profile image

Taha Belkhouja

Ph.D. in Computer Science

(Last Update: April 2024)

About Me

I obtained my Ph.D. in Computer Science at Washington State University where I was advised by Professor Jana Doppa. My general research interests are in the area of robust and trustworthy machine learning. My research focuses on developing efficient algorithms and theory to improve reliability and safety of deep learning algorithms for diverse problem settings and data domains. My current work includes:

  • Robustness and reliability of deep learning models for the time-series domain with diverse applications including mobile health, smart grid management, human activity monitoring, and agriculture automation.
  • Trustworthy machine learning for sequential data.
  • Uncertainty quantification for robust and effective Human-ML collaborative systems using conformal prediction.

Current Research Projects

Adversarial Robustness against Time-Series Perturbations

There is significant growth in the Internet of Things (IoT), mobile applications and data analytics which are based on predictive models over time-series data collected from various sources. Some important applications include smart home automation, mobile health, smart grid management, and finance. Safe and reliable deployment of such machine learning (ML) systems require the ability to be robust to adversarial/natural perturbations to time-series data.

*Depiction of real-world data affected by noise.

When the data collected is distorted, is the commonly used Minkowski distance appropriate to compare the similarity of the signals? Time-series perturbations such as time-shifts and frequency-distortion affect significantly the ability of the ML model to classify correctly the input. How can we enhance the robustness of these classifiers using adversarial perturbations and appropriate similarity measures between time-series instances?
Related papers: TSA-STAT (JAIR'22) & DTW-AR (TPAMI'22)

*Depiction of real-world data affected by sensor rotation.

Time-series data acquisition is prone to natural perturbations (such as hardware orientation or amplified noise) that affect significantly the data. Such distortion yields signals that are dissimilar according to Minkowski distances. On the other hand, elastic measures are very expensive to compute. Therefore, how can we enhance the robustness of deep models during training to recognize correctly the distorted inputs?
Related papers: RO-TS (AAAI'22) & StatOpt (ICCAD'22)

Out-Of-Distribution (OOD) Detection for Safety-Critical Application

One of the failure scenarios in the AI safety domain is confident predictions on Out-Of-Distribution (OOD) examples, essentially for real-world contexts with low tolerance for error. Such examples, not observed during the training phase or outside the intended context of deployment, pose a significant risk of leading to unsafe decision-making outcomes. OOD detectors have the potential of achieving AI systems capable of functioning reliably when presented with these unforeseen examples and improves the predictive uncertainty of deep-learning models.
Related papers: SR Score (TIST'23)

Uncertainty Quantification for Reliable Machine-Learning


Most practices often train models on specific data and distribute them as black-box models. A significant concern in this practice is the difficulty of rigorously quantifying the uncertainty of black-box algorithms and capturing the deviation of the prediction from the ground truth. Safe deployment of deep neural networks in high-stake real-world applications requires theoretically-sound uncertainty quantification. We study Conformal Prediction for uncertainty quantification of deep models to obtain effective human-ML collaborative systems. We particularly focus on overcoming challenges like imbalanced data distributions, data heterogeneity, distribution shift, and coverage for sub-populations.
Related papers: NCP (AAAI'23) & aPRCP (UAI'23)

Past Research Projects

Cybersecurity for Wireless Implantable Medical Devices

Implantable and Wearable Medical Devices (IMDs) are trending technologies in personal healthcare systems. They enable efficient diagnostics and scalable monitoring of patient's health status in real-time. Information security is a serious challenge to these devices as malicious attacks threaten the health and/or the privacy of patients. On the other hand, IMDs' architectures are characterized by limited resources, such as energy supply, processing power, and memory. Hence, balancing security/confidentiality with the efficiency of these devices is a substantial matter for IMD technologies to progress.
Highlighted papers: Biometric-based authentication & IMD plain-text authentication

Publications

Journals

Out-of-Distribution Detection in Time-Series Domain: A Novel Seasonal Ratio Scoring Approach T. Belkhouja, Y. Yan, and J. Doppa. ACM Transactions on Intelligent Systems and Technology (TIST), 2023.

Dynamic Time Warping based Adversarial Framework for Time-Series Domain T. Belkhouja, Y. Yan, and J. Doppa. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022.

Adversarial Framework with Certified Robustness for Time-Series Data via Statistical Features T. Belkhouja, J. Doppa. Journal of Artificial Intelligence Research (JAIR), 2022.

Analyzing Deep Learning for Time-Series Data through Adversarial Lens in Mobile and IoT Applications. T. Belkhouja, J. Doppa. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 2020.

Biometric-based Authentication Scheme for Implantable Medical Devices during Emergency Situations. T. Belkhouja, X. Du, A. Mohamed, A.K. Al-Ali, M. Guizani. Future Generation Computer Systems - Elsevier, 2019.

Symmetric Encryption Relying on Chaotic Henon System for Secure Hardware-Friendly Wireless Communication of Implantable Medical Systems. T. Belkhouja, X. Du, A. Mohamed, A.K. Al-Ali, M. Guizani. Journal of Sensor and Actuator Networks, 2018.

Conference Papers

Adversarial Framework with Certified Robustness for Time-Series Data via Statistical Features. T. Belkhouja and J. Doppa. 32nd International Joint Conference on Artificial Intelligence (IJCAI), 2023.

Probabilistically Robust Conformal Prediction. S. Ghosh, Y. Shi, T. Belkhouja, Y. Yan, J. Doppa, and B. Jones 39th Uncertainty in Artificial Intelligence (UAI), 2023.

Improving Uncertainty Quantification of Deep Classifiers via Neighborhood Conformal Prediction: Novel Algorithm and Theoretical Analysis. T. Belkhouja*, S. Ghosh*, Y. Yan, and J. Doppa. 37th AAAI Conference on Artificial Intelligence, 2023. (* denotes equal contribution)

Energy-Efficient Missing Data Recovery in Wearable Devices: A Novel Search-based Approach. T. Belkhouja*, D. Hussein*, G. Bhat, and J. Doppa. ACM/IEEE International Symposium on Low Power Electronics and Design (ISLPED), 2023. (* denotes equal contribution)

Training Robust Deep Models for Time-Series Domain: Novel Algorithms and Theoretical Analysis. T. Belkhouja, Y. Yan, and J. Doppa. 36th AAAI Conference on Artificial Intelligence, 2022.

Reliable Machine Learning for Wearable Activity Monitoring: Novel Algorithms and Theoretical Guarantees. T. Belkhouja*, D. Hussein*, G. Bhat, and J. Doppa. 41st International Conference on Computer-Aided Design (ICCAD), 2022. (* denotes equal contribution)

Role-based Hierarchical Medical Data Encryption for Implantable Medical Devices T. Belkhouja, S Sorour, M Hefeida. IEEE Global Communications Conference (GlobeCom), 2019.

Light-Weight Solution to Defend Implantable Medical Devices Against Man-In-The-Middle Attack. T. Belkhouja, X. Du, A. Mohamed, A.K. Al-Ali, M. Guizani. IEEE Global Communications Conference (GlobeCom), 2018.

Salt Generation for Hashing Schemes based on ECG readings for Emergency Access to Implantable Medical Devices. T. Belkhouja, X. Du, A. Mohamed, A.K. Al-Ali, M. Guizani. International Symposium on Networks, Computers and Communications (ISNCC), 2018.

Light-weight encryption of wireless communication for implantable medical devices using henon chaotic system. T. Belkhouja, X. Du, A. Mohamed, A.K. Al-Ali, M. Guizani. Wireless Networks and Mobile Communications International Conference (WINCOM), 2017.

New Plain-Text Authentication Secure Scheme for Implantable Medical Devices with Remote Control. T. Belkhouja, X. Du, A. Mohamed, A.K. Al-Ali, M. Guizani. IEEE Global Communications Conference (GlobeCom), 2017.

Service

Professional Events Organization

Tutorial on Advances in Robust Time-Series ML - AAAI 2024. Lead organizer

Program Committee Member

International Conference of Machine Learning - (ICML) 2024

AAAI Conference on Artificial Intelligence - (AAAI) 2024

AAAI Conference on Artificial Intelligence - AAAI Student Program 2024

AAAI Conference on Artificial Intelligence - AAAI Safe and Robust AI Track 2024

Conference on Neural Information Processing Systems - (NeurIPS) 2023

International Conference of Machine Learning - (ICML) 2023

International Conference on Artificial Intelligence and Statistics - (AISTATS) 2023

AAAI Conference on Artificial Intelligence - (AAAI) 2023

Teaching

Teaching Assistant, Washington State University

CptS 315 - Introduction to Data Mining Spring 2020 - Spring 2021

CptS 570 - Machine Learning Fall 2020

CptS 223 - Advanced Data Structures in C++ Fall 2020

CptS 451 - Introduction to Database Systems Spring 2020

CptS 440/540 - Introduction to Data Mining Fall 2019

Teaching Assistant, University of Idaho

ECE 241 - Digital Logic Circuit Lab 2017-2019

ECE 311 - Microelectronics I Lab Spring 2019