Photo of David Miller

David Miller

Professor

Affiliation(s):

  • School of Electrical Engineering and Computer Science
  • Electrical Engineering

227C Electrical Engineering West

djm25@psu.edu

814-865-6510

Research Areas:

Data Science and Artificial Intelligence; Signal and Image Processing

Interest Areas:

Signal processing

 
 

 

Education

Publications

Journal Articles

  • Kamyar Roshan, David J Miller and Andre Van Duin, 2023, "Optimization of ReaxFF reactive force field parameters for Cu/Si/O systems via neural network inversion with application to Copper Oxide interaction with Silicon", Journal of Physical Chemistry
  • David J Miller, Hang Wang and George Kesidis, 2023, "Anomaly detection of adversarial examples using class-conditional generative adversarial networks", Computers and Security
  • Zhen J Xiang, David J Miller and George Kesidis, 2021, "Reverse engineering imperceptible backdoor attacks on deep neural networks for detection and training set cleansing", Computers and Security
  • David J Miller, Zhen Xiang, Hang Wang and George Kesidis, 2021, "Revealing perceptible backdoors, without the training set, via the maximum achievable miclassification fraction statistic", Neural Computation
  • David J Miller, Najah Ghalyan, Sudeepta Mondal and Asok Ray, 2021, "HMM conditional-likelihood based change detection with strict delay tolerance", Mechanical Systems and Signal Processing
  • David J Miller, George Kesidis and Yujia Wang, 2020, "Adversarial learning in statistical classification: a comprehensive review of attacks and defenses", Proceedings of the IEEE
  • Guoqiang Yu and David J Miller, 2019, "Asymmetric independence modeling for identifying novel gene-environment interactions", Scientific Reports
  • Aotian Wang, David J Miller, Qin P andng, , 2019, "Constrained maximum entropy models to select genotype interactions associated with censored failure times", Journal of Bioinformatics and Computational Biology
  • David J Miller, 2019, "When not to classify: anomaly detection of attacks on DNNs at test time"
  • Najah Ghalyan, David J Miller and Asok Ray, 2019, "Hidden Markov model based decision-making using short-length time series"
  • David J Miller, Yinxue Wang, Guoqiang andYu, , 2017, "Automated functional analysis of astrocytes from chronic time-lapse calcium imaging data", Frontiers in Neuroinformatics
  • David J Miller and Hossein Soleimani, 2017, "Exploiting the value of class labels on high-dimensional feature spaces: topic models for semi-supervised document classification", Pattern Analysis and Applications
  • Hossein Soleimani and David J Miller, 2016, "ATD: Anomalous topic discovery in high dimensional discrete data", IEEE Trans. on Knowledge and Data Engineering
  • John Keltner and David J Miller, 2016, "HIV distal neuropathic pain is associated with smalle ventral posterior cingulate cortex", Pain Medicine
  • Haoti Zhong, David J Miller and Ken Urish, 2016, "T2 map signal variation predicts symptomatic osteoarthritis progression: data from the osteoarthritis initiative", Skeletal Radiology
  • Zhicong Qiu, David J Miller and George Kesidis, 2016, "A maximum entropy framework for semisupervised and active learning with unknown and label-scarce classes", IEEETrans. on Neural Networks and Learning Systems
  • A. Kurve, David J Miller and G. Kesidis, 2015, "Multicategory crowdsourcing accounting for variable task difficulty, worker skill, and worker intention", IEEE Trans. on Knowledge and Data Engineering
  • David J Miller and H. Soleimani, 2015, "On an Objective Basis for the Maximum Entropy Principle", Entropy
  • Hossein Soleimani and David Miller, 2015, "Parsimonious Topic Models with Salient Word Discovery", IEEE Trans. on Knowledge and Data Engineering
  • Zhiqiang Guo, Huaiqing Wang, Jie Yang and David J. Miller, 2015, "A Stock Market Forecasting Model Combining Two-directional Two-dimensional Principal Component Analysis and Radial Basis Function Neural Network", PloS One
  • Yuquan Shan, Jayaram Raghuram, George Kesidis, David J Miller and Anna Scaglione, 2015, "Generation bidding game with potentially false attestation of flexible demand", EURASIP Journal on advances in signal Processing
  • Zhicong Qiu, David Miller and George Kesidis, 2015, "Semisupervised and active learning with unknown and label-scarce categories", IEEE Transactions on Neural Networks and Learning Systems
  • John Keltner, George Kesidis and David Miller, 2015, "HIV Distal Neuropathic Pain is associated with Smaller Ventral Posterior Cingulate Cortex", Pain Medicine
  • J. Raghuram, David J Miller and G. Kesidis, 2014, "Unsupervised, low latency anomaly detection of algorithmically generated domain names by generative probabilistic modeling", Journal of Advanced Research
  • John R. Keltner, Christine Fennema-Notestine, Florin Vaida, Dongzhe Wang, Donald R. Franklin, Robert H. Dworkin, Chelsea Sanders, J. Allen McCutchan, Sarah L. Archibald, David J Miller, George Kesidis, Clint Cushman, Sung Min Kim, Ian Abramson, Michael J. Taylor, Rebecca J. Theilmann, Michelle D. Julaton, Randy J. Notestine, Stephanie Corkran, Mariana Cherner, Nichole A. Duarte, Terry Alexander, Jessica Robinson-Rapp, Benjamin B. Gelman, David M. Simpson, Ann C. Collier, Christina M. Marra, Susan Morgello, Greg Brown, Igor Grant, J. Hampton Atkinson, Terry L. Jernigan and Rongald J. Ellis, 2014, "HIV-associated distal neuropathic pain is associated with smaller total cerebral cortical gray matter", J Neurovirol, 20, (3), pp. 209-18
  • A. Kurve, C. Griffin, David J Miller and G. Kesidis, 2014, "Optimizing Cluster Formation in Super-Peer Networks via Local Incentive Design", Journal of Peer-to-Peer Networking and Applications
  • A. Jaiswal, David J Miller and P. Mitra, 2013, "Schema Matching and embedded value mapping for databases with opaque column names and mixed continuous and discrete-valued data fields", ACM Transactions on Database Systems, 38, pp. 1-34
  • David J Miller, J. Raghuram, G. Kesidis and C. Collins, 2012, "Improved Generative Semisupervised Learning Based on Fine-Grained Component-Conditional Class Labeling", Neural Computation, pp. 1926-1966
  • X. Yuan, David J Miller, J. Zhang, D. Herrington and Y. Wang, 2012, "An overview of population genetic data simulation", Journal of Computational Biology
  • B. Zhang, David J Miller and Y. Wang, 2012, "Nonlinear system modeling with random matrices: echo state networks revisited", IEEE Transactions on Neural Networks
  • T. Adali, David J Miller, K. Diamantaras and J. Larsen, 2011, "Trends in Machine Learning for Signal Processing", IEEE Signal Processing Magazine
  • G. Zou, G. Kesidis and David J Miller, 2011, "A flow classifier with tamper-resistant features and an evaluation of its portability to a new domain", IEEE Journal on Select Areas in Communications
  • L. Chen, G. Yu, C. Langefeld and David J Miller, 2011, "Comparative analysis of methods for detecting interacting loci", BMC Bioinformatics
  • Y. Aksu, David J Miller, G. Kesidis, D. Bigler and Q. Yang, 2011, "An MRI-derived definition of MCI-to-AD conversion for long-term, automatic prognosis of MCI patients", PloS One
  • S. Markley and David J Miller, 2010, "Joint Parsimonious Modeling and Model Order Selection for Multivariate Gaussian Mixtures", IEEE Journal on Select Areas in Signal Processing, special issue on model selection, pp. 548-559
  • Y. Aksu, David J Miller and G. Kesidis, 2010, "Margin-Maximizing Feature Elimination Methods for Linear and Nonlinear Kernel-Based Discriminant Functions", IEEE Trans. on Neural Networks, pp. 701-717
  • A. Jaiswal, David J Miller and P. Mitra, 2010, "Uninterpreted schema matching with embedded value mapping under opaque column names and data values", IEEE Trans. on Knowledge and Data Engineering, pp. 291-304
  • Guoqiang Yu, Yuanjian Feng, David J Miller, Jinahua Xuan, Eric P. Hoffman, Robert Clarke, Ben Davidson, Ie-Ming Shih and Yue Wang, 2010, "Matched gene selection and committee classifier for molecular classification of heterogeneous diseases", Journal of Machine Learning Research
  • D. Bigler, Y. Aksu, David J Miller and Q. Yang, 2009, "STAMPS: software tool for automated MRI post-processing on a supercomputer", Computer methods and programs in biomedicine, pp. 146-157
  • David J Miller and Y. Zhang, 2009, "An algorithm for learning maximum entropy probability models of disease risk that efficiently searches and sparingly encodes multilocus genomic interactions", Bioinformatics
  • David J Miller, Y. Wang and G. Kesidis, 2008, "Emergent unsupervised clustering paradigms with potential application to bioinformatics", Frontiers in Bioscience, 13, pp. 677-690
  • Y. Zhu, Z. Wang, Y. Feng, J. Xuan and David J Miller, 2008, "A ground truth based comparative study on clustering of gene expression data", Frontiers in Bioscience
  • Y. Wang, David J Miller and R. Clarke, 2008, "Approaches to working in high-dimensional data spaces: gene expression microarrays", British Journal of Cancer, MinReview, pp. 6
  • David J Miller, S. Pal and Y. Wang, 2008, "Extensions of transductive learning for distributed ensemble classification and application to biometric authentication", Neurocomputing
  • Y. Zhu, Huai Li, David J Miller, Zuyi Wang, Jianhua Xuan, Robert Clarke, Eric P. Hoffman and Yue Wang, 2008, "caBIG VISDA: modeling, visualization, and discovery for cluster analysis of genomic data", BMC Bioinformatic
  • David J Miller, Y. Zhang and G. Kesidis, 2008, "Decision aggregation in distributed classification by a transductive extension of maximum entropy/improved iterative scaling", EURASIP Journal on Advances in Signal Processing
  • David J Miller and S. Pal, 2007, "Transductive methods for distributed ensemble classification", Neural Computation, pp. 856-884
  • David Bazell, David J Miller and Mark Subbaro, 2006, "Objective subclass determination of Sloan digital sky survey unknown spectral objects", The Astrophysics Journal, 649, (2), pp. 678-691
  • Jisheng Wang, David J Miller and George Kesidis, 2006, "Efficient mining of the multidimensional traffic cluster hierarchy for digesting, visualization, and anomaly identification", IEEE Journal on Selected Areas in Communications, Special issue on High-speed Network Security, 24, (10), pp. 1929-1941
  • Michael W. Graham and David J Miller, 2006, "Unsupervised learning of parsimonious mixtures on large spaces with integrated feature and component selection", IEEE Transactions on Signal Processing, 54, (4), pp. 1289-1303
  • Qi Zhao and David J Miller, 2005, "Mixture modeling with pairwise instance-level class constraints", Neural Computation, 17, (11), pp. 2482-2507
  • Yitan Zhu and David J Miller, , "Convex analysis of mixtures for separating non-negative well-grounded sources", Scientific Reports
  • Hossein Soleimani and David J Miller, , "Semi-supervised multi-label multi-instance learning for structured data", Neural Computation
  • David J Miller, Najah Ghalyan, Asok anday, , , "A locally algorithm for estimating a generating partition from an observed time series and its application to anomaly detection", Neural Computation
  • David J Miller, Chi-Hsiang Lin, Lulu Chen, Chong-Yung Chi, Yue W andng, , , "Detection of sources in non-negative blind source separation by minimum description length criterion", IEEE Trans. on Neural Networks and Learning Systems
  • David J Miller, Zhen Xiang and George Kesidis, , "Revealing backdoors post-training in DNN classifiers via optimized perturbations inducing group misclassification", IEEE Transactions on Neural Networks for Learning Systems
  • Xi Li, David J Miller and George Kesidis, , "A BIC-based Mixture Model Defense against Data Poisoning Attacks on Classifiers", IEEE Transactions on Knowledge and Data Engineering

Conference Proceedings

  • Xi Li, Zhen Xiang, David J Miller and George Kesidis, 2023, "A BIC-based Mixture Model Defense against Data Poisoning Attacks on Classifiers"
  • Hang Wang, David J Miller, George Kesidis and Sahar Karimi, 2023, "Training set cleansing of backdoor poisoning by self-supervised representation learning"
  • Zhen Xiang, David J Miller and George Kesidis, 2022, "Post-Training Detection of Backdoor Attacks for Two-Class and Multi-Attack Scenarios"
  • Xi Li, David J Miller and George Kesidis, 2022, "Test-time detection of backdoor triggers for poisoned deep neural networks"
  • Zhen Xiang, David J Miller, S. Chen, Xi Li and George Kesidis, 2021, "A backdoor attack against 3D point cloud classifiers"
  • Zhen Xiang, David J Miller and George Kesidis, 2021, "L-RED: Efficient post-training detection of imperceptible backdoor attacks without access to the training set"
  • Alex Ororbia, David J Miller and Lee Giles, 2019, "Learned iterative decoding for lossy image compression systems"
  • Zhen Xiang, David J Miller and George Kesidis, 2019, "A benchmark study of backdoor data poisoning defenses for deep neural network classifiers"
  • Yujia Wang, David J Miller and George Kesidis, 2019, "When not to classify: detection of reverse engineering attacks on DNN image classifiers"
  • Haoti Zhong, David J Miller and Anna Squicciarini, 2019, "Toward image privacy classification and spatial attribution of private content"
  • David J Miller and George Kesidis, 2018, "Unsupervised parsimonious cluster-based anomaly detection (PCAD)"
  • Haoti Zhong, Anna Squicciarini and David J Miller, 2018, "Toward automated multiparty privacy conflict detection"
  • David J Miller, Zhen Xi andng, , 2018, "Locally optimal predictive source coding", Conference on Information Sciences and Systems (CISS)
  • David J Miller, Haoti Zhong, Anna Squicciar andni, , 2017, "A group-based personalized model for image privacy classification and labeling", International Joint Conference on Artificial Intelligence
  • David J Miller, Najah Ghalyan, Asok anday, , 2017, "A locally optimal algorithm for estimating a generating partition from an observed time series"
  • David J Miller, Xinyi Hu, Zhicong Qiu, George Kesi andis, , 2017, "Adversarial learning: a review and experimental study"
  • Zhicong Qiu, David J Miller and George Kesidis, 2017, "Flow-based botnet detection through semisupervised active learning"
  • Yuquan J Shan, Chiara Lo Prete, David J Miller and George Kesidis, 2016, "A simulation framework for uneconomic virtual bidding in day-ahead electricity markets", ACM Sigmetrics performance evaluation review
  • Hossein Soleimani and David J Miller, 2016, "Semi-supervised multi-label topic models for document classification and sentence labeling", CIKM (acceptance rate 18%)
  • Hossein Soleimani and David J Miller, 2016, "ATD: Anomalous topic discovery in high dimensional discrete data"
  • Haoti Zhong, David J Miller and Anna Squicciarini, 2016, "Content-driven detection of cyberbullying on the instagram social network"
  • Hossein Soleimani and David J Miller, 2016, "Increasing the value of class labels in semisupervised topic modeling", IJCNN
  • G. Shi, David Miller, Yizhi Wang, Gerard Broussard, Yue Wang, Lin Tian, Guoqiang andYu, , 2015, ""FASP: A Machine Learning Approach to Functional Astrocyte Phenotyping from Time-Lapse Calcium Imaging Data"
  • Zhicong Qiu, David Miller and George Kesidis, 2015, "Detecting clusters of anomalies on low-dimensional feature subsets with application to network traffic flow data,"
  • J. Raghuram, G. Kesidis, David J Miller, K. Levitt, J. Rowe and A. Scaglione, 2014, "Generation bidding game with flexible demand", 9th International workshop on feedback computing
  • Zhicong Qiu, David J Miller, Brian Stieber and Tim Fair, 2014, "Actively learning to distinguish suspicious from innocuous anomalies in a batch of vehicle tracks", SPIE
  • G. Jin, R. Raich and David J Miller, 2013, "A generative semisupervised model for multi-view learning when some views are label free", ICASSP
  • H. Chen, David J Miller and C. L. Giles, 2013, "How a link ages over time in a coauthorship network", dbSocial
  • F. Kocak, David J Miller and G. Kesidis, 2013, "An Algorithm for Detecting Anomalous Latent Classes in a Batch of Network Traffic Flows", Conf. on Info. Sciences and Systems, Princeton
  • A. Kurve, David J Miller and G. Kesidis, 2013, "Defeating Tyranny of the Masses: Semisupervised Multicategory Crowdsourcing Accounting for Worker Skill and Intention, Task Difficulty, and Task Heterogeneity", Proc. GameSec (Security Games)
  • Jianping He, David J Miller and George Kesidis, 2013, "Latent interest group discovery and management by peer-to-peer online social networks", Proc. ASE/IEEE SocialCom
  • David J Miller, F. Kocak and G. Kesidis, 2012, "Sequential anomaly detection in a batch with growing number of tests: application to network intrusion detection", IEEE Workshop on Machine Learning for Signal Processing
  • J. Raghuram, David J Miller and G. Kesidis, 2012, "Semisupervised domain adaptation for mixture model based classifiers", Conf. on Info. Sciences and Systems
  • A. Natraj, David J Miller and K. Sullivan, 2012, "Anomaly detection driven active learning for identifying suspicious trakcs and events in WAMI video", SPIE Defense, Security, and Sensing
  • B. Celik, J. Raghuram, G. Kesidis and David J Miller, 2011, "Salting public traces with attack traffic to test flow classifiers", Proc. Usenix Cyber Security Experimentation and Test Workshop
  • David J Miller, C. Lin, G. Kesidis and C. Collins, 2010, "Improved fine-grained component-conditional class labeling with active learning", Intl. Conf. on Machine Learning and Applications, pp. 1-6
  • L. Chen, G. Yu, David J Miller, L. Song, C. Langefeld, D. Herrington, Y. Liu and Y. Wang, 2009, "A Ground Truth Based Comparative Study on Detecting Epistatic SNPs", Proc. IEEE Intl Conf. on Bioinformatics & Biomedicine
  • J. Park, David J Miller, J. F. Doherty and S. Thompson, 2009, "A study on the feasibility of low probability of intercept sonar", Conf. on Info. Sciences and Systems
  • David J Miller, C. Lin, G. Kesidis and C. Collins, 2009, "Semisupervised mixture modeling with fine-grained component-conditional class labeling and transductive inference", IEEE Workshop on Machine Learning for Signal Processing
  • David J Miller, Y. Zhang and G. Kesidis, 2008, "A transductive extension of maximum entropy/iterative scaling for decision aggregation in distributed classification", ICASSP 2008
  • Y. Aksu, David J Miller and G. Kesidis, 2008, "Margin-based feature selection techniques for support vector machine classification", Proc.of IEEE Workshop on Cognitive Information Processing (CIP)
  • Y. Zhang, Y. Aksu, G. Kesidis, David J Miller and Y. Wang, 2008, "SVM margin-based feature elimination applied to high-dimensional DNA microarray data", IEEE Workshop on Machine Learning for Signal Processing
  • J. Wang, G. Kesidis and David J Miller, 2007, "New directions iin covert malware modeling which exploit while-listing", Proc. IEEE Sarnoff Symposium on Comunications
  • Y. Aksu, G. Kesidis and David J Miller, 2007, "Scalable, efficient, stepwise-optimal feature elimination in support vector machines", Proc. of IEEE Workshop on Machine Learning for Signal Processing
  • A. Nag, David J Miller, A. Brown and K. Sullivan, 2007, "Combined generative-dscriminative learning for object recognition using local image descriptors", Proc. IEEE Workshop on Machine Learning for Signal Processing
  • David J Miller, Siddharth Pal and Yue Wang, 2006, "Constraint-based transductive learning for distributed ensemble classification", IEEE Workshop on Machine Learning for Signal Processing, pp. 15-20
  • Jisheng Wang, David J Miller and George Kesidis, 2006, "Multidimensional flow mining for digesting, visualization, and signature extraction", DETER Community Workshop
  • David J Miller and Siddharth Pal, 2006, "Transductive methods for distributed ensemble classification", Conference on Information Sciences and Systems, pp. 1605-1610
  • Jisheng Wang, Ihab Hamadeh, George Kesidis and David J Miller, 2006, "Polymorphic worm detection and defense: system design, experimental methodology, and data resources", SIGCOMM Workshop on Large Scale Attack Defense (LSAD)
  • Andrew Brown, Kevin Sullivan and David J Miller, 2006, "Feature-aided multiple target tracking in the image plane", Proc. of the SPIE, Intelligent Computing: Theory and Applications IV, 6229, pp. 62290Q
  • Qi Zhao and David J Miller, 2005, "Semisupervised learning of mixture models with class constraints", IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), MMLSP-L2.1
  • David J Miller, Siddharth Pal and Qi Zhao, 2005, "A latent variable extension of iterative scaling for classification on continuous and mixed continuous-discrete feature spaces", Conf. on Info. Sciences and Systems (CISS), TA2-7
  • David J Miller and Siddharth Pal, 2005, "An extension of iterative scaling for joint decision-level and feature-level fusion in ensemble classification", IEEE Workshop on Machine Learning for Signal Processing, pp. 61-66
  • Zhen Xiang, David J Miller, S. Chen, Xi Li and George Kesidis, , "Detecting backdoor attacks against point cloud classifiers"
  • Cong Liao, Haoti Zhong, Sencun Zhu, Anna Squicciarini and David J Miller, , "DeepDoor: targeted attack against convolutional neural networks via stealthy backdoor injection"

Manuscripts

  • Hang Wang, Zhen Xiang, David J Miller and George Kesidis, 2024, "MM-BD: post-training detection of backdoor attacks with arbitrary backdoor pattern types using a maximum margin statistic"
  • Abhikesh Nag, David J Miller, Andrew Brown and Kevin Sullivan, , "A system for vehicle recognition in video based on SIFT features, mixture models, and support vector machines"
  • Y. Feng, Z. Wang, Y. Zhu, J. Xuan, David J Miller, R. Clarke, E. Hoffman and Y. Wang, , "Learning the tree of phenotype using genomic data and VISDA", IEEE Symposium on Bioinformatics and Bioengineering
  • David J Miller and Siddharth Pal, , "An extension of iterative scaling for decision and data aggregation in ensemble classification", Journal of VLSI Signal Processing Systems, special issue on MLSP2005
  • K. L. Urish, C. R. Chu, J. R. Durkin, M. G. Keffalas, David J Miller and Timothy J. Mosher, , "T2 texture index of cartilage can predict early symptomatic OA progression: data from the osteoarthritis initiative", The Journal of Bone and Joint Surgery
  • J. Raghuram, David J Miller and G. Kesidis, , "Instance-Level Constraint Based Semi-supervised Learning With Imposed Space-Partitioning", IEEE Transactions on Neural Networks and Learning Systems
  • J. Raghuram, David J Miller and G. Kesidis, , "A space partitioning solution for semisupervised learning with instance-level constraints", IEEE Transactions on Neural Networks-Learning Systems

Research Projects

Honors and Awards

Service

Service to Penn State:

Service to External Organizations:

 


 

About

The School of Electrical Engineering and Computer Science was created in the spring of 2015 to allow greater access to courses offered by both departments for undergraduate and graduate students in exciting collaborative research fields.

We offer B.S. degrees in electrical engineering, computer science, computer engineering and data science and graduate degrees (master's degrees and Ph.D.'s) in electrical engineering and computer science and engineering. EECS focuses on the convergence of technologies and disciplines to meet today’s industrial demands.

School of Electrical Engineering and Computer Science

The Pennsylvania State University

207 Electrical Engineering West

University Park, PA 16802

814-863-6740

Department of Computer Science and Engineering

814-865-9505

Department of Electrical Engineering

814-865-7667