Patents by Inventor Miriam Silver

Miriam Silver has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20260351031
    Abstract: Presented herein are systems and methods for the employment of machine learning models for image processing as may be performed by computing devices associated with an end user. A method may include obtaining video data comprising a plurality of frames including a document of a document type. The method may include executing an object recognition engine of a machine-learning architecture using image data of the plurality of frames, the object recognition engine trained to detect edges of documents. The method may include identifying, based on the edge detection, a plurality of boundaries for the document. The method may include validating, based on the plurality of boundaries, the document as the document type. The method may include transmitting via one or more networks, to a computer remote from the computing device, responsive to the validation of the type of document, the image data for the plurality of frames depicting the document.
    Type: Application
    Filed: July 13, 2026
    Publication date: November 5, 2026
    Applicant: Citibank, N.A.
    Inventors: Ashutosh K. SUREKA, Venkata Sesha Kiran Kumar ADIMATYAM, Miriam SILVER, Daniel FUNKEN
  • Patent number: 12783615
    Abstract: Systems, methods, and devices for facilitating computational resource access by artificial intelligence (AI) agents through token-based allocation and multi-agent workflow optimization. The system generates tokens corresponding to computational resources including processing power, memory, storage, and bandwidth. AI agents submit resource requests with priority tokens, creating queues ordered by priority token quantity. Higher-priority bids receive preferential positions. The system transfers resource tokens to agents based on queue order, enabling resource access through token exchange. The system can receive user prompts indicating computational objectives and determines multiple AI agentic approaches comprising AI model sequences. After evaluating approaches against operational policies, the system generates resource utilization and performance estimates, executing a preferred approach balancing efficiency with output quality.
    Type: Grant
    Filed: March 2, 2026
    Date of Patent: November 3, 2026
    Assignee: Citibank, N.A.
    Inventors: Ganesh Prasad Bhat, James Myers, Payal Jain, Tariq Husayn Maonah, Mariusz Saternus, Daniel Lewandowski, Biraj Krushna Rath, Stuart Murray, Philip Davies, Sourabh Deb, Jason Engelbrecht, Zheyu Wang, Haolin Jin, Avi Levin, Nimrod Barak, Miriam Silver
  • Patent number: 12775603
    Abstract: Systems and methods for a programming language-agnostic data modeling platform that is both less resource intensive and scalable. Additionally, the programming language-agnostic data modeling platform allows for advanced analytics to be run on descriptions of the known logical data models, to generate data offerings describing underlying data, and to easily format data for compatibility with artificial intelligence systems. The systems and methods use a supplemental data structure that comprises logical data modeling metadata, in which the logical data modeling metadata describes the logical data model in a common, standardized language. For example, the logical data modeling metadata may comprise a transformer lineage of the logical data model.
    Type: Grant
    Filed: January 27, 2025
    Date of Patent: October 27, 2026
    Assignee: Citibank, N.A.
    Inventors: Chuan Li, James Boyd Adams, Yan Liu, Peter Huang, Alicia Wang, Miriam Silver
  • Patent number: 12762253
    Abstract: The systems and methods disclosed herein receives artifacts generated using a first set of models within a multi-model superstructure. The multi-model superstructure includes a second set of models to test the first set of models. The multi-model superstructure dynamically routes the artifacts of the first set of models to one or more models of the second set of models by (i) determining a set of dimensions of the artifacts against which to evaluate the artifacts and (ii) identifying the models in the second set used to test the particular dimension. The second set of models then assesses each artifact against a set of assessment metrics. If an artifact fails to meet one or more assessment metrics, the second set of models generates actions to align the artifact with the set of assessment metrics.
    Type: Grant
    Filed: April 18, 2025
    Date of Patent: October 13, 2026
    Assignee: CITIBANK, N.A.
    Inventors: Sofia Rahman, James Myers, Prashant Praveen, Shardul Malviya, Wayne Liao, Deepak Jain, Samantha Cory, Mariusz Saternus, Daniel Lewandowski, Biraj Krushna Rath, Stuart Murray, Philip Davies, Payal Jain, Tariq Husayn Maonah, Vishal Mysore, Ramkumar Ayyadurai, Chamindra Desilva, William Franklin Cameron, Miriam Silver, Prithvi Narayana Rao, Pramod Goyal, Manjit Rajaretnam
  • Patent number: 12756673
    Abstract: The systems and methods disclosed herein load a monitoring program into a kernel or other monitoring component of an operating system external to a user space. The monitoring program attaches to at least one hook point associated with execution of an artificial intelligence agent and captures a plurality of event records (a process identifier, an operation identifier, a resource identifier, a timestamp) associated with the agent. The system generates a cryptographic value by applying one or more functions to a representation of at least a subset of the event records and maintains the cryptographic value on a distributed database within a record associated with the agent. The distributed database maintains a sequence of records that links each record to one or more previous records. The system can detect anomalous agent operations and execute enforcement actions within the monitoring component that restrict agent execution.
    Type: Grant
    Filed: May 15, 2026
    Date of Patent: October 6, 2026
    Assignee: Citibank, N.A.
    Inventors: Vishal Mysore, Prithvi Narayana Rao, Payal Jain, Sawyer Uzzell, Joao Paulo De Castro Marchese, James Randolph Myers, Ganesh Prasad Bhat, Miriam Silver
  • Patent number: 12755160
    Abstract: The systems and methods disclosed herein provide a lightweight artificial intelligence agent router that dynamically allocates tasks across a plurality of stateless AI agents. The router receives a task request and classifies it into one or more task types by comparing the request against historical task-agent pairings stored in a datastore. Each agent is registered in an agent registry that includes a metadata profile with performance metrics derived from prior executions. The router scores each agent by evaluating these performance metrics against the classified task type to rank the agents and select a subset of the agents whose scores satisfy a threshold value. The router determines an execution order by evaluating dependencies between sequential portions of the task request, thereby ensuring that outputs from earlier agents are available as inputs to subsequent agents. After task completion, the router updates the agent registry with execution results to adjust future routing decisions.
    Type: Grant
    Filed: March 18, 2026
    Date of Patent: October 6, 2026
    Assignee: Citibank, N.A.
    Inventors: Miriam Silver, James Myers, William Franklin Cameron, Prithvi Narayana Rao, Ganesh Prasad Bhat, Sourabh Deb, Jason Engelbrecht, Zheyu Wang, Haolin Jin
  • Publication number: 20260303545
    Abstract: Systems and methods disclosed herein enforce agent compliance using kernel-level eBPF programs. The system obtains a machine-readable data structure defining operative boundaries for a target AI agent set and generates a reference value by applying a transformation operation on the data structure. The system loads eBPF programs and policy maps into a kernel, attaching them to hook points to intercept agent operations. Kernel-captured events are received via a kernel event stream, and an observer component generates a kernel-attested observed value by canonically serializing the events and applying a second transformation operation. A compliance comparator determines verification status by comparing the reference value with the observed value. When non-compliance is detected, the system loads an enforcement program into the kernel to restrict agent operations.
    Type: Application
    Filed: June 16, 2026
    Publication date: October 1, 2026
    Applicant: Citibank, N.A.
    Inventors: James Randolph MYERS, Miriam SILVER, Ganesh Prasad BHAT
  • Patent number: 12744806
    Abstract: Presented herein are systems and methods for generating suspicious activity reports using large language models. A system may include one or more processors that obtain event data associated with an event from a client device and from one or more databases, apply a prompt generator on the event data to generate a large language model (LLM) prompt, and generate a machine-readable suspicious activity (SAR) report in accordance with an LLM prompt. The one or more processors may also apply the prompt generator on the event data based on determining that a fraud risk score associated with the event satisfies a reporting threshold score. Computer program products are also presented.
    Type: Grant
    Filed: November 25, 2024
    Date of Patent: September 22, 2026
    Assignee: Citibank, N.A.
    Inventors: Girish Wali, Deepali Tuteja, Prasanth Babu Madakasira Ramakrishna, Brett Pickard, Saketh Ram Gurumurthi, Miriam Silver
  • Publication number: 20260281059
    Abstract: The systems and methods disclosed herein load a monitoring program into a kernel or other monitoring component of an operating system external to a user space. The monitoring program attaches to at least one hook point associated with execution of an artificial intelligence agent and captures a plurality of event records (a process identifier, an operation identifier, a resource identifier, a timestamp) associated with the agent. The system generates a cryptographic value by applying one or more functions to a representation of at least a subset of the event records and maintains the cryptographic value on a distributed database within a record associated with the agent. The distributed database maintains a sequence of records that links each record to one or more previous records. The system can detect anomalous agent operations and execute enforcement actions within the monitoring component that restrict agent execution.
    Type: Application
    Filed: May 15, 2026
    Publication date: September 17, 2026
    Inventors: Vishal Mysore, Prithvi Narayana Rao, Payal Jain, Sawyer Uzzell, Joao Paulo De Castro Marchese, James Randolph Myers, Ganesh Prasad Bhat, Miriam Silver
  • Publication number: 20260253137
    Abstract: Presented herein are systems and methods for the employment of machine learning models for image processing. A mobile application for client-side image processing and validation, which interacts with and leverages native image processing software of the client device, where the image processing software and the mobile application include any number of machine-learning models for identifying a document and attributes of the document for recognition and validation. This mobile application uses the image processing software from a client operating system to control the camera. The image processing software generates various types of information about a video frame and the document, and the mobile application invokes APIs or software libraries of the image processing software to access the information and validate the frame and document.
    Type: Application
    Filed: April 20, 2026
    Publication date: August 27, 2026
    Applicant: Citibank, N.A.
    Inventors: Ashutosh K. SUREKA, Venkata Sesha Kiran Kumar ADIMATYAM, Miriam SILVER, Daniel FUNKEN, Toan PHAM, Vicky KAPADIA, Sakthivel PALANIVEL, Anurag BHAKOO
  • Publication number: 20260253136
    Abstract: Presented herein are systems and methods for the employment of machine learning models for image processing. A mobile application for client-side image processing and validation, which interacts with and leverages native image processing software of the client device, where the image processing software and the mobile application include any number of machine-learning models for identifying a document and attributes of the document for recognition and validation. This mobile application uses the image processing software from a client operating system to control the camera. The image processing software generates various types of information about a video frame and the document, and the mobile application invokes APIs or software libraries of the image processing software to access the information and validate the frame and document.
    Type: Application
    Filed: April 20, 2026
    Publication date: August 27, 2026
    Applicant: Citibank, N.A.
    Inventors: Ashutosh K. SUREKA, Venkata Sesha Kiran Kumar ADIMATYAM, Miriam SILVER, Daniel FUNKEN, Toan PHAM, Vicky KAPADIA, Sakthivel PALANIVEL, Anurag BHAKOO
  • Publication number: 20260252712
    Abstract: Systems and methods for generating predicted end-to-end cyber-security attack characteristics via bifurcated machine learning-based processing of multi-modal data are disclosed. The system accesses multi-modal data indicating a set of security information related to a computing system. The system then generates a set of extracted characteristics indicating a cyber-security attack on the computing system, via a supervised machine learning model, using the multi-modal data. Using this information, the system generates a revised set of extracted characteristics indicating the cyber-security attack, via an unsupervised machine learning model, using the extracted set of characteristics indicating the cyber-security attack, where the revised set of characteristics includes at least one new characteristic that was not included in the extracted set of characteristics indicating the cyber-security attack on the computing system.
    Type: Application
    Filed: April 17, 2026
    Publication date: August 27, 2026
    Inventors: William Franklin Cameron, Pramod Goyal, Prithvi Narayana Rao, Manjit Rajaretnam, Miriam Silver
  • Patent number: 12718605
    Abstract: Presented herein are systems and methods for the employment of machine learning models for image processing as may be performed by computing devices associated with an end user. A method may include obtaining video data comprising a plurality of frames including a document of a document type. The method may include executing an object recognition engine of a machine-learning architecture using image data of the plurality of frames, the object recognition engine trained to detect edges of documents. The method may include identifying, based on the edge detection, a plurality of boundaries for the document. The method may include validating, based on the plurality of boundaries, the document as the document type. The method may include transmitting via one or more networks, to a computer remote from the computing device, responsive to the validation of the type of document, the image data for the plurality of frames depicting the document.
    Type: Grant
    Filed: August 7, 2025
    Date of Patent: August 25, 2026
    Assignee: Citibank, N.A.
    Inventors: Ashutosh K. Sureka, Venkata Sesha Kiran Kumar Adimatyam, Miriam Silver, Daniel Funken
  • Publication number: 20260244998
    Abstract: Systems and methods for detecting anomalies in generative outputs are disclosed herein. The system receives a user prompt indicating a request for data over a time period. The system inputs, into a model, the user prompt to cause the model to generate an output based on the user prompt. The system then generates the first tokens based on the output. To generate the second tokens, the system retrieves, based on the user prompt, sources relating to the data requested by the user prompt. The system then generates queries to request, from the sources, the data over the time period and generates the second tokens based on the retrieved data. The system then performs a comparison of the first tokens and the second tokens and accepts or rejects the output of the model based on the comparison.
    Type: Application
    Filed: April 13, 2026
    Publication date: August 20, 2026
    Inventors: Nigil Satish Jeyashekar, Miriam Silver, James Randolph Myers, Payal Jain, Tariq Husayn Maonah, Mariusz Saternus, Daniel Lewandowski, Biraj Krushna Rath, Stuart Murray, Philip Davies
  • Publication number: 20260244759
    Abstract: Described herein are systems and methods for discovering and proactively mitigating previously unknown security vulnerabilities. The systems and methods herein can utilize security vulnerability information to discover potential security threats and can utilize this information to generate an attack using a machine learning model, such as a large language model. Generated attacks can be carried out to assess impact of a security vulnerability. An output can be provided that represents the assessed impact. In some implementations, the systems and methods herein generate patches or other mitigations for security vulnerabilities, which can be tested and deployed to address security vulnerabilities.
    Type: Application
    Filed: November 17, 2025
    Publication date: August 20, 2026
    Inventors: William Franklin Cameron, Pramod Goyal, Prithvi Narayana Rao, Manjit Rajaretnam, Miriam Silver
  • Publication number: 20260220552
    Abstract: Systems and methods described herein enable adaptive, threshold-based modification of node maps representing ontologies, knowledge graphs, or code development pipelines using generative artificial intelligence. The disclosed platform can retrieve a node map and generate one or more candidate perturbations that modify nodes or relationships within the node map. The disclosed platform can evaluate the effect of the perturbations by comparing respective outputs against ground-truth data. Perturbations can be automatically determined based on changes in external datasets, compliance policies, or operational requirements. The perturbations can be implemented when a computed perturbation quality value satisfies a threshold quality criterion. As such, the system enables efficient, policy-compliant evolution of relational system architectures in dynamic environments.
    Type: Application
    Filed: March 26, 2026
    Publication date: July 30, 2026
    Inventors: James Myers, Ganesh Prasad BHAT, Tariq Husayn Maonah, Mariusz Saternus, Daniel Lewandowski, Biraj Krushna Rath, Stuart Murray, Philip Davies, Nigil Satish Jeyashekar, Miriam Silver, Payal Jain
  • Publication number: 20260211906
    Abstract: Presented herein are systems and methods for aggregating data from disparate sources using generative models. A computing system may retrieve, from a plurality of data sources, a first plurality of datasets for at least one of a plurality of features for a network environment over a first time period. The computing system may execute a first generative model using the first plurality of datasets to create a second plurality of datasets. The computing system may identify, from the second plurality of datasets, at least one dataset corresponding to a feature of the plurality of features. The one or more processors may execute select at least one machine learning model based on the feature. The computing system may execute the at least one ML model using the dataset to determine an output. The computing system may cause displaying of a visualization of the output via a graphical user interface.
    Type: Application
    Filed: January 16, 2026
    Publication date: July 23, 2026
    Applicant: CITIBANK, N.A.
    Inventors: Deepali TUTEJA, Girish WALI, David Anandaraj ARULRAJ, Miriam SILVER
  • Publication number: 20260212195
    Abstract: The systems and methods disclosed herein provide a lightweight artificial intelligence agent router that dynamically allocates tasks across a plurality of stateless AI agents. The router receives a task request and classifies it into one or more task types by comparing the request against historical task-agent pairings stored in a datastore. Each agent is registered in an agent registry that includes a metadata profile with performance metrics derived from prior executions. The router scores each agent by evaluating these performance metrics against the classified task type to rank the agents and select a subset of the agents whose scores satisfy a threshold value. The router determines an execution order by evaluating dependencies between sequential portions of the task request, thereby ensuring that outputs from earlier agents are available as inputs to subsequent agents. After task completion, the router updates the agent registry with execution results to adjust future routing decisions.
    Type: Application
    Filed: March 18, 2026
    Publication date: July 23, 2026
    Inventors: Miriam SILVER, James MYERS, William Franklin CAMERON, Prithvi Narayana RAO, Ganesh Prasad BHAT, Sourabh DEB, Jason ENGELBRECHT, Zheyu WANG, Haolin JIN
  • Patent number: 12688667
    Abstract: Presented herein are systems and methods for the employment of machine learning models for image processing. A method may include a capture of a video feed including image data of a document at a client device. The client device can provide the video feed to another computing device. The method can include, by the client device or the other computing device object recognition for recognizing a type of document and capturing an image exceeding a quality threshold of the document amongst the frames within the video feed. The method may further include the execution of other image processing operations on the image data to improve the quality of the image or features extracted therefrom. The method may further include anti-fraud detection or scoring operations to determine an amount of risk associated with the image data.
    Type: Grant
    Filed: April 4, 2025
    Date of Patent: July 21, 2026
    Assignee: CITIBANK, N.A.
    Inventors: Ashutosh K. Sureka, Venkata Sesha Kiran Kumar Adimatyam, Miriam Silver, Daniel Funken
  • Publication number: 20260203417
    Abstract: The present disclosure relates to systems, methods, and devices for providing a centralized data store that receives and transmits data via agents that operate independently of one another. In some implementations, the agents transform data prior to transmission to the centralized data store. In some implementations, the centralized data store is configured to transform data. The centralized data store can evaluate, route, score, and otherwise manipulate and select received data. The centralized data store can respond to data requests based at least in part on its evaluation of received data.
    Type: Application
    Filed: February 20, 2026
    Publication date: July 16, 2026
    Inventors: Miriam Silver, William Franklin Cameron, Prithvi Narayana Rao