Abstract: A variable payload robot is disclosed. In various embodiments, a robot includes two or more joints, each actuated by an associated joint motor and each joint motor having a different capacity, the robot comprising an end effector configured to grasp an object. A processor coupled to the robot is configured to determine based at least in part on the respective capacities of at least a subset of the joint motors and a payload related attribute of the object a plan and trajectory to move the object from a source location to a destination location.

Abstract: Certain example embodiments relate to a method for selecting wireless ridelity (Wi-Fi) channel for mitigating and/or reducing interference, wherein the method may detect the presence of nearby access points and determine the number of access points by an access point detector module. The method may determine the minimum value of received signal strength indicator (RSSI) by the access point detector module, and may determine the congestion information from the nearby devices by a peer congestion observer module. Furthermore, the method may calculate at least one weighted parameter and select a preferred channel to create a hotspot for communication by a channel selector module.

Abstract: A Building Management System (BMS) may be controlled in accordance with predicted occupancy using a trained model. A model is trained by providing the model with time stamped environmental data and corresponding time stamped occupancy data pertaining to a training building, wherein the time stamped environmental data is derived from one or more environmental sensors of the training building and the corresponding time stamped occupancy data is derived from one or more occupancy sensors of the training building. Once trained, the trained model is provided with time stamped environmental data for a use building that is derived from one or more environmental sensors of the use building. Occupancy data for the use building is not required. The trained model outputs a predicted occupancy value that represents a predicted occupancy count in the use building, and the BMS of the use building is controlled based at least in part on the predicted occupancy value.

Abstract: A robotic sorting system, method, and device is disclosed. The robotic sorting system includes a communication interface, and one or more processors coupled to the communication interface. The one or more processors are configured to (a) obtain item data via the communication interface, the item data including an indication of one or more items to be routed across a plurality of outbound stations, (b) obtain capability data for the plurality of outbound stations, the capability data indicating one or more capabilities for at least one outbound station, (c) determine a plan to route a selected item to a destination outbound station selected from among the plurality of outbound station, the plan being determined based at least in part on the item data and the capability data for the destination outbound station, and (d) cause the plan to be implemented to route the item to a particular handling path associated with the destination outbound station.

Abstract: Various embodiments provide a robust backdoor attack on machine learning (ML)-based detection systems that can be applied to demonstrate and identify vulnerabilities thereof. In various embodiments, an artificial intelligence (AI)-based Trojan attack is generated and implanted inside a ML model trained for classification and/or detection tasks, and the AI-based Trojan attack can be triggered by specific inputs to manipulate the expected outputs of the ML model. Analysis of the behavior of an ML model having the AI-based Trojan implanted (and/or triggered) then enables identification of vulnerabilities of the ML model and further enables the design of ML models with improved security. Various embodiments of the present disclosure provide a fast and cost-effective solution in achieving 100% attack success rate that significantly outperforms adversarial attacks on ML models, thereby improving applicability and depth in testing ML-based detection systems.

Abstract: Communications are exchanged with a copy service of a host to identify writers associated with the copy service. The identification includes a type of a writer as being a system or application writer. Writers identified as system writers are added to a list of writers that should participate in a backup operation. For writers identified as application writers, components of an application writer are iterated through to determine whether a component of the application writer has a name or logical path that includes a name of a system service. When any component has the name or logical path that includes the name of the system service, the application writer is promoted to be of type system writer by adding the application writer to the list of writers that should participate in the backup operation. Components of each writer listed in the list of writers are backed up.

Abstract: Writers participating in a backup are identified. A mapping is generated between the writers and associated files. The mapping includes file properties. The mapping is initialized by tagging the writers with a full backup tag. A base backup copy of the writers is created by conducting a full backup of each writer tagged with the full backup tag. At a current backup operation after creating the base backup, a list of current files that will participate in the current backup operation is generated. The list of current files is compared against the files in the mapping to determine whether a particular writer associated with a current file should be tagged with the full backup tag or an incremental backup tag. The particular writer is tagged with the incremental backup tag when file properties associated with the current file have changed.

Abstract: Writers participating in a backup are identified. A mapping is generated between the writers and associated files. The mapping includes file properties. The mapping is initialized by tagging the writers with a full backup tag. A base backup copy of the writers is created by conducting a full backup of each writer tagged with the full backup tag. At a current backup operation after creating the base backup, a list of current files that will participate in the current backup operation is generated. The list of current files is compared against the files in the mapping to determine whether a particular writer associated with a current file should be tagged with the full backup tag or an incremental backup tag. The particular writer is tagged with the incremental backup tag when file properties associated with the current file have changed.

Abstract: According to some embodiments, systems and methods are provided, including a memory storing processor-executable code; and a processing unit to execute the executable program code to: execute an automation test for a user interface application, wherein execution of the automation test includes accessing a web-object; determine whether the web-object is included in an object repository; in a case it is determined the web-object is not included in the object repository, create the web-object in the object repository; and in a case it is determined the web-object is included in the object repository: determine whether the accessed web-object includes at least one different property from the web-object included in the object repository; and update the web-object included in the object repository with the at least one different property in the accessed web-object. Numerous other aspects are provided.

Abstract: The present disclosure describes systems and methods for hardware-assisted malware detection. One such system comprises a memory; and a hardware processor of a computing device operatively coupled to the memory. The hardware processor is configured to execute a software application suspected of being malware; monitor behavior of the software application at run-time; and acquire an input time sequence of data records based on a trace analysis of the software application, wherein the input time sequence comprises a plurality of features of the software application. The hardware processor is further configured to classify the software application as being a malicious software application based on the plurality of features of the software application; and output a ranking of a subset plurality of features by their respective contributions towards the classification of the software application as being malicious software.

Abstract: Described is a system for synchronizing expiration times for incremental backup data stored on a cloud-based object storage. More particularly, the system may provide a layer of intelligence when updating the expiration times associated with backup data to ensure that a full recovery of the client data to a point-in-time of any incremental backup may be performed. To provide such a capability, the system may maintain specialized metadata identifying expiration times for objects and a list of objects required to perform a full recovery to a point-in-time for each of the performed backups (e.g. full or incremental). The system may access this metadata to identify which objects stored by a previous backup are still referenced by a subsequent backup. Based on the identified objects, the system may synchronize object expiration times to ensure objects are not prematurely deleted from the object storage.

Abstract: Various examples are provided related to software and hardware architectures that enable lightweight and real-time Denial-of-Service (DoS) and Distributed Denial-of-Service (DDoS) attack detection. In one example, among others, a method for detection and localization of denial-of-service (DoS) attacks includes detecting, by a router of an intellectual property (IP) core in a network-on-chip (NoC) based system-on-chip (SoC) architecture, a compromised packet stream based at least in part upon a packet arrival curve (PAC) associated with the router; identifying, by the IP core, a candidate IP core in the NoC as a potential attacker based at least in part upon a destination packet latency curve (DLC) associated with the IP core; and transmitting, by the router, a notification message indicating that the candidate IP core is the potential attacker to a router of the candidate IP core.

Abstract: An exemplary strike box is configured for use with a lockset including a bolt operable to move in an extending direction and a retracting direction. The strike box includes a housing having an opening sized and configured to receive the bolt, and further includes a bolt-slowing mechanism mounted in the housing. The bolt-slowing mechanism is configured to engage the bolt as the bolt moves in the extending direction, and to exert a force urging the bolt in the retracting direction. The force exerted by the bolt-slowing mechanism slows the extension speed of the bolt, such that the strike box reduces noise generated during such extension.

Abstract: A 5G or 6G communication system for supporting a higher data transmission rate in certain example instances. Certain example embodiments may provide a method for managing PAN devices in a cluster using a first PAN device in the cluster of the PAN devices. The method may include receiving an input comprising an inner cluster attribute from a user. The method may include determining that the first PAN device has the inner cluster attribute. The method may include determining whether an inner cluster corresponding to the inner cluster attribute is available under the cluster, where the inner cluster comprises a subset of the PAN devices with the inner cluster attribute. The method may include joining the inner cluster, in response to determining that the inner cluster is available under the cluster. The method may include creating the inner cluster, in response to determining that the inner cluster is not available under the cluster.

Abstract: The present disclosure describes systems and methods for test pattern generation to detect a hardware Trojan using delay-based analysis. One such method comprises determining a set of initial test patterns to activate the hardware Trojan within an integrated circuit design; and generating a set of succeeding test patterns to activate the hardware Trojan within the integrated circuit design using a reinforcement learning model. The set of initial test patterns can be applied as an input to the reinforcement learning model. Further, the reinforcement learning model can be trained with a stochastic learning scheme to increase a probability of triggering one or more rare nodes in the integrated circuit design and identify optimal test vectors to maximize delay-based side-channel sensitivity when the hardware Trojan is activated in the integrated circuit design. Other methods and systems are also provided.

Abstract: A method for identifying a user of an electronic device, includes: capturing at least one image frame of a portion of the user’s face; extracting facial descriptors from the at least one image frame of the portion of the user’s face; generating first facial descriptor coordinates by using the facial descriptors; determining a first distance between the first facial descriptor coordinates and second facial descriptor coordinates; resizing the first facial descriptor coordinates at least one of radially and angularly based on the first distance between the first facial descriptor coordinates and the second facial descriptor coordinates, and a weight associated with the facial descriptors used to generate the first facial descriptor coordinates.

Abstract: Various examples are provided related to software and hardware architectures that enable lightweight and trust-aware routing. In one example, among others, a method for trust-aware routing includes calculating trust values to represent how much a node can be trusted to route packets through its router. Each node can store the trust values of routers that are one hop and two hops away from it, which represent direct trust and delegated trust, respectively. When a router receives a packet, the router can update trust values and forward the packet to the next hop.

Abstract: Various embodiments provide methods, apparatuses, computer program products, systems, and/or the like for an efficient framework that enables explainability machine learning for various machine learning-based tasks. In various embodiments, the framework for explainable ML is configured for acceleration and efficient computing using hardware accelerators. To provide acceleration of explainable ML, various embodiments exploit synergies between convolution operations for data objects (e.g., matrix, images, tensors, arrays) and Fourier transform operations, and various embodiments apply these synergies in hardware accelerators configured to perform such operations. Accordingly, various embodiments of the present disclosure may be applied in order to provide real-time or near real-time outcome interpretation in various machine learning-based tasks. Extensive experimental evaluations demonstrate that various embodiments described herein can provide drastic improvement in interpretation time (e.g.

Abstract: A method for selectively etching at least one feature in a first region with respect to a second region of a stack is provided. The first region is selectively etched with respect to the second region to form at least one partial feature in the first region, the at least one partial feature having a depth with respect to a surface of the second region. An in-situ a fluorine-free, non-conformal, carbon-containing mask is deposited over the first region and the second region, wherein the carbon-containing mask is selectively deposited on the second region at a second thickness with respect to the first region at a first thickness, the second thickness being greater than the first thickness. The first region is further etched in-situ to etch the at least one partial feature and wherein the carbon-containing mask acts as an etch mask for the second region.

Abstract: Described is a system for rule-based re-tiering of backup data stored on a cloud-based object storage. More specifically, the system may re-tier objects based on one or more storage rules such that the system retains the ability to efficiently perform a full restore of backup data even when incremental backups are performed to a cloud-based object storage. To provide such a capability, the system may maintain a specialized metadata database that stores information indicating the backup time for each backup, and a list of objects required to perform a full restore to each of the backup times. Accordingly, when initiating a re-tiering based on one or more storage rules, the system may intelligently select candidate objects for re-tiering by leveraging the metadata database to ensure that objects that may still need to be referenced are not unnecessarily moved to a lower storage tier.