Abstract: A method is provided for embedding an integrated circuit (IC) into a 3D-printed object. The method includes providing a filament having a material for 3D-printing an object, and an integrated circuit embedded within the filament material. The filament is used to form at least part of the 3D-printed object. A 3D-printing system is provided for implementing the method. The 3D-printing system includes a filament dispenser for storing and dispensing the 3D-printing filament. A platform provides a work surface for supporting the object as the object is being printed. A processor is provided for controlling a printing operation of the 3D-printer, and for 3D-printing the object with the filament having the ICs embedded therein. A configuration circuit is provided for configuring the IC as the IC is embedded in the 3D-printed object.

Abstract: A method and data processing system are provided for detecting a malicious component in a data processing system. The malicious component may be of any type, such as a hardware trojan, malware, or ransomware. In the method, a plurality of counters is used to count events in the data processing system during operation, where each event has a counter associated therewith. A machine learning model is trained a normal pattern of behavior of the data processing system using the event counts. After training, an operation of the data processing system is monitored using the machine learning model. Current occurrences of events in the data processing system are compared to the normal pattern of behavior. If a different pattern of behavior is detected, an indication, such as a flag, of the different pattern of behavior is provided.

Abstract: A method is provided for shuffling an order of a plurality of data blocks. In the method, a random number is generated, the random number corresponding to an index for a data block of the plurality of data blocks, where each data block of the plurality of data blocks has an index that uniquely identifies each data block of the plurality of data blocks. The increment function with a parameter is applied to the random number to generate a new index, the new index corresponds to a data block of the plurality of data blocks. The data block corresponding to the new index is selected as the next data block of a reordering of the plurality of data blocks. The method is iterated until the reordering of the plurality of data blocks is complete.

Abstract: A method for protecting a machine learning model is provided. In the method, a first machine learning model is trained, and a plurality of machine learning models derived from the first machine learning model is trained. Each of the plurality of machine learning models may be different from the first machine learning model. During inference operation, a first input sample is provided to the first machine learning model and to each of the plurality of machine learning models. The first machine learning model generates a first output and the plurality of machine learning models generates a plurality of second outputs. The plurality of second outputs are aggregated to determine a final output. The final output and the first output are classified to determine if the first input sample is an adversarial input. If it is adversarial input, a randomly generated output is provided instead of the first output.

Abstract: A method and data processing system for making a machine learning model more resistant to adversarial examples are provided. In the method, an input for a machine learning model is provided. A randomly generated mask is added to the input to produce a modified input. The modified input is provided to the machine learning model. The randomly generated mask negates the effect of a perturbation added to the input for causing the input to be an adversarial example. The method may be implemented using the data processing system.

Abstract: A method is provided for detecting copying of a machine learning model. A plurality of inputs is provided to a first machine learning model. The first machine learning model provides a plurality of output values. A sequence of bits of a master input is divided into a plurality of subsets of bits. The master input may be an image. Each subset of the plurality of subsets of bits corresponds to one of the plurality of output values. An ordered sequence of the inputs is generated based on the plurality of subsets of bits. The ordered sequence of the inputs is inputted to a second machine learning model. It is then determined if output values from the second machine learning model reproduces the predetermined master input. If the predetermined master input is reproduced, the second machine learning model is a copy of the first machine learning model.

Abstract: A data processing system includes a processor, a cache memory, a speculative cache memory, and a control circuit. The processor is for executing instructions. The cache memory is coupled to the processor and is for storing the instructions and related data. A speculative cache is coupled to the processor and is for storing only speculative instructions and related data. The control circuit is coupled to the processor, to the cache memory, and to the speculative cache. The control circuit is for causing speculative instructions to be stored in the speculative cache in response to receiving an indication from the processor. Also, a method is provided for speculative execution in the data processing system.

Abstract: A method is provided for managing a machine learning system. In the method, a database is provided for storing a plurality of data elements. A plurality of machine learning models is trained using assigned subsets of the plurality of data elements. The outputs of the plurality of machine learning models is provided to an aggregator. During inference operation of the machine learning system, the aggregator determines a final output based on outputs from the plurality of models. If it is determined that an assigned subset must be changed because, for example, a record must be deleted, then the data element is removed from the selected assigned subset. The affected machine learning model associated with the changed assigned subset is removed, and retrained using the changed assigned subset.

Abstract: A method is provided for embedding an integrated circuit (IC) into a 3D-printed object. The method includes providing a filament having a material for 3D-printing an object, and an integrated circuit embedded within the filament material. The filament is used to form at least part of the 3D-printed object. A 3D-printing system is provided for implementing the method. The 3D-printing system includes a filament dispenser for storing and dispensing the 3D-printing filament. A platform provides a work surface for supporting the object as the object is being printed. A processor is provided for controlling a printing operation of the 3D-printer, and for 3D-printing the object with the filament having the ICs embedded therein. A configuration circuit is provided for configuring the IC as the IC is embedded in the 3D-printed object.

Abstract: Various embodiments relate to a method of producing a machine learning model with a fingerprint that maps an input value to an output label, including: selecting a set of extra input values, wherein the set of extra input values does not intersect with a set of training labeled input values for the machine learning model; selecting a first set of artificially encoded output label values corresponding to each of the extra input values in the set of extra input values, wherein the first set of artificially encoded output label values are selected to indicate the fingerprint of a first machine learning model; and training the machine learning model using a combination of the extra input values with associated first set of artificially encoded output values and the set of training labeled input values to produce the first learning model with the fingerprint.

Abstract: A method is provided for shuffling an order of a plurality of data blocks. In the method, a random number is generated, the random number corresponding to an index for a data block of the plurality of data blocks, where each data block of the plurality of data blocks has an index that uniquely identifies each data block of the plurality of data blocks. The increment function with a parameter is applied to the random number to generate a new index, the new index corresponds to a data block of the plurality of data blocks. The data block corresponding to the new index is selected as the next data block of a reordering of the plurality of data blocks. The method is iterated until the reordering of the plurality of data blocks is complete.

Abstract: A data processing system includes a processor, a cache memory, a speculative cache memory, and a control circuit. The processor is for executing instructions. The cache memory is coupled to the processor and is for storing the instructions and related data. A speculative cache is coupled to the processor and is for storing only speculative instructions and related data. The control circuit is coupled to the processor, to the cache memory, and to the speculative cache. The control circuit is for causing speculative instructions to be stored in the speculative cache in response to receiving an indication from the processor. Also, a method is provided for speculative execution in the data processing system.