BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Department of Electrical & Computer Engineering - ECPv6.17.5//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Department of Electrical & Computer Engineering
X-ORIGINAL-URL:https://ece.northeastern.edu
X-WR-CALDESC:Events for Department of Electrical & Computer Engineering
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20220313T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20221106T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20230312T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20231105T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20240310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20241103T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20230602T110000
DTEND;TZID=America/New_York:20230602T120000
DTSTAMP:20230508T193647Z
CREATED:20230508T193647Z
LAST-MODIFIED:20230508T193647Z
UID:6319-1685703600-1685707200@ece.northeastern.edu
SUMMARY:Cheng Gongye's PhD Proposal Review
DESCRIPTION:“Hardware Security Vulnerabilities in Deep Neural Networks and Mitigations” \nCommittee Members:\nProf. Yunsi Fei (Advisor)\nProf. Xue Lin\nProf. Xiaolin Xu \nAbstract:\nOver the past decade\, Deep Neural Networks (DNNs) have revolutionized numerous fields. With the increasing deployment of DNN models in security-sensitive and mission-critical applications\, such as autonomous driving\, ensuring the security and privacy of DNN inference is of paramount importance. \nThis Ph.D. dissertation investigates two primary hardware security attack vectors: fault attacks and side-channel attacks. Fault attacks compromise the integrity of a targeted application by intentionally disrupting the computation or injecting faults on parameters. Side-channel attacks exploit information leakage from the application execution through physical parameters such as power consumption\, electromagnetic emanations\, and timing to retrieve secrets\, thereby breaching confidentiality. \nFor fault attacks\, we demonstrate a power-glitching fault injection attack on FPGA-based DNN accelerators in cloud environments. The attack exploits vulnerabilities in the shared power distribution network and leverages time-to-digital converter (TDC) sensors for precise fault injection timing\, and results in model misclassification\, an integrity compromise on the targeted application. We propose a lightweight defense framework for detecting and mitigating adversarial bit-flip attacks induced by RowHammer on DNNs. This framework employs a dynamic channel-shuffling obfuscation scheme and a logits-based model integrity monitor\, offering negligible performance loss. This framework effectively protects various DNN models from RowHammer attacks without any retraining or model structure modifications. \nFor side-channel attacks\, we present a floating-point timing side channels attack to reverse-engineer multi-layer perceptron (MLP) model parameters in software implementations. This attack successfully recovers DNN parameters\, weights and biases. \nRegarding ongoing research\, we observe that previous studies often focus on academic prototypes\, resulting in limited applicability. To bridge these gaps\, we select the AMD-Xilinx DPU\, one of the most advanced DNN accelerators to date\, to conduct the analysis. We propose a side-channel attack that utilizes electromagnetic emissions to extract parameters. Furthermore\, we propose a comprehensive fault analysis of quantized DNN models by simulations and discuss potential mitigation strategies.
URL:https://ece.northeastern.edu/event/cheng-gongyes-phd-proposal-review/
LOCATION:MA
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20230605T110000
DTEND;TZID=America/New_York:20230605T123000
DTSTAMP:20230522T211405Z
CREATED:20230522T211405Z
LAST-MODIFIED:20230522T211405Z
UID:6345-1685962800-1685968200@ece.northeastern.edu
SUMMARY:Can Qin's PhD Dissertation Defense
DESCRIPTION:“Unveiling the Power of Transfer Learning in Data-Driven AI” \nCommittee Members:\nProf. Raymond Fu (Advisor)\nProf. Octavia Camps\nProf. Huaizu Jiang \nAbstract:\nThe big data stands as a cornerstone of deep learning\, which has significantly improved a wide range of machine learning and computer vision tasks. Despite such a great success\, data collection is time-consuming and costly\, considering manual efforts and privacy restrictions. Transfer learning is a promising direction toward data-efficient AI by leveraging acquired data and pre-trained models as guidance. This dissertation focus on the feature and model transfer across different domains and tasks\, which can be roughly summarized into three sections. \n(1) Section One focuses on Unsupervised Domain Adaptation (UDA) without any labels in the target domain. The technical challenge of UDA is the distribution mismatch across domains. I have presented a hierarchical alignment model as the solution. \n(2) Section Two extends UDA into semi-supervised domain adaptation (SSDA) with minimal target-domain labels\, which is useful and effortless to acquire. To avoid overfitting toward labeled data\, I have proposed structural regularization verified on different classification benchmarks. \n(3) Section Three mainly explores the model transfer\, including teacher-student knowledge distillation and heterogeneous models infusion with a high potential for model compression and enhancement.
URL:https://ece.northeastern.edu/event/can-qins-phd-dissertation-defense/
LOCATION:MA
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20230613T173000
DTEND;TZID=America/New_York:20230613T191500
DTSTAMP:20230617T021216Z
CREATED:20230522T181116Z
LAST-MODIFIED:20230617T021216Z
UID:6356-1686677400-1686683700@ece.northeastern.edu
SUMMARY:Ignorance Is Bliss: A Career Retrospective
DESCRIPTION:  \nDean Gregory D. Abowd will present his SIGCHI Lifetime Research Award Acceptance Lecture \nDate: Tues.\, June 13\, 2023 \nTime: 5:30 to 7:15 PM\, reception following Dean Abowd’s talk \nPlace: In-Person and Livestream\nBostonCHI meeting at Northeastern University in ISEC Auditorium (102 ISEC)\, and reception in ISEC Atrium \nRegistration is appreciated but not required. View BostonCHI for more information. \nPresentation Abstract: In 1988\, as a graduate student grappling to find a research identity\, Gregory D. Abowd accidentally discovered the field of Human Computer Interaction (HCI). Over the past 35 years\, he pursued a passion for applying the tools and techniques of computing to uncover how the human experience with technology can be understood and transformed. That leap into HCI was just the first of a number of leaps of faith. Abowd’s career has been a series of shifting research agendas\, each one inspired by some life events. In all cases\, he was buoyed by a bevy of talented and supportive colleagues\, advisors and advisees alike\, who gave him the courage to jump into a research topic that he didn’t know much about. That “ignorance” has allowed him to be more fearless than he had the right to be. In this talk\, Abowd will reflect on his professional journey\, hoping to inspire others to dispel fear of the unknown and unlock their potential. Life\, like research\, is best when shared with others whom you can respect and befriend. \n—————————————— \nGregory D. Abowd\, dean of the College of Engineering and professor of electrical and computer engineering at Northeastern University\, has received the Lifetime Research Award from the Association for Computing Machinery’s (ACM) Special Interest Group on Computer-Human Interaction (SIGCHI). The award is presented to individuals for “the best\, most fundamental\, and influential research contributions to the study of human-computer interaction (HCI)” and is awarded for a lifetime of innovation and leadership. \n 
URL:https://ece.northeastern.edu/event/ignorance-is-bliss-a-career-retrospective/
LOCATION:102 ISEC\, 360 Huntington Ave\, 102 ISEC\, Boston\, MA\, 02115\, United States
GEO:42.3377335;-71.0869121
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=102 ISEC 360 Huntington Ave 102 ISEC Boston MA 02115 United States;X-APPLE-RADIUS=500;X-TITLE=360 Huntington Ave\, 102 ISEC:geo:-71.0869121,42.3377335
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20230620T080000
DTEND;TZID=America/New_York:20230620T170000
DTSTAMP:20230624T221028Z
CREATED:20230624T221028Z
LAST-MODIFIED:20230624T221028Z
UID:6404-1687248000-1687280400@ece.northeastern.edu
SUMMARY:Alfred P. Navato's PhD Dissertation Defense
DESCRIPTION:Title:\nEnabling Anomaly Detection in Complex Chemical Mixtures Through Multimodal Data Fusion \nDate:\n6/26/2023 \nTime:\n10:00:00 AM \nLocation:\nSH 210\, \nCommittee Members:\nProf. Mueller (Advisor)\nProf. Erdogmus\nProf. Ioannidis\nProf. Onnis-Hayden \nAbstract:\nRecently innovations in machine learning and data processing are increasingly tied to ensuring useability and interpretability when these methods are applied within end-user domains.  One societally important example of such a domain is management and operations of water infrastructure in cities\, where data collection is currently costly and limited\, enabling analytics have the potential to generate real impact for urban communities\, and correctness of results is critical to protect human and environmental health.  This dissertation holistically considers issues of generalizability\, transferability\, and applicability of a range of data fusion and machine learning approaches across end-user domains within the context of solution building for improved real-time management of wastewater infrastructure.  The first chapter provides an overview of the challenges associated with anomaly detection within the wastewater field and reviews the performance of various anomaly detection techniques implemented in other disciplines.  The second chapter discusses the barriers and opportunities in cross-disciplinary pollination of data fusion techniques.  The third chapter presents development of an unsupervised approach facilitating quantitative characterization of the complex background which is wastewater\, necessary to be able to implement any automated operational interventions.  The fourth chapter develops an approach for cost-minimization/information-maximization design of a sensor to facilitate specifically detection of chemical anomalies (defined as inflow events that might compromise wastewater treatment facilities) by using machine learning and feature selection techniques to minimize the number of input signals needed to achieve reasonable accuracies.  Together the third and fourth chapters provide a clear\, explainable\, actionable pathway forward in envisioning next generation wastewater infrastructure\, demonstrating novel and impactful use of data fusion and machine learning techniques in a real-world context.
URL:https://ece.northeastern.edu/event/alfred-p-navatos-phd-dissertation-defense/
LOCATION:MA
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20230620T130000
DTEND;TZID=America/New_York:20230620T140000
DTSTAMP:20230522T212041Z
CREATED:20230522T212041Z
LAST-MODIFIED:20230522T212041Z
UID:6354-1687266000-1687269600@ece.northeastern.edu
SUMMARY:Chang Liu's PhD Dissertation Defense
DESCRIPTION:“Unleashing the Potential of Transfer Learning for Visual Applications” \nCommittee Members:\nProf. Raymond Fu (Advisor)\nProf. Sarah Ostadabbas\nProf. Zhiqiang Tao \nAbstract:\nThe recent flourish of deep learning in various tasks is largely accredited to the rich and accessible labeled data. Nonetheless\, massive supervision remains a luxury for many real-world applications. Further\, the domain shift problem has also seriously impeded large-scale deployments of deep-learning models. As a remedy\, Transfer learning aims at improving the performance of target learners on target domains by transferring the knowledge contained in different but related source domains. In this way\, the dependence on a large number of target domain data can be reduced for constructing target learners. \nIn this dissertation research\, I investigate two major problems in transfer learning\, domain adaptation (DG) and domain adaptation (DA)\, on various visual applications. (1) The challenge of DG lies in an over-simplified assumption\, that is\, the source and target data are independent and identically distributed (i.i.d.) while ignoring out-of-distribution (OOD) scenarios commonly encountered in practice. This issue is common in visual applications such as object recognition\, hyperparameter optimization\, and face recognition. We propose algorithms that are specifically designed for each task\, such as metric learning\, adversarial regularization\, feature disentanglement\, and meta-learning. (2) DA can be considered a special case of DG with unlabeled target data available. The major challenge is how to align the labeled source and unlabeled target data. We delve into the applications of image recognition and video recognition and propose algorithms to ensure domain-wise discriminativeness and class-wise closeness across domains. Experiments show that the proposed algorithms outperform the state-of-the-art methods on the commonly-used benchmark datasets.
URL:https://ece.northeastern.edu/event/chang-lius-phd-dissertation-defense/
LOCATION:MA
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20230623T100000
DTEND;TZID=America/New_York:20230623T110000
DTSTAMP:20230606T193237Z
CREATED:20230606T193237Z
LAST-MODIFIED:20230606T193237Z
UID:6395-1687514400-1687518000@ece.northeastern.edu
SUMMARY:Cooper Loughlin's PhD Dissertation Defense
DESCRIPTION:“Deep Generative Models for High Dimensional Spatial and Temporal Data Analysis” \nCommittee Members:\nProf. Vinay Ingle (Advisor)\nDr. Dimitris Manolakis\nProf. Purnima Ratilal-Makris \nAbstract:\nData analysis and exploitation in practical applications is challenging when observations are the result of many interacting natural and man-made phenomena. We address two important problems for which traditional methods of analysis are insufficient. One problem of practical interest is the identification of particular materials from remotely sensed hyperspectral imagery. This is traditionally accomplished by comparing image pixel spectra to those from a known material library. Such techniques are limited by spectral variability\, background interference\, and imperfect compensation of atmospheric components. Established methods address these limitations with statistical techniques. Simple probability models result in tractable methods; however\, analyses are limited by errors due\, in particular\, due to false alarms. \nAnalysis of complex time series is another challenging problem\, particularly when data are high dimensional. This arises in air quality monitoring\, where atmospheric concentration measurements of multiple pollutants are taken over time. Two analysis goals in this context are forecasting and anomaly detection. Both tasks are enabled by an accurate model for the temporal dynamics and interaction between pollutants. Air quality data are complex due to long term temporal dependencies\, non-linear dependence between pollutants\, and missing observations. Traditional multivariate time series analysis approaches\, such as the vector autoregression and linear dynamical system models\, fail to capture those characteristics necessary for a sufficient probabilistic model. \nWe use deep generative models to develop practical solutions that address these problems. This is made possible through the application of deep latent variable models. The modeling approach follows the philosophy that complex data can typically be explained by simpler underlying factors of variation. Variational autoencoders (VAEs) are deep latent variable models that emulate data generation by transforming simple\, low dimensional\, latent random vectors through a deep neural network. VAEs are trained to produce samples that resemble the training data\, thus capturing a manifold on which complex data are distributed. This philosophy is extended to time series data\, where we consider sequences of latent vectors. \nWe utilize VAEs develop a flexible generative model for hyperspectral imagery. Based on that model\, we develop a novel material identification framework which localizes target material spectra along the manifold. Through experiments on real data\, we show that the \ac{VAE} approach is better able to reject false alarms from materials with similar spectra when compared to established methods alone. We additionally develop a novel dynamical \ac{VAE} model for time series of air quality data. Using that model\, we develop practical methods for computing forecast distributions using Monte Carlo integration. We evaluate forecast distributions against real air quality data and demonstrate the ability to predict temporal dynamics and forecast uncertainty. The primary contribution of this work is to develop practical solutions to challenging data analysis problems through the use of deep generative models.
URL:https://ece.northeastern.edu/event/cooper-loughlins-phd-dissertation-defense/
LOCATION:MA
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20230626T083000
DTEND;TZID=America/New_York:20230626T093000
DTSTAMP:20230624T220848Z
CREATED:20230624T220848Z
LAST-MODIFIED:20230624T220848Z
UID:6402-1687768200-1687771800@ece.northeastern.edu
SUMMARY:Deniz Unal's PhD Proposal Review
DESCRIPTION:Title:\nSoftware-Defined Underwater Acoustic Networks \nCommittee Members:\nProf. Tommaso Melodia (Advisor)\nProf. Stefano Basagni\nProf. Kaushik Chowdhury\nDr. Emrecan Demirors \nAbstract:\nThe exploration\, monitoring\, and understanding of oceans play a crucial role in addressing climate change\, overseeing underwater pipelines\, and preventing maritime warfare attacks. To achieve these significant objectives\, it is vital to utilize networks of cost-effective and flexible underwater devices capable of efficiently collecting and transmitting information to the shore. However\, the progress of underwater networks heavily relies on underwater acoustic modems\, which currently face limitations such as low data rates and inflexible hardware designs\, limiting their usability to specific scenarios. To overcome these limitations\, we propose a modular software-defined acoustic networking platform built on the Zynq system-on-chip architecture that can be easily deployed in a compact form factor. Our platform distinguishes itself from existing solutions in several ways. Firstly\, it possesses the capability to adapt to varying conditions by adjusting protocol parameters at all layers of the networking stack. Secondly\, it achieves high data rate connections\, particularly over short distances. Additionally\, it seamlessly integrates with other sub-sea platforms\, including underwater drones. We demonstrate the capabilities and the performance of our platform with tasks\, such as channel estimation and characterization\, establishing high data rate Orthogonal Frequency-Division Multiplexing (OFDM) links\, and running third-party software to implement JANUS standard. In addition\, we introduce the enabling technologies for the development and implementation of underwater networks. These technologies facilitate the establishment of connectivity between underwater networks and the shore\, as well as the integration of modems with underwater vehicles. Lastly\, we provide a demonstration of the algorithmic development conducted on our platform. We mainly consider high-rate\, wideband\, adaptive links and perform experimental evaluations at sea. In particular\, we demonstrate multicarrier communications with mobile platforms with the presence of Doppler and compare the performance of forward error correction methods\, and demonstrate dataset recording for artificial intelligence research.
URL:https://ece.northeastern.edu/event/deniz-unals-phd-proposal-review/
LOCATION:MA
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20230629T170000
DTEND;TZID=America/New_York:20230629T173000
DTSTAMP:20230626T213036Z
CREATED:20230626T213009Z
LAST-MODIFIED:20230626T213036Z
UID:6407-1688058000-1688059800@ece.northeastern.edu
SUMMARY:Zifeng Wang's PhD Dissertation Defense
DESCRIPTION:Title: Effective and Efficient Continual Learning \nCommittee Members:\nProf. Jennifer Dy (Advisor)\nProf. Stratis Ioannidis\nProf. Yanzhi Wang \nAbstract:\nContinual Learning (CL) aims to develop models that mimic the human ability to learn continually without forgetting knowledge acquired earlier. While traditional machine learning methods focus on learning with a certain dataset (task)\, CL methods adapt a single model to learn a sequence of tasks continually. \nIn this thesis\, we target developing effective and efficient CL methods under different challenging and resource-limited settings. Specifically\, we (1) leverage the idea of sparsity to achieve cost-effective CL\, (2) propose a novel prompting-based paradigm for parameter-efficient CL\, and (3) utilize task-invariant and task-specific knowledge to enhance existing CL methods in a general way. \nWe first introduce our sparsity-based CL methods. The first method\, Learn-Prune-Share (LPS)\, splits the network into task-specific partitions\, leading to no forgetting\, while maintaining memory efficiency. Moreover\, LPS integrates a novel selective knowledge sharing scheme\, enabling adaptive knowledge sharing in an end-to-end fashion. Taking a step further\, we present Sparse Continual Learning (SparCL)\, a novel framework that leverages sparsity to enable cost-effective continual learning on edge devices. SparCL achieves both training acceleration and accuracy preservation through the synergy of three aspects: weight sparsity\, data efficiency\, and gradient sparsity. \nSecondly\, we present a new paradigm\, prompting-based CL\, that aims to train a more succinct memory system that is both data and memory efficient. We first propose a method that learns to dynamically prompt (L2P) a pre-trained model to learn tasks sequentially under different task transitions\, where prompts are small learnable parameters maintained in a memory space. We then improve L2P by proposing DualPrompt\, which decouples prompts into complementary “General” and “Expert” prompts to learn task-invariant and task-specific instructions\, respectively. \nFinally\, we propose DualHSIC\, a simple and effective CL method that generalizes the idea of leveraging task-invariant and task-specific knowledge. DualHSIC consists of two complementary components that stem from the so-called Hilbert Schmidt independence criterion (HSIC): HSIC-Bottleneck for Rehearsal (HBR) lessens the inter-task interference and HSIC Alignment (HA) promotes task-invariant knowledge sharing. \nComprehensive experimental results demonstrate the effectiveness and efficiency of our methods over the state-of-the-art methods on multiple CL benchmarks.
URL:https://ece.northeastern.edu/event/zifeng-wangs-phd-dissertation-defense/
LOCATION:MA
END:VEVENT
END:VCALENDAR