George Kesidis
Overview
Explore the profile of George Kesidis including associated specialties, affiliations and a list of published articles.
Author names and details appear as published. Due to indexing inconsistencies, multiple individuals may share a name, and a single author may have variations. MedLuna displays this data as publicly available, without modification or verification
Snapshot
Snapshot
Articles
11
Citations
80
Followers
0
Related Specialties
Related Specialties
Top 10 Co-Authors
Top 10 Co-Authors
Published In
Affiliations
Affiliations
Soon will be listed here.
Recent Articles
1.
Xiang Z, Miller D, Wang H, Kesidis G
Neural Comput
. 2021 Feb;
33(5):1329-1371.
PMID: 33617746
Backdoor data poisoning attacks add mislabeled examples to the training set, with an embedded backdoor pattern, so that the classifier learns to classify to a target class whenever the backdoor...
2.
Xiang Z, Miller D, Kesidis G
IEEE Trans Neural Netw Learn Syst
. 2020 Dec;
33(3):1177-1191.
PMID: 33326384
With wide deployment of deep neural network (DNN) classifiers, there is great potential for harm from adversarial learning attacks. Recently, a special type of data poisoning (DP) attack, known as...
3.
Miller D, Wang Y, Kesidis G
Neural Comput
. 2019 Jul;
31(8):1624-1670.
PMID: 31260390
A significant threat to the recent, wide deployment of machine learning-based systems, including deep neural networks (DNNs), is adversarial learning attacks. The main focus here is on evasion attacks against...
4.
Keltner J, Connolly C, Vaida F, Jenkinson M, Fennema-Notestine C, Archibald S, et al.
Pain Med
. 2016 Aug;
18(3):428-440.
PMID: 27497320
Objective: . Despite modern antiretroviral therapy, HIV-associated neuropathy is one of the most prevalent, disabling and treatment-resistant complications of HIV disease. The presence and intensity of distal neuropathic pain is...
5.
Qiu Z, Miller D, Kesidis G
IEEE Trans Neural Netw Learn Syst
. 2016 Feb;
28(4):917-933.
PMID: 26829808
We investigate semisupervised learning (SL) and pool-based active learning (AL) of a classifier for domains with label-scarce (LS) and unknown categories, i.e., defined categories for which there are initially no...
6.
Raghuram J, Miller D, Kesidis G
J Adv Res
. 2015 Feb;
5(4):423-33.
PMID: 25685511
We propose a method for detecting anomalous domain names, with focus on algorithmically generated domain names which are frequently associated with malicious activities such as fast flux service networks, particularly...
7.
Raghuram J, Miller D, Kesidis G
IEEE Trans Neural Netw Learn Syst
. 2014 Jul;
25(8):1520-37.
PMID: 25050949
A new method for semisupervised learning from pairwise sample (must- and cannot-link) constraints is introduced. It addresses an important limitation of many existing methods, whose solutions do not achieve effective...
8.
Keltner J, Fennema-Notestine C, Vaida F, Wang D, Franklin D, Dworkin R, et al.
J Neurovirol
. 2014 Feb;
20(3):209-18.
PMID: 24549970
Despite modern antiretroviral therapy, HIV-associated sensory neuropathy affects over 50 % of HIV patients. The clinical expression of HIV neuropathy is highly variable: many individuals report few symptoms, but about...
9.
An MRI-derived definition of MCI-to-AD conversion for long-term, automatic prognosis of MCI patients
Aksu Y, Miller D, Kesidis G, Bigler D, Yang Q
PLoS One
. 2011 Oct;
6(10):e25074.
PMID: 22022375
Alzheimer's disease (AD) and mild cognitive impairment (MCI) are of great current research interest. While there is no consensus on whether MCIs actually "convert" to AD, this concept is widely...
10.
Aksu Y, Miller D, Kesidis G, Yang Q
IEEE Trans Neural Netw
. 2010 Mar;
21(5):701-17.
PMID: 20194055
Feature selection for classification in high-dimensional spaces can improve generalization, reduce classifier complexity, and identify important, discriminating feature "markers." For support vector machine (SVM) classification, a widely used technique is...