Abstract: In some examples, a method of vector-raster data fusion includes receiving vector data for a geographical location, and statistically analyzing the vector data to obtain vector statistics. In some examples the method further includes rasterizing the vector statistics, and storing at least one of the vector data and the rasterized vector statistics together in a key-value store together with previously stored raster data for the geographical location. In some examples, the vector data further includes metadata, and the method further includes storing the metadata in at least one of the key-value store or a separate vector database.

Abstract: Mechanisms are provided to provide an improved computer tool for determining and mitigating the presence of adversarial inputs to an image classification computing model. A machine learning computer model processes input data representing a first image to generate a first classification output. A cohort of second image(s), that are visually similar to the first image, is generated based on a comparison of visual characteristics of the first image to visual characteristics of images in an image repository. A cohort-based machine learning computer model processes the cohort of second image(s) to generate a second classification output and the first classification output is compared to the second classification output to determine if the first image is an adversarial image. In response to the first image being determined to be an adversarial image, a mitigation operation by a mitigation system is initiated.

Abstract: An example operation may include one or more of creating a source file, segmenting the source file into source file segments, creating a number of auxiliary data segments corresponding to source file segments, performing a chameleon hash of the source file segments and the auxiliary data segments, obtaining a source file signature from the chameleon hash, performing a cryptographic hash of the auxiliary data segments, obtaining an auxiliary data signature from the cryptographic hash, and storing the source file and cryptographic signatures to a shared ledger of a blockchain network. Each auxiliary data segment includes a random string of data that is generated based on a corresponding source file segment.

Abstract: Methods and systems for managing vegetation include training a machine learning model based on an image of a training data region before a weather event, an image of the training data region after the weather event, and information regarding the weather event. A risk score is generated for a second region using the trained machine learning model based on an image of the second region and predicted weather information for the second region. The risk score is determined to indicate high-risk vegetation in the second region. A corrective action is performed to reduce the risk of vegetation in the second region.

Abstract: Mechanisms are provided for training a classifier to identify adversarial input data. A neural network processes original input data representing a plurality of non-adversarial original input data and mean output learning logic determines a mean response for each intermediate layer of the neural network based on results of processing the original input data. The neural network processes adversarial input data and layer-wise comparison logic compares, for each intermediate layer of the neural network, a response generated by the intermediate layer based on processing the adversarial input data, to the mean response associated with the intermediate layer, to thereby generate a distance metric for the intermediate layer. The layer-wise comparison logic generates a vector output based on the distance metrics that is used to train a classifier to identify adversarial input data based on responses generated by intermediate layers of the neural network.

Abstract: Techniques regarding adaptive data recovery schemes are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a data management component that can modify a data recovery scheme based on performance data exhibited by a network of data centers and a data recovery requirement. The data recovery scheme can direct a relocation of data within the network.

Abstract: Mechanisms are provided to provide an improved computer tool for determining and mitigating the presence of adversarial inputs to an image classification computing model. A machine learning computer model processes input data representing a first image to generate a first classification output. A cohort of second image(s), that are visually similar to the first image, is generated based on a comparison of visual characteristics of the first image to visual characteristics of images in an image repository. A cohort-based machine learning computer model processes the cohort of second image(s) to generate a second classification output and the first classification output is compared to the second classification output to determine if the first image is an adversarial image. In response to the first image being determined to be an adversarial image, a mitigation operation by a mitigation system is initiated.

Abstract: ML model(s) are created and trained using training data from user(s) to create corresponding trained ML model(s). The training data is in FHE domains, each FHE domain corresponding to an individual one of the user(s). The trained machine learning model(s) are run to perform inferencing using other data from at least one of the user(s). The running of the ML model(s) determines results. The other data is in a corresponding FHE domain of the at least one user. Using at least the results, it is determined which of the following issues is true: the results comprise objectionable material, or at least one of the trained ML model(s) performs prohibited release of information. One or more actions are taken to take to address the issue determined to be true. Methods, apparatus, and computer program product are disclosed.

Abstract: Scalable feature classification for 3D point cloud data is provided. In one aspect, a method for rasterizing 3D point cloud data includes: obtaining the 3D point cloud data; generating a digital elevation model (DEM) from the 3D point cloud data; decomposing the DEM into local and global fluctuations to obtain a local DEM; generating geo-referenced shapes by automatically thresholding the local DEM; cropping and normalizing the local DEM using minimum bounding boxes derived from the geo-referenced shapes and manual annotations from subject matter experts to create a cropped DEM; and linking geo-spatially tagged labels from the subject matter experts to the cropped DEM. These data can be then directly fed into a system having an ensemble of artificial neural networks. By way of example, a scalable ecosystem is presented on the basis of the geo-spatial platform IBM PAIRS.

Abstract: An example operation may include one or more of joining, by a host device, a blockchain managed by one or more devices on a decentralized network, the blockchain is configured to use one or more smart contracts that specify transactions among a plurality of end-users, creating on the blockchain the smart contract defining authentication parameters for an authentication of an end-user from the plurality of the end-users, executing the smart contract to perform the authentication of the end-user associated with a transaction based on the authentication parameters by generating an authentication challenge for the transaction, and recording an authentication log produced by the authentication challenge into a metadata of a transaction payload for analytics.

Abstract: Methods and systems for generating a random number include extracting feature information from a structure having a random physical configuration. The feature information is converted to a string of binary values to generate a random number. Pseudo-random numbers are generated using the random number as a seed to improve the security of encrypted information.

Abstract: An example operation may include one or more of detecting a suspected biometric authentication incident, submitting a first blockchain transaction including a first report to a blockchain network, submitting a second blockchain transaction including a second report to the blockchain network, and taking an action, by one or more blockchain nodes, in response to determining one or more of the first and second reports are relevant to the one or more blockchain nodes. The first report includes public and private data corresponding to the suspected biometric authentication incident, and the second report includes one or more of a root cause and mitigation steps for the incident.

Abstract: Respective sets of homomorphically encrypted training data are received from multiple users, each encrypted by a key of a respective user. The respective sets are provided to a combined machine learning model to determine corresponding locally learned outputs, each in an FHE domain of one of the users. Conversion is coordinated of the locally learned outputs in the FHE domains into an MFHE domain, where each converted locally learned output is encrypted by all of the users. The converted locally learned outputs are aggregated into a converted composite output in the MFHE domain. A conversion is coordinated of the converted composite output in the MFHE domain into the FHE domains of the corresponding users, where each converted decrypted composite output is encrypted by only a respective one of the users. The combined machine learning model is updated based on the converted composite outputs. The model may be used for inferencing.

Abstract: A textual message that is nonconforming to a grammar of a language is received. The textual message is transformed into a grammatically structured interrogative form. A first sentence of a received content is scored relative to the interrogative form. The received content includes a proposal for an action in a form of a plurality of grammatically compliant structures. Based on the scoring, a response sentence having a highest score is selected. Responsive to the highest score corresponding to the response sentence being above a threshold, the response sentence is transformed into a corresponding summary phrase that is not constrained by the grammar.

Abstract: An example operation may include one or more of determining, by a file redaction device, redacted segments of a source file, receiving, by a signature update device, the redacted source file segments, a stored trapdoor key, and stored auxiliary data segments, determining modified auxiliary data from the redacted source file segments, the trapdoor key and the auxiliary data segments, executing chaincode to obtain a modified auxiliary data signature and identifiers of the redacted source file segments, and storing the modified auxiliary data signature and identifiers of the redacted source file segments to a shared ledger of a blockchain network. Each stored auxiliary data segment including a random string of data corresponding to a segment of the source file.

Abstract: An example operation may include one or more of initiating, by a file verification device, verification of a source file or a redacted source file, executing one of a smart contract or chaincode to verify the chameleon hash signature and the auxiliary data hash signature, and providing a notification whether the verification was successful or unsuccessful. In response to initiating verification of the source file, the method further includes the file verification device receiving stored source file segments and stored auxiliary data segments, generating a chameleon hash signature, and generating an auxiliary data hash signature. In response to initiating verification of the redacted source file, the method further includes receiving stored redacted file segments, stored auxiliary data segments, and stored modified auxiliary data, generating a chameleon hash signature, and generating an auxiliary data hash signature.

Abstract: An example operation may include one or more of creating a source file, segmenting the source file into source file segments, creating a number of auxiliary data segments corresponding to source file segments, performing a chameleon hash of the source file segments and the auxiliary data segments, obtaining a source file signature from the chameleon hash, performing a cryptographic hash of the auxiliary data segments, obtaining an auxiliary data signature from the cryptographic hash, and storing the source file and cryptographic signatures to a shared ledger of a blockchain network. Each auxiliary data segment includes a random string of data that is generated based on a corresponding source file segment.

Abstract: Generating a textual description of an image includes classifying an image represented by image data into a domain-specific category, and segmenting one or more elements in the image data based on the domain-specific category. Each element of the one or more elements is compared to a domain-independent model to detect one or more statistical anomalies in the one or more elements. The one or more detected statistical anomalies are characterized using one or more domain-independent text phrases. The one or more domain-independent text phrases are converted to one or more domain-specific descriptions based upon the domain-specific category.

Abstract: Scalable feature classification for 3D point cloud data is provided. In one aspect, a method for rasterizing 3D point cloud data includes: obtaining the 3D point cloud data; generating a digital elevation model (DEM) from the 3D point cloud data; decomposing the DEM into local and global fluctuations to obtain a local DEM; generating geo-referenced shapes by automatically thresholding the local DEM; cropping and normalizing the local DEM using minimum bounding boxes derived from the geo-referenced shapes and manual annotations from subject matter experts to create a cropped DEM; and linking geo-spatially tagged labels from the subject matter experts to the cropped DEM. These data can be then directly fed into a system having an ensemble of artificial neural networks. By way of example, a scalable ecosystem is presented on the basis of the geo-spatial platform IBM PAIRS.

Abstract: A bias compensation method, system, and computer program product include modifying a behavior of a first analytic engine service with a second analytic engine service, where the first service accepts user submitted data and communicates an assessment of the data in a form of a label associated with the corresponding submitted data, where the second service accepts an input and communicates an assessment in a form of a label associated with the corresponding input, and where a behavior model of the first service and the second service includes a discrepancy between the output labels by each service with respect to true labels of data accepted, further including composing a new analytic engine service from the first service and the second service to optimize a service bias in terms of a test dataset based on the behavior model and the known true assessments.