Digital Commons Network^™

Multi-Functional Smartwatch Crown, Charles No

Defensive Publications Series

This disclosure describes a multi-functional smartwatch crown that an improved navigation experience, e.g., for a smartwatch. The crown is designed to rotate about an axis as a rotating side button that is mapped to some smartwatch navigation actions. The crown can also be pushed in and out as a button for other navigation actions. The crown is additionally configured to be toggled up and down (jog toggle) along a side of the smartwatch, e.g., for added functionality such as increasing or decreasing volume, or for up and down pagination, etc. The crown can also be locked into different positions after …

Static System-Call Graph Generation, Alexandre Boulgakov

Defensive Publications Series

Certain techniques for testing for the presence of malicious code within executables are based on the observation that system calls (syscalls) are a main pathway for exploits. The problem of generating a graph of syscalls of an executable is thus of importance in computer security. The present disclosure describes the generation of the syscall graph of a binary executable given a control flow graph of the executable. Along with a syscall graph, a set of potential asynchronous entry points into the graph is also returned.

Flow-Graph Analysis Of System Calls For Exploit Detection, Anthony Desnos, Elena Petrova, Alexandre Boulgakov, Richard Neal, Zubin Mithra

Defensive Publications Series

One technique of improving computer security is to test an executable for presence of malicious code without running the executable. The present disclosure enables such detection of malicious code by leveraging the observation that system calls (syscalls) are a main pathway for exploits, since syscalls are an important way for a program to interact with an operating system kernel. The disclosure describes techniques to compute a control flow graph for the executable comprising only syscalls. A number of independent control flows are produced from such a control flow graph. Graph analysis/matching techniques are applied to detect exploit patterns in these …

Smart Linkification Of Content Within Applications, Jan Althaus, Thomas Binder, Jacek Jurewicz, Lukas Zilka, Sebastian Millius, Matthew Sharifi, Regina O'Dell, Abodunrinwa Toki, Evelyn Kao

Defensive Publications Series

When a user initiates text selection within an application, the operating system can examine text content displayed within the application to predict text selection bounds along with a possible destination application for the selected text. Until the user initiates selection, there may be no indication that a piece of text content might be actionable. Further, the functionality may not work as intended in cases where application developers implement a custom operation for the input mode utilized for passing the text content and associated action from one application to another. With user permission, this disclosure applies regular expression parsing and neural …

Optimizer For User-Interface Layout Computations, John Hoford Hoford, Nicolas Roard

Defensive Publications Series

User-interface (UI) developers use design tools such as layout managers to lay out UI elements. A good design tool enables developers to create efficient user interfaces, while itself being efficient to use. Current design tools sometimes produce designs that have inefficient user interfaces, e.g., inflexible (hard-to-change) layouts, or user interfaces with performance problems.

This disclosure provides techniques that improve the efficiency of the computations underlying the UI design tool. Additionally, the techniques provide direct, visual feedback attributing computational cost to specific sub-areas of the screen, enabling developers to optimize the user interface.

Active Directory And Calendaring Based Allocation And Reservation Of Wireless Resources, Sukrit Dasgupta, Jp Vasseur, Santosh Pandey

Defensive Publications Series

Present techniques dedicate wireless channel resources based on applications that will be used in collaborative meetings. The degree of reservation is determined using machine learning algorithms that have knowledge from a prior history of meetings, participants in the meeting, etc. This ensures that collaborative applications will perform favorably, leading to more effective collaborations. Several novel components are involved in these techniques, which control the network infrastructure, determine the users that need reservation(s), identify the applications that will be used, and also utilize machine learning to model the usage and requirements.

Predicting 5g Usage And Resource Contention Through Real-Time Mass Transit And Traffic Mapping, David Hanes, Chuck Byers, Joe Clarke, Gonzalo Salgueiro

Defensive Publications Series

Internet of Things (IoT) and sensor fusion techniques may be used to collect data about the current positions and anticipated movements of wireless subscribers, thus enabling fifth-generation (5G) networks to proactively avoid overloads by modifying their capacities and coverage patterns. Data may be collected, for example, from mass transit systems, smart highway systems, smart buildings, security cameras, 5G networks themselves, and other sources, and machine learning techniques may be applied to generate maps of anticipated load patterns. As a result, the 5G networks may then be adjusted to address overloads in various manners, such as by adjusting the service bandwidth, …

Service Level Agreement Enforcement And Measurement Of Network Slices, Robert Barton, John Graybeal, Bart Brinckman, Jerome Henry, Catherine Rosenberg

Defensive Publications Series

The embodiments presented herein disclose a method to predict, score, and ultimately select networks such as radio access networks, as well as heterogeneous network layers such as macro, piccolo, and the like. Technologies that are optimally able to meet service level agreements for different types of network slices, such as enterprise Wi-Fi and SP 3GPP, may also be selected.

Wireless Augmented Reality (Ar) / Virtual Reality (Vr) Channel Prediction, Ardalan Alizadeh, Amir Kamalizad, Matt Silverman

Defensive Publications Series

A wireless AR/VR headset may constantly report the exact coordination and orientation of itself and/or a user to a server. This information can be initially used at an access point (AP) to generate a look-up table (LUT). The LUT may include estimated channels from the AP to all spatial points that the headset may potentially sweep (e.g., in a certain application). During regular usage of AR/VR, the reported location of the headset is extracted in the AP to predict the channel at each point from the LUT and to update a multi-user MIMO steering matrix accordingly. A sounding process is …

Device Orientation Detection Through Signal Features, Xu Zhang, Amir Kamalizad, Khashayar Mirfakhraei

Defensive Publications Series

Techniques are described herein for using Radio Frequency (RF) signal features at multiple Access Points (APs) to detect the orientation of a client device. These orientation-related RF signal features may be used over time and over multiple APs to perform device tracking/authentication and pattern recognition in 5G or Internet of Things (IoT) networks.

Flexible Container And Service Visibility For Integration With External Legacy Enterprise Firewalls And Appliances, Sanjeev Rampal, Meenakshi Kaushik

Defensive Publications Series

The techniques described herein enable customers to leverage existing investments in legacy non-containerized firewalls or other legacy appliances while performing those security, and other, functions on traffic originating from new containerized workloads running elsewhere in the enterprise. This provides an end-to-end solution that solves a number of pragmatic real world problems that enterprise customers will face as they move toward cloud and containers while wanting to leverage their existing investments in security and firewall appliances.

Dormancy Prediction And User Equipment Driven Active-Dormant Transitions, Sooraj Sasindran, Naveen Kalla

Defensive Publications Series

The decision to move a mobile device to dormant radio resource state is typically driven by the mobile network. For example, after a period of observed inactivity, the network may move the mobile device to dormancy. However, mobile applications may send data shortly after the mobile device is moved to dormancy which results in sub-optimal power and bandwidth use. This disclosure provides techniques that enable the mobile device to predict immediate data transmission requirements. The predictions are used by the mobile device to drive active-dormant transitions at the radio resource control (RRC) layer.

Intelligent Ranking For Photo Galleries Using Sharing Intent, John Oberbeck

Defensive Publications Series

Users often share digital photographs over communication links, e.g., via SMS, chat, URLs, etc. This disclosure describes techniques to determine and present ranked candidate images for sharing to other users and user devices. The ranking is based on a variety of characteristics of the images, including time of capture of the images, as well as other user-permitted factors that can indicate user intent, such as history of previous sharing of images by the user, the current or recent device context of the user (chat or conversation, application being used, data on the user’s screen, and so on), etc. By intelligently …

Machine Learning For Wireless Solution Optimizations: Intelligent Ue Paging Retry Timer, Tariq Habibullah, Dennis Lanov, Solomon Ayyankulankara Kunjan, Chad Crum

Defensive Publications Series

Dynamic changes in the behavior of Radio Access Nodes (RANs) require dynamic adjustment of core network's communication strategy with such RAN. The techniques presented herein specify a novel approach to dynamically calculate and adjust the paging retry timer on a radio access network, such as a 5G Mobile Network, in order to prevent excessive signaling on the radio access network causing unnecessary usage of valuable radio resources. The techniques presented herein leverage subscriber and RAN statistics to perform supervised time-series regression in order to calculate the optimal time the core network should wait before attempting to retry the paging message …

Spiral Data Reporting Mechanism In Low-Power And Lossy Networks, Xiaopu Zhang, Caijun Jiang, Dapeng Zhu, Zaochun Zhang

Defensive Publications Series

The embodiments presented herein relate to low-power and lossy networks (LLNs), and more specifically, to dividing LLN nodes into groups. Groups may be determined by traversing a directed acyclic graph (DAG) topology in a spiral manner. In this manner, contention, collisions, and interference may be minimized, while bandwidth usage can be maximized.

External Interference Management On Radio Access Network Technology, Ariel Kenig, Lior Steinberger

Defensive Publications Series

The embodiments disclosed herein relate to automatically detecting and managing external interference present in cellular networks, which can significantly improve the availability and quality of network resources and the user experience. Eliminating the need to manually detect and manage sources of interference may, for example, reduce costs and the duration in which a network is negatively impacted.

Dynamic Container Network And Service Mesh Policy Actions Based On Malware And Intrusion Detection, Sanjeev Rampal

Defensive Publications Series

A closed loop solution is provided for dynamically enforcing container network and service mesh policies based on dynamic malware detection. This may be integrated with existing enterprise firewalls, intrusion detection systems, and other similar malware detection appliances.

Camera-Assisted Radio Resource Management, Ardalan Alizadeh, Amir Kamalizad, Matt Silverman, Pooya Monajemi

Defensive Publications Series

Current Radio Resource Management (RRM) implementations usually do not respond quickly to changes in the coverage area environment. Accordingly, techniques are described herein for making a reliable decision on applying different RRM functionalities in an optimal time and reducing latency on changing the network parameters. This fuses the information extracted from real-time video streams of the environment into the RRM unit to predict the network load and adapt algorithms accordingly.

Crowd Sourcing-Based True Coverage Hole And Radio Frequency Issue Detection, Shankar Ramanathan, Gonzalo Salgueiro, Muhilan Natarajan, Robert Barton, Jerome Henry

Defensive Publications Series

Techniques are described herein for collecting wireless data from client devices to provide a true picture of a Radio Frequency (RF) coverage model. This is used by the wireless infrastructure (controller) to better optimize the RF coverage model, steer clients to a better network, alert users to coverage holes in their area, and provide historical feedback to users about the quality of coverage in various areas.

Human Usage Description For 5g Network Endpoints, M. David Hanes, Chuck Byers, Joe Clarke, Gonzalo Salgueiro

Defensive Publications Series

Just as Manufacturers Usage Description (MUD) defines security and access control for “things,” Human Usage Description (HUD) does the same for humans by associating a user and all of their devices in a database. With such a database, a 5G provider has insights into user behavior on the network in context with the user device. This allows for more accurate Quality of Experience (QoE) and network slicing at the user device level, common licensing and security across multiple devices, next generation media consumption, and revenue generation through targeted advertising.

Automatic Failure Triage And Recovery Using Unsupervised Learning, Jon-Paul Sullivan

Defensive Publications Series

Techniques are provided to improve pipeline automation and reduce mundane operational tasks by automating the triage and remediation of any pipeline failures. This increases the efficiency of operations engineers and allows them to spend their time performing more useful activities. Unsupervised learning means that over time the effectiveness of the solution improves, and the nature of the solution enables it to scale better than a human would at the same task.

Efficient Multi-Graph Or Rooted Subgraph Matching Via Merging, Alexandre Boulgakov

Defensive Publications Series

The problem of matching one or more graphs or subgraphs with a non-deterministic finite automaton (NFA) is of importance in various domains of computer science. An example is regular-expression matching, which can be formulated as a graph-matching problem. Current techniques of matching multiples graphs or subgraphs against NFAs have relatively high computational complexity. This disclosure presents matching techniques with complexity that is linear in the size of the graph. A single, larger, graph is constructed from the set of graphs to be matched. The larger graph is considered as an NFA. A single-NFA to single-NFA matching procedure of linear space …

Converged Wireless Technology Architectures: Hybrid Networks Consisting Of Lora And Wi-Sun Nodes, Pascal Thubert, Huimin She

Defensive Publications Series

The embodiments presented herein utilize class B LoRa to avoid conflicts with Wi-SUN traffic that is on the same band. In areas covered by a LoRa edge, portions of the time slots of specific channels may be aggregated into longer time slots to adapt to LoRa spreading factors. Edge mesh nodes may use class B to pull traffic from channels of LoRa devices at the appropriate time. LoRa may be configured to operate in the appropriate channels, and any interference with Wi-SUN can be minimalized.

Sleep And Wake Commands For Voice-Activated Devices, N/A

Defensive Publications Series

Voice-activated devices continue to increase in popularity, availability, and functionality. To use a voice-activated device, a user will speak a particular keyword or hot word. In order to respond to a command at all times, the voice-activated device actively monitors the surrounding environment for the keyword or hot word using a microphone or other device, which means that the microphone of the voice-activated device hears all sound received while active. Although active monitoring may increase user interaction or satisfaction with the voice-activated device, audio monitoring may raise privacy concerns. To address these concerns, voice-activated devices can be equipped with a …

Son-Powered Dynamic Optimization Of Relay Layer To Enhance Coverage And Capacity Of A Cellular Network Combined With Centralized Son On Macro Layer, Alon Ben Ami, Tal Dunsky

Defensive Publications Series

The usage patterns of cellular networks can change dramatically over short periods of time, such as when a large number of people crowd a very small space within a cell's coverage area for only a short period of time. In order to save on costly and inefficient current solutions, the techniques presented herein suggest a Self-Organizing Network (SON)-optimized system of relays as a layer on top of an existing system. Such relays can be deployed ad hoc, such as in the cars of people arriving at a troubled location, to alleviate temporary coverage and load issues. SON will control the …

Massive Mimo Optimization Using Self-Optimizing Networks, Krishna Veni Thombarapu, Murali Mohan Cheekati, Prasada Rao Ponnamaneni

Defensive Publications Series

Massive multiple-input and multiple-output (MIMO), which refers to the practice of employing a large number of antennas at a base station to achieve better spectral efficiency using the same time and frequency resources, has received extensive interest as a potential solution for a next-generation cellular system. Presented herein are techniques to optimize a MIMO antenna configuration in order to reduce power consumption (and therefore operation cost) in a next-generation cellular network, paving the way to an energy-efficient wireless network.

Enterprise Analytics: Method And Apparatus For Sda Packet Debugging, Flow Visibility And Monitoring, Rajeev Kumar, Parth Shah, Akshay Dorwat, Manas Pati

Defensive Publications Series

The present techniques perform software defined access (SDA) packet visibility, monitoring, and analytics without impacting performance overhead. An Application Specific Integrated Circuit (ASIC) may be used to perform these processes at line rate without involvement from a central processing unit.

Matching A Graph With A Non-Deterministic Finite Automaton, Alexandre Boulgakov

Defensive Publications Series

The problem of matching a graph with a non-deterministic finite automaton (NFA) is of importance in various domains of computer science. An example is regular-expression matching, which can be formulated as a graph-matching problem. Current techniques of matching graphs against NFAs have relatively high computational complexity. This disclosure presents matching techniques with complexity that is linear in the size of the graph. The graph to be matched against the NFA is itself considered as an NFA. A synchronized product of the two NFAs is defined, and the matching problem is shown equivalent to a reachability problem solvable in linear (time …

Branching Neural Networks, Ufuk Can Biçici, Cem Keskin, Shahram Izadi

Defensive Publications Series

A conditional deep learning model that learns specialized representations on a decision tree is described. Unlike similar methods taking a probabilistic mixture of experts (MoE) approach, a feature augmentation based method is used to jointly train all network and decision parameters using back–propagation, which allows for deterministic binary decisions at both training and test time, specializing subtrees exclusively to clusters of data. Feature augmentation involves combining intermediate representations with scores or confidences assigned to branches. Each representation is augmented with all of the scores assigned to the active branch on the computational path to encode the entire path information, which …

Context Sensitive Network Security Score, Swami Anantha, Byju Pularikkal, Santosh Patil, Sourav Chakraborty

Defensive Publications Series

Techniques are described herein for quantifying a security impact of network vulnerabilities (e.g., hardware/software/configuration) on a network. The security impact quantification is calculated by weighting a configuration vulnerability score and an infrastructure security vulnerability score with a Vulnerability Reach Index (VRI). The VRI is an indication of the depth in the network of the impact of a vulnerability.