0 Hang Wang, et al. ∙

research

∙ 01/20/2022

Post-Training Detection of Backdoor Attacks for Two-Class and Multi-Attack Scenarios

Backdoor attacks (BAs) are an emerging threat to deep neural network cla...

0 Zhen Xiang, et al. ∙

research

∙ 12/06/2021

Test-Time Detection of Backdoor Triggers for Poisoned Deep Neural Networks

Backdoor (Trojan) attacks are emerging threats against deep neural netwo...

0 Xi Li, et al. ∙

research

∙ 10/20/2021

Detecting Backdoor Attacks Against Point Cloud Classifiers

Backdoor attacks (BA) are an emerging threat to deep neural network clas...

0 Zhen Xiang, et al. ∙

research

∙ 09/06/2021

Backdoor Attack and Defense for Deep Regression

We demonstrate a backdoor attack on a deep neural network used for regre...

0 Xi Li, et al. ∙

research

∙ 07/28/2021

Robust and Active Learning for Deep Neural Network Regression

We describe a gradient-based method to discover local error maximizers o...

0 Xi Li, et al. ∙

research

∙ 06/15/2021

Age of Information for Small Buffer Systems

Consider a message processing system whose objective is to produce the m...

0 George Kesidis, et al. ∙

research

∙ 05/28/2021

A BIC based Mixture Model Defense against Data Poisoning Attacks on Classifiers

Data Poisoning (DP) is an effective attack that causes trained classifie...

0 Xi Li, et al. ∙

research

∙ 05/21/2021

Anomaly Detection of Test-Time Evasion Attacks using Class-conditional Generative Adversarial Networks

Deep Neural Networks (DNNs) have been shown vulnerable to adversarial (T...

0 Hang Wang, et al. ∙

research

∙ 04/23/2021

Age of information distribution under dynamic service preemption

Age of Information (AoI) has emerged as an important quality-of-service ...

0 George Kesidis, et al. ∙

research

∙ 04/16/2021

Age of information without service preemption

When designing a message transmission system, from the point of view of ...

0 George Kesidis, et al. ∙

research

∙ 04/12/2021

A Backdoor Attack against 3D Point Cloud Classifiers

Vulnerability of 3D point cloud (PC) classifiers has become a grave conc...

0 Zhen Xiang, et al. ∙

research

∙ 10/20/2020

L-RED: Efficient Post-Training Detection of Imperceptible Backdoor Attacks without Access to the Training Set

Backdoor attacks (BAs) are an emerging form of adversarial attack typica...

0 Zhen Xiang, et al. ∙

research

∙ 10/15/2020

Reverse Engineering Imperceptible Backdoor Attacks on Deep Neural Networks for Detection and Training Set Cleansing

Backdoor data poisoning is an emerging form of adversarial attack usuall...

0 Zhen Xiang, et al. ∙

research

∙ 09/09/2020

CASH: A Credit Aware Scheduling for Public Cloud Platforms

The public cloud offers a myriad of services which allows its tenants to...

0 Aakash Sharma, et al. ∙

research

∙ 11/18/2019

Revealing Perceptible Backdoors, without the Training Set, via the Maximum Achievable Misclassification Fraction Statistic

Recently, a special type of data poisoning (DP) attack, known as a backd...

0 Zhen Xiang, et al. ∙

research

∙ 10/15/2019

Notes on Lipschitz Margin, Lipschitz Margin Training, and Lipschitz Margin p-Values for Deep Neural Network Classifiers

We provide a local class purity theorem for Lipschitz continuous, half-r...

0 George Kesidis, et al. ∙

research

∙ 08/27/2019

Revealing Backdoors, Post-Training, in DNN Classifiers via Novel Inference on Optimized Perturbations Inducing Group Misclassification

Recently, a special type of data poisoning (DP) attack targeting Deep Ne...

1 Zhen Xiang, et al. ∙

research

∙ 05/18/2019

A caching system with object sharing

We consider a public content caching system that is shared by a number o...

0 George Kesidis, et al. ∙

research

∙ 04/12/2019

Adversarial Learning in Statistical Classification: A Comprehensive Review of Defenses Against Attacks

With the wide deployment of machine learning (ML) based systems for a va...

0 David J. Miller, et al. ∙

research

∙ 04/11/2019

The distribution of age-of-information performance measures for message processing systems

The idea behind the recently introduced "age of information" performance...

0 George Kesidis, et al. ∙

research

∙ 01/28/2019

Temporal Overbooking of Lambda Functions in the Cloud

We consider the problem of scheduling "serverless computing" instances s...

0 George Kesidis, et al. ∙

research

∙ 10/31/2018

A Mixture Model Based Defense for Data Poisoning Attacks Against Naive Bayes Spam Filters

Naive Bayes spam filters are highly susceptible to data poisoning attack...

0 David J. Miller, et al. ∙

research

∙ 10/31/2018

When Not to Classify: Detection of Reverse Engineering Attacks on DNN Image Classifiers

This paper addresses detection of a reverse engineering (RE) attack targ...

0 Yujia Wang, et al. ∙

research

∙ 10/01/2018

Heterogeneous MacroTasking (HeMT) for Parallel Processing in the Public Cloud

Using tiny, equal-sized tasks (Homogeneous microTasking, HomT) has long ...

0 Yuquan Shan, et al. ∙

research

∙ 08/01/2018

Relative Age of Information: Maintaining Freshness while Considering the Most Recently Generated Information

A queueing system handling a sequence of message arrivals is considered ...

0 George Kesidis, et al. ∙

research

∙ 08/01/2018

Average age of coupon type and related average age of information

We consider two types of problems associated with a bufferless server wi...

0 George Kesidis, et al. ∙

research

∙ 03/02/2018

Online Scheduling of Spark Workloads with Mesos using Different Fair Allocation Algorithms

In the following, we present example illustrative and experimental resul...

0 Yuquan Shan, et al. ∙

research

∙ 03/02/2018

Online Scheduling Fair of Spark Workloads with Mesos using Different Fair Allocation Algorithms

In the following, we present example illustrative and experimental resul...

0 Yuquan Shan, et al. ∙

research

∙ 12/29/2017

An Efficient and Fair Multi-Resource Allocation Mechanism for Heterogeneous Servers

Efficient and fair allocation of multiple types of resources is a crucia...

0 Jalal Khamse-Ashari, et al. ∙

research

∙ 12/18/2017

When Not to Classify: Anomaly Detection of Attacks (ADA) on DNN Classifiers at Test Time

A significant threat to the recent, wide deployment of machine learning-...

0 David J. Miller, et al. ∙

research

∙ 12/04/2017

Changing proxy-server identities as a proactive moving-target defense against reconnaissance for DDoS attacks

We consider a cloud based multiserver system consisting of a set of repl...

0 Neda Nasiriani, et al. ∙

research

∙ 11/24/2017

Is Non-Neutrality Profitable for the Stakeholders of the Internet Market? - Part II

In this part of the paper, we obtain analytical results for the case tha...

0 Mohammad Hassan Lotfi, et al. ∙

research

∙ 05/17/2017

Scheduling Distributed Resources in Heterogeneous Private Clouds

We first consider the static problem of allocating resources to ( i.e. ,...

0 George Kesidis, et al. ∙

research

∙ 05/17/2017

Efficient max-min and proportional fair constrained multiresource scheduling

We consider the problem of scheduling a group of heterogeneous, distribu...

0 George Kesidis, et al. ∙

research

∙ 04/17/2017

Stationary Distribution of a Generalized LRU-MRU Content Cache

Many different caching mechanisms have been previously proposed, explori...

0 George Kesidis, et al. ∙

George Kesidis

Featured Co-authors