David J. Miller

ORCID

Publication Activity (10 Years)

Years Active: 1992-2024
Publications (10 Years): 77

Top Venues

CoRR

MLSP

ICASSP

IEEE Trans. Neural Networks Learn. Syst.

Publications

Jayaram Raghuram, George Kesidis, David J. Miller
On Trojans in Refined Language Models. CoRR (2024)
Hang Wang, David J. Miller, George Kesidis
Post-Training Overfitting Mitigation in DNN Classifiers. CoRR (2023)
Xi Li, David J. Miller, Zhen Xiang, George Kesidis
A BIC-Based Mixture Model Defense Against Data Poisoning Attacks on Classifiers. MLSP (2023)
Hang Wang, David J. Miller, George Kesidis
Anomaly detection of adversarial examples using class-conditional generative adversarial networks. Comput. Secur. 124 (2023)
Hang Wang, Zhen Xiang, David J. Miller, George Kesidis
Improved Activation Clipping for Universal Backdoor Mitigation and Test-Time Detection. CoRR (2023)
Hang Wang, Sahar Karami, Ousmane Dia, Hippolyt Ritter, Ehsan Emamjomeh-Zadeh, Jiahui Chen, Zhen Xiang, David J. Miller, George Kesidis
Training Set Cleansing of Backdoor Poisoning by Self-Supervised Representation Learning. ICASSP (2023)
Xi Li, Zhen Xiang, David J. Miller, George Kesidis
Backdoor Mitigation by Correcting the Distribution of Neural Activations. CoRR (2023)
Zhen Xiang, David J. Miller, Siheng Chen, Xi Li, George Kesidis
Detecting Backdoor Attacks against Point Cloud Classifiers. ICASSP (2022)
Xi Li, Zhen Xiang, David J. Miller, George Kesidis
Test-Time Detection of Backdoor Triggers for Poisoned Deep Neural Networks. ICASSP (2022)
Zhen Xiang, David J. Miller, George Kesidis
Detection of Backdoors in Trained Classifiers Without Access to the Training Set. IEEE Trans. Neural Networks Learn. Syst. 33 (3) (2022)
Zhen Xiang, David J. Miller, George Kesidis
Post-Training Detection of Backdoor Attacks for Two-Class and Multi-Attack Scenarios. CoRR (2022)
Erik Meijering, Vince D. Calhoun, Gloria Menegaz, David J. Miller, Jong Chul Ye
Deep Learning in Biological Image and Signal Processing [From the Guest Editors]. IEEE Signal Process. Mag. 39 (2) (2022)
Zhen Xiang, David J. Miller, George Kesidis
Post-Training Detection of Backdoor Attacks for Two-Class and Multi-Attack Scenarios. ICLR (2022)
Hang Wang, Zhen Xiang, David J. Miller, George Kesidis
Universal Post-Training Backdoor Detection. CoRR (2022)
Hang Wang, S. Karami, O. Dia, H. Ritter, Ehsan Emamjomeh-Zadeh, J. Chen, Zhen Xiang, David J. Miller, George Kesidis
Training set cleansing of backdoor poisoning by self-supervised representation learning. CoRR (2022)
Xi Li, George Kesidis, David J. Miller, Maxime Bergeron, Ryan Ferguson, Vladimir Lucic
Robust and Active Learning for Deep Neural Network Regression. CoRR (2021)
Zhen Xiang, David J. Miller, Siheng Chen, Xi Li, George Kesidis
A Backdoor Attack against 3D Point Cloud Classifiers. ICCV (2021)
Zhen Xiang, David J. Miller, Siheng Chen, Xi Li, George Kesidis
A Backdoor Attack against 3D Point Cloud Classifiers. CoRR (2021)
Zhen Xiang, David J. Miller, Siheng Chen, Xi Li, George Kesidis
Detecting Backdoor Attacks Against Point Cloud Classifiers. CoRR (2021)
Hang Wang, David J. Miller, George Kesidis
Anomaly Detection of Test-Time Evasion Attacks using Class-conditional Generative Adversarial Networks. CoRR (2021)
Zhen Xiang, David J. Miller, Hang Wang, George Kesidis
Detecting Scene-Plausible Perceptible Backdoors in Trained DNNs Without Access to the Training Set. Neural Comput. 33 (5) (2021)
Zhen Xiang, David J. Miller, George Kesidis
Reverse engineering imperceptible backdoor attacks on deep neural networks for detection and training set cleansing. Comput. Secur. 106 (2021)
Zhen Xiang, David J. Miller, George Kesidis
L-Red: Efficient Post-Training Detection of Imperceptible Backdoor Attacks Without Access to the Training Set. ICASSP (2021)
Xi Li, Zhen Xiang, David J. Miller, George Kesidis
Test-Time Detection of Backdoor Triggers for Poisoned Deep Neural Networks. CoRR (2021)
Xi Li, George Kesidis, David J. Miller, Vladimir Lucic
Backdoor Attack and Defense for Deep Regression. CoRR (2021)
Xi Li, David J. Miller, Zhen Xiang, George Kesidis
A BIC based Mixture Model Defense against Data Poisoning Attacks on Classifiers. CoRR (2021)
David J. Miller, Zhen Xiang, George Kesidis
Adversarial Learning Targeting Deep Neural Network Classification: A Comprehensive Review of Defenses Against Attacks. Proc. IEEE 108 (3) (2020)
Zhen Xiang, David J. Miller, George Kesidis
L-RED: Efficient Post-Training Detection of Imperceptible Backdoor Attacks without Access to the Training Set. CoRR (2020)
Zhen Xiang, David J. Miller, George Kesidis
Reverse Engineering Imperceptible Backdoor Attacks on Deep Neural Networks for Detection and Training Set Cleansing. CoRR (2020)
Xi Li, David J. Miller, Zhen Xiang, George Kesidis
A Scalable Mixture Model Based Defense Against Data Poisoning Attacks on Classifiers. DDDAS (2020)
Zhen Xiang, David J. Miller, George Kesidis
Revealing Backdoors, Post-Training, in DNN Classifiers via Novel Inference on Optimized Perturbations Inducing Group Misclassification. ICASSP (2020)
Weiqiang Liu, Maximilian John, Andreas Karrenbauer, Adam Allerhand, Fabrizio Lombardi, Michael Shulte, David J. Miller, Zhen Xiang, George Kesidis, Antti Oulasvirta, Niraj Ramesh Dayama, Morteza Shiripour
Scanning the Issue. Proc. IEEE 108 (3) (2020)
Haoti Zhong, Cong Liao, Anna Cinzia Squicciarini, Sencun Zhu, David J. Miller
Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbation. CODASPY (2020)
Zhen Xiang, David J. Miller, Hang Wang, George Kesidis
Revealing Perceptible Backdoors in DNNs, Without the Training Set, via the Maximum Achievable Misclassification Fraction Statistic. MLSP (2020)
David J. Miller, Yujia Wang, George Kesidis
When Not to Classify: Anomaly Detection of Attacks (ADA) on DNN Classifiers at Test Time. Neural Comput. 31 (8) (2019)
Zhen Xiang, David J. Miller, George Kesidis
Revealing Perceptible Backdoors, without the Training Set, via the Maximum Achievable Misclassification Fraction Statistic. CoRR (2019)
Zhen Xiang, David J. Miller, George Kesidis
A Benchmark Study Of Backdoor Data Poisoning Defenses For Deep Neural Network Classifiers And A Novel Defense. MLSP (2019)
Zhen Xiang, David J. Miller, George Kesidis
Revealing Backdoors, Post-Training, in DNN Classifiers via Novel Inference on Optimized Perturbations Inducing Group Misclassification. CoRR (2019)
George Kesidis, David J. Miller
Notes on Lipschitz Margin, Lipschitz Margin Training, and Lipschitz Margin p-Values for Deep Neural Network Classifiers. CoRR (2019)
David J. Miller, Zhen Xiang, George Kesidis
Adversarial Learning in Statistical Classification: A Comprehensive Review of Defenses Against Attacks. CoRR (2019)
Hossein Soleimani, David J. Miller
Exploiting the value of class labels on high-dimensional feature spaces: topic models for semi-supervised document classification. Pattern Anal. Appl. 22 (2) (2019)
Haoti Zhong, Hao Li, Anna Cinzia Squicciarini, Sarah Michele Rajtmajer, David J. Miller
Toward Image Privacy Classification and Spatial Attribution of Private Content. IEEE BigData (2019)
Yujia Wang, David J. Miller, George Kesidis
When Not to Classify: Detection of Reverse Engineering Attacks on DNN Image Classifiers. ICASSP (2019)
Haoti Zhong, Anna Cinzia Squicciarini, David J. Miller
Toward Automated Multiparty Privacy Conflict Detection. CIKM (2018)
David J. Miller, Yujia Wang, George Kesidis
Anomaly Detection of Attacks (Ada) on DNN Classifiers at Test Time. MLSP (2018)
Cong Liao, Haoti Zhong, Anna Cinzia Squicciarini, Sencun Zhu, David J. Miller
Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbation. CoRR (2018)
Zhen Xiang, David J. Miller
Locally optimal, delay-tolerant predictive source coding. CISS (2018)
Chia-Hsiang Lin, Chong-Yung Chi, Lulu Chen, David J. Miller, Yue Wang
Detection of Sources in Non-Negative Blind Source Separation by Minimum Description Length Criterion. IEEE Trans. Neural Networks Learn. Syst. 29 (9) (2018)
David J. Miller, George Kesidis, Zhicong Qiu
Unsupervised Parsimonious Cluster-Based Anomaly Detection (PCAD). MLSP (2018)
Yujia Wang, David J. Miller, George Kesidis
When Not to Classify: Detection of Reverse Engineering Attacks on DNN Image Classifiers. CoRR (2018)
David J. Miller, Xinyi Hu, Zhen Xiang, George Kesidis
A Mixture Model Based Defense for Data Poisoning Attacks Against Naive Bayes Spam Filters. CoRR (2018)
Haoti Zhong, David J. Miller, Anna Cinzia Squicciarini
Flexible Inference for Cyberbully Incident Detection. ECML/PKDD (3) (2018)
Zhicong Qiu, David J. Miller, George Kesidis
Flow based botnet detection through semi-supervised active learning. ICASSP (2017)
David J. Miller, Xinyi Hu, Zhicong Qiu, George Kesidis
Adversarial Learning: A Critical Review and Active Learning Study. CoRR (2017)
Haoti Zhong, Anna Cinzia Squicciarini, David J. Miller, Cornelia Caragea
A Group-Based Personalized Model for Image Privacy Classification and Labeling. IJCAI (2017)
David J. Miller, Xinyi Hu, Zhicong Qiu, George Kesidis
Adversarial learning: A critical review and active learning study. MLSP (2017)
Yuquan Shan, Chiara Lo Prete, George Kesidis, David J. Miller
A simulation framework for uneconomic virtual bidding in day-ahead electricity markets. ACC (2017)
Zhicong Qiu, David J. Miller, George Kesidis
A Maximum Entropy Framework for Semisupervised and Active Learning With Unknown and Label-Scarce Classes. IEEE Trans. Neural Networks Learn. Syst. 28 (4) (2017)
Hossein Soleimani, David J. Miller
Semisupervised, Multilabel, Multi-Instance Learning for Structured Data. Neural Comput. 29 (4) (2017)
David J. Miller, Yujia Wang, George Kesidis
When Not to Classify: Anomaly Detection of Attacks (ADA) on DNN Classifiers at Test Time. CoRR (2017)
Yinxue Wang, Guilai Shi, David J. Miller, Yizhi Wang, Congchao Wang, Gerard Broussard, Yue Wang, Lin Tian, Guoqiang Yu
Automated Functional Analysis of Astrocytes from Chronic Time-Lapse Calcium Imaging Data. Frontiers Neuroinformatics 11 (2017)
Hossein Soleimani, David J. Miller
Exploiting the value of class labels in topic models for semi-supervised document classification. IJCNN (2016)
Hossein Soleimani, David J. Miller
ATD: Anomalous Topic Discovery in High Dimensional Discrete Data. IEEE Trans. Knowl. Data Eng. 28 (9) (2016)
Yizhi Wang, David J. Miller, Kira Poskanzer, Yue Wang, Lin Tian, Guoqiang Yu
Graphical Time Warping for Joint Alignment of Multiple Curves. NIPS (2016)
Yinxue Wang, Guilai Shi, David J. Miller, Yizhi Wang, Gerard Broussard, Yue Wang, Lin Tian, Guoqiang Yu
FASP: A machine learning approach to functional astrocyte phenotyping from time-lapse calcium imaging data. ISBI (2016)
Hossein Soleimani, David J. Miller
Semi-supervised Multi-Label Topic Models for Document Classification and Sentence Labeling. CIKM (2016)
Yuquan Shan, Chiara Lo Prete, George Kesidis, David J. Miller
A simulation framework for uneconomic virtual bidding in day-ahead electricity markets: Short talk. SIGMETRICS Perform. Evaluation Rev. 44 (3) (2016)
Haoti Zhong, Hao Li, Anna Cinzia Squicciarini, Sarah Michele Rajtmajer, Christopher Griffin, David J. Miller, Cornelia Caragea
Content-Driven Detection of Cyberbullying on the Instagram Social Network. IJCAI (2016)
George Kesidis, David J. Miller, Zhicong Qiu
IP-level fast re-routing for robustness to mass failure events using a hybrid bandwidth and reliability cost metric. MILCOM (2016)
Zhicong Qiu, David J. Miller, George Kesidis
Detecting clusters of anomalies on low-dimensional feature subsets with application to network traffic flow data. MLSP (2015)
Hossein Soleimani, David J. Miller
ATD: Anomalous Topic Discovery in High Dimensional Discrete Data. CoRR (2015)
Aditya Kurve, David J. Miller, George Kesidis
Multicategory Crowdsourcing Accounting for Variable Task Difficulty, Worker Skill, and Worker Intention. IEEE Trans. Knowl. Data Eng. 27 (3) (2015)
Yuquan Shan, Jayaram Raghuram, George Kesidis, David J. Miller, Anna Scaglione, Jeff Rowe, Karl N. Levitt
Generation bidding game with potentially false attestation of flexible demand. EURASIP J. Adv. Signal Process. 2015 (2015)
Hossein Soleimani, David J. Miller
Parsimonious Topic Models with Salient Word Discovery. IEEE Trans. Knowl. Data Eng. 27 (3) (2015)
David J. Miller, Hossein Soleimani
On an Objective Basis for the Maximum Entropy Principle. Entropy 17 (1) (2015)
Zhicong Qiu, David J. Miller, George Kesidis
Detecting Clusters of Anomalies on Low-Dimensional Feature Subsets with Application to Network Traffic Flow Data. CoRR (2015)
Aditya Kurve, Christopher Griffin, David J. Miller, George Kesidis
Optimizing cluster formation in super-peer networks via local incentive design. Peer-to-Peer Netw. Appl. 8 (1) (2015)
Jayaram Raghuram, George Kesidis, Christopher Griffin, Karl N. Levitt, David J. Miller, Jeff Rowe, Anna Scaglione
A Bidding Game for Generators in the Presence of Flexible Demand. Feedback Computing (2014)
Jayaram Raghuram, David J. Miller, George Kesidis
Instance-Level Constraint-Based Semisupervised Learning With Imposed Space-Partitioning. IEEE Trans. Neural Networks Learn. Syst. 25 (8) (2014)
Yuquan Shan, Jayaram Raghuram, George Kesidis, Christopher Griffin, Karl N. Levitt, David J. Miller, Jeff Rowe, Anna Scaglione
Generation bidding game with flexible demand. CoRR (2014)
Fatih Kocak, David J. Miller, George Kesidis
Detecting anomalous latent classes in a batch of network traffic flows. CISS (2014)
Hossein Soleimani, David J. Miller
Sparse topic models by parameter sharing. MLSP (2014)
Hossein Soleimani, David J. Miller
Parsimonious Topic Models with Salient Word Discovery. CoRR (2014)
Anuj R. Jaiswal, David J. Miller, Prasenjit Mitra
Schema matching and embedded value mapping for databases with opaque column names and mixed continuous and discrete-valued data fields. ACM Trans. Database Syst. 38 (1) (2013)
Aditya Kurve, David J. Miller, George Kesidis
Multicategory Crowdsourcing Accounting for Plurality in Worker Skill and Intention, Task Difficulty, and Task Heterogeneity. CoRR (2013)
Aditya Kurve, David J. Miller, George Kesidis
Defeating Tyranny of the Masses in Crowdsourcing: Accounting for Low-Skilled and Adversarial Workers. GameSec (2013)
Jianping He, David J. Miller, George Kesidis
Latent Interest-Group Discovery and Management by Peer-to-Peer Online Social Networks. SocialCom (2013)
Xiguo Yuan, David J. Miller, Junying Zhang, David M. Herrington, Yue Wang
An Overview of Population Genetic Data Simulation. J. Comput. Biol. 19 (1) (2012)
Bai Zhang, David J. Miller, Yue Joseph Wang
Nonlinear System Modeling With Random Matrices: Echo State Networks Revisited. IEEE Trans. Neural Networks Learn. Syst. 23 (1) (2012)
David J. Miller, Fatih Kocak, George Kesidis
Sequential anomaly detection in a batch with growing number of tests: Application to network intrusion detection. MLSP (2012)
Jayaram Raghuram, David J. Miller, George Kesidis
Semisupervised domain adaptation for mixture model based classifiers. CISS (2012)
David J. Miller, Jayaram Raghuram, George Kesidis, Christopher M. Collins
Improved Generative Semisupervised Learning Based on Finely Grained Component-Conditional Class Labeling. Neural Comput. 24 (7) (2012)
Tülay Adali, David J. Miller, Konstantinos I. Diamantaras, Jan Larsen
Trends in Machine Learning for Signal Processing [In the Spotlight]. IEEE Signal Process. Mag. 28 (6) (2011)
Guixi Zou, George Kesidis, David J. Miller
A Flow Classifier with Tamper-Resistant Features and an Evaluation of Its Portability to New Domains. IEEE J. Sel. Areas Commun. 29 (7) (2011)
Z. Berkay Celik, Jayaram Raghuram, George Kesidis, David J. Miller
Salting Public Traces with Attack Traffic to Test Flow Classifiers. CSET (2011)
J. Daniel Park, David J. Miller, John F. Doherty, Stephen C. Thompson
Feasibility of range estimation using sonar LPI. CISS (2010)
Yaman Aksu, David J. Miller, George Kesidis, Qing X. Yang
Margin-maximizing feature elimination methods for linear and nonlinear kernel-based discriminant functions. IEEE Trans. Neural Networks 21 (5) (2010)
Scott C. Markley, David J. Miller
Joint Parsimonious Modeling and Model Order Selection for Multivariate Gaussian Mixtures. IEEE J. Sel. Top. Signal Process. 4 (3) (2010)
Anuj R. Jaiswal, David J. Miller, Prasenjit Mitra
Uninterpreted Schema Matching with Embedded Value Mapping under Opaque Column Names and Data Values. IEEE Trans. Knowl. Data Eng. 22 (2) (2010)
David J. Miller, Chu-Fang Lin, George Kesidis, Christopher M. Collins
Improved Fine-Grained Component-Conditional Class Labeling with Active Learning. ICMLA (2010)

David J. Miller.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

David J. Miller