Defense Notices

Convolutional Neural Networks (CNNs) have achieved great success in broad computer vision tasks. However, due to the lack of labeled data, many available CNN models cannot be widely used in many real scenarios or suffer from significant performance drop. To solve the problem of lack of correctly labeled data, we explored the capability of existing unsupervised domain adaptation (UDA) methods on image classification and proposed two new methods to improve the performance.

1. An Unsupervised Domain Adaptation Model based on Dual-module Adversarial Training: we proposed a dual-module network architecture that employs a domain discriminative feature module to encourage the domain invariant feature module to learn more domain invariant features. The proposed architecture can be applied to any model that utilizes domain invariant features for UDA to improve its ability to extract domain invariant features. Through the adversarial training by maximizing the loss of their feature distribution and minimizing the discrepancy of their prediction results, the two modules are encouraged to learn more domain discriminative and domain invariant features respectively. Extensive comparative evaluations are conducted and the proposed approach significantly outperforms the baseline method in all image classification tasks.

2. Exploiting maximum classifier discrepancy on multiple classifiers for unsupervised domain adaptation: The adversarial training method based on the maximum classifier discrepancy between the two classifier structures has been applied to the unsupervised domain adaptation task of image classification. This method is straightforward and has achieved very good results. However, based on our observation, we think the structure of two classifiers, though simple, may not explore the full power of the algorithm. Thus, we propose to add more classifiers to the model. In the proposed method, we construct a discrepancy loss function for multiple classifiers following the principle that the classifiers are different from each other. By constructing this loss function, we can add any number of classifiers to the original framework. Extensive experiments show that the proposed method achieves significant improvements over the baseline method.

COVID-19 is caused by the SARS-COV-2 contagious virus. It causes a devastating effect on the health of humans leading to high morbidity and mortality worldwide. Infected patients should be screened effectively to fight against the virus. Chest X-Ray (CXR) is one of the important adjuncts in the detection of visual responses related to SARS-COV-2 infection. Abnormalities in chest x-ray images are identified for COVID-19 patients. COVID-Net a deep convolutional neural network, is used here to detect COVID-19 cases from Chest X-ray images. COVIDX dataset used in this project is generated from five different open data access repositories. COVID-Net makes predictions using an explainability method to gain knowledge into critical factors related to COVID cases. We also perform quantitative and qualitative analyses to understand the decision-making behavior. 

Multimedia networking is the area of study associated with the delivery of heterogeneous data including, but not limited to, imagery, video, audio, and interactive content. Multimedia and communication network researchers have continually struggled to devise solutions for addressing the three core challenges in multimedia delivery: security, reliability, and performance. Solutions to these challenges typically exist in a spectrum of compromises achieving gains in one aspect at the cost of one or more of the others. Networked videogames represent the pinnacle of multimedia presented in a real-time interactive format. Continual improvements to multimedia delivery have led to tools such as buffering, redundant coupling of low-resolution alternative data streams, congestion avoidance, and forced in-order delivery of best-effort service; however, videogames cannot afford to pay the latency tax of these solutions in their current state.

This dissertation aims to address these challenges through the application of a novel networking protocol, leveraging emerging technology such as block-chain enabled smart contracts, to provide security, reliability, and performance gains to distributed network applications. This work provides a comprehensive overview of contemporary networking approaches used in delivering videogame multimedia content and their associated shortcomings. Additionally, key elements of block-chain technology are identified as focal points for prospective solution development, notably through the application of distributed ledger technology, consensus mechanisms and smart contracts. Preliminary results from empirical evaluation of contemporary videogame networking applications have confirmed security and performance flaws existing in well-funded AAA videogame titles. Ultimately, this work aims to solve challenges that the videogame industry has struggled with for over a decade.

The broader impact of this research is to improve the real-time delivery of interactive multimedia content. Positive results in the area will have wide reaching effects in the future of content delivery, entertainment streaming, virtual conferencing, and videogame performance.

Activism is a universal concept that has often played a major role in putting an end to injustices and human rights abuses globally. Political activism in specific is a modern day term coined to refer to a form of activism in which a group of people come into collision with a more omnipotent adversary - national or international governments - who often has a purview and control over the very telecommunications infrastructure that is necessary for activists in order to organize and operate. As technology and social media use have become vital to the success of activism movements in the twenty first century, our study focuses on surfacing the technical challenges and the defensive strategies that activists employ during a political revolution. We find that security and privacy behavior and app adoption is influenced by the specific societal and political context in which activists operate. In addition, the impact of a social media blockade or an internet blackout can trigger a series of anti-censorship approaches at scale and cripple activists’ technology use. To a large extent the combination of low tech defensive strategies employed by activists were sufficient against the threats of surveillance, arrests and device confiscation. Throughout our results we surface a number of design principles but also some design tensions that could occur between the security and usability needs of different populations. And thus, we present a set of observations that can help guide technology designers and policy makers. 

Recent advances in machine learning (ML), known as deep neural networks (DNN) or deep learning, have greatly improved the state-of-the-art for many ML tasks, such as image classification (He, Zhang, Ren, & Sun, 2016; Krizhevsky, Sutskever, & Hinton, 2012; LeCun, Bottou, Bengio, & Haffner, 1998; Szegedy et al., 2015; Zeiler & Fergus, 2014), speech recognition (Graves, Mohamed, & Hinton, 2013; Hannun et al., 2014; Hinton et al., 2012), complex games and learning from simple reward signals (Goodfellow et al., 2014; Mnih et al., 2015; Silver et al., 2016), and many other areas as well. NN and ML methods have been applied to the task of autonomously controlling a vehicle with only a camera image input to successfully navigate on road (Bojarski et al., 2016). However, advances in deep learning are not yet applied systematically to this task. In this work I used a simulated environment to implement and compare several methods for controlling autonomous navigation behavior using a standard camera input device to sense environmental state. The simulator contained a simulated car with a camera mounted on the top to gather visual data while being operated by a human controller on a virtual driving environment. The gathered data was used to perform supervised training for building an autonomous controller to drive the same vehicle remotely over a local connection. Reproduced past results that have used simple neural networks and other ML techniques to guide similar test vehicles using a camera. Compared these results with more complex deep neural network controllers, to see if they can improve navigation performance based on past methods on measures of speed, distance, and other performance metrics on unseen simulated road driving tasks.

Remote attestation is the act of making trust decisions about a communicating party. During this process, an appraiser asks a target to execute an attestation protocol that generates and returns evidence. The appraiser can then make claims about the target by evaluating the evidence. Copland is a formally specified, executable language for representing attestation protocols. We introduce Copland centered negotiation as prerequisite to attestation to find a protocol that meets the target’s needs for constrained disclosure and the appraiser’s desire for comprehensive information. Negotiation begins when the appraiser sends a request, a Copland phrase, to the target. The target gathers all protocols that satisfy the request and then, using their privacy policy, can filter out the phrases that expose sensitive information. The target sends these phrases to the appraiser as a proposal. The appraiser then chooses the best phrase for attestation, based on situational requirements embodied in a selection function. Our focus is statically ensuring the target does not share sensitive information though terms in the proposal, meeting their need for constrained disclosure. To accomplish this, we realize two independent implementation of the privacy and selection policies using indexed types and subset types. In using indexed types, the policy check is accomplishes by indexing the term grammar with the type of evidence the term produces. The statically ensures that terms written in the language will satisfy the privacy policy criteria. In using the subset type, we statically limit the collection of terms to those that satisfy the privacy policy. This type abides by the rules of set comprehension to build a set such that all elements of the set satisfy the privacy policy. Combining our ideas for a dependently typed privacy policy and negotiation, we give the target the chance to suggest a term or terms for attestation that fits the appraiser’s needs while not disclosing sensitive information.

COVID-19 is a disease that spreads from human to human which can be controlled by ensuring proper use of a facial mask. The spread of COVID-19 can be limited if people strictly maintain social distancing and use a facial mask. Very sadly, people are not obeying these rules properly which is speeding the spread of this virus. Detecting the people not obeying the rules and informing the corresponding authorities can be a solution in reducing the spread of Corona virus. The proposed method detects the face from the image correctly and then identifies if it has a mask on it or not. As a surveillance task performer, it can also detect a face along with a mask in motion. It has numerous applications, such as autonomous driving, education, surveillance, and so on.

Fatigue and microsleep at the wheel are often the cause of serious accidents and death. Fatigue, in general, is difficult to measure or observe unlike alcohol and drugs, which have clear key indicators and tests that are available easily. Hence, detection of driver’s fatigue and its indication is an active research area. Also, I believe that drowsiness can negatively impact people in working and classroom environments as well. Drowsiness in the workplace especially while working with heavy machinery may result in serious injuries similar to those that occur while driving drowsily. The proposed system for detecting driver drowsiness has a webcam that records the video of the driver and driver’s face is detected in each frame employing image processing techniques. Facial landmarks on the detected face are pointed and subsequently the eye aspect ratio, mouth opening ratio and nose length ratio are computed and depending on their values, drowsiness is detected. If drowsiness is detected, a warning or alarm is sent to the driver from the warning system.

Fingerspelling in sign language has been the means of communicating technical terms and proper nouns when they do not have dedicated sign language gestures. The automatic recognition of fingerspelling can help resolve communication barriers when interacting with deaf people. The main challenges prevalent in automatic recognition tasks are the ambiguity in the gestures and strong articulation of the hands. The automatic recognition model should address high inter-class visual similarity and high intra-class variation in the gestures. Most of the existing research in fingerspelling recognition has focused on the dataset collected in a controlled environment. The recent collection of a large-scale annotated fingerspelling dataset in the wild, from social media and online platforms, captures the challenges in a real-world scenario. This study focuses on implementing a fine-grained visual attention approach using Transformer models to address the challenges existing in two fingerspelling recognition tasks: multiclass classification of static gestures and sequence-to-sequence prediction of continuous gestures. For a dataset with a single gesture in a controlled environment (multiclass classification), the Transformer decoder employs the textual description of gestures along with image features to achieve fine-grained attention. For the sequence-to-sequence prediction task in the wild dataset, fine-grained attention is attained by utilizing the change in motion of the video frames (optical flow) in sequential context-based attention along with a Transformer encoder model. The unsegmented continuous video dataset is jointly trained by balancing the Connectionist Temporal Classification (CTC) loss and maximum-entropy loss. The proposed methodologies outperform state-of-the-art performance in both datasets. In comparison to the previous work for static gestures in fingerspelling recognition, the proposed approach employs multimodal fine-grained visual categorization. The state-of-the-art model in sequence-to-sequence prediction employs an iterative zooming mechanism for fine-grained attention whereas the proposed method is able to capture better fine-grained attention in a single iteration.

With the rapid development of machine learning (ML) and deep learning (DL) methodologies, DL methods can be leveraged for wireless network reconfigurability and channel modeling. While deep learning-based methods have been applied in a few wireless network use cases, there is still much to be explored. In this project, we focus on the application of deep learning methods for two scenarios. In the first scenario, a user transmitter was moving randomly within a campus area, and at certain spots sending wireless signals that were received by multiple antennas. We construct an active deep learning architecture to predict user locations from received signals after dimensionality reduction, and analyze 4 traditional query strategies for active learning to improve the efficiency of utilizing labeled data. We propose a new location-based query strategy that considers both spatial density and model uncertainty when selecting samples to label. We show that the proposed query strategy outperforms all the existing strategies. In the second scenario, a reconfigurable intelligent surface (RIS) containing 4096 tunable cells reflects signals from a transmitter to users in an office for better performance. We use the training data of one user's received signals under different RIS configurations to learn the impact behavior of the RIS on the wireless channel. Based on the context and experience from the first scenario, we build a DL neural network that maps RIS configurations to received signal estimations. In the second phase, the loss function was customized towards our final evaluation formula to obtain the optimum configuration array for a user. We propose and build a customized DL pipeline that automatically learns the behavior of RIS on received signals, and generates the optimal RIS configuration array for each of the 50 test users.