Accenture Global Solutions Limited

Columbia University

International Business Machines Corporation

Accenture Global Services Gmbh

Malek Ben Salem

Benjamin Glen McCarty

Salvatore J Stolfo

Amin Hassanzadeh

Song Luo

Shlomo Hershkop

Gary Walter Behm

Yue J Li

Angelos D Keromytis

Vasileios Kemerlis

Aolin Ding

Brian M Bowen

Pratap V Prabhu

Neil Hayden Liberman

Xiaoyong Yuan

Teresa Sheausan Tung

Keith Howard Tabakman

Shaan Mulchandani

Zhijie Wang

James J Solderitsch

Kirby James Linvill

Chien An Chen

Krishna Mohan Dasari

Rafae Bhatti

Ganesh Devarajan

Lei Ding

Mário Lauande Lacroix

John Donovan Delmare, Jr

Leah Ding

Louis William Divalentin

Steven Robert Roberts

Changwei Liu

Tennyson Yuan

Siegfried Matthias Philippe Lafon

Cristian Daniel Ariza

Mohamed Aftkhar

Aritomo Shinozaki

Nahid Farhady

Mohnish Gahlot

Bai Chien Kao

Karthik Rajkumar Kannan

Young Ki Lee

Benjamin Glen Mccarty

A code remediation system accesses a programming code including vulnerabilities such as potential secrets and remediates at least a subset of the potential secrets to generate modified programming code wherein the subset of potential secrets which are determined to be actual secrets are replaced with access mechanisms to storage locations on a vault wherein the actual secrets are secured. To identify the subset of potential secrets forming the actual secrets to be remediated, the code remediation system is configured to filter out false positives among the potential secrets and identify true positives. When an application executing the modified code encounters an access mechanism, it accesses the vault to retrieve the actual secrets.

Programming code vulnerability remediation

An Artificial Intelligence (AI) based filter apparatus includes an input filter and an output filter protecting a generative AI model and preventing restricted content from being transmitted to user devices. When a user query is received, the input filter determines if the user query can be transmitted to the generative AI model by generating an input risk score for the received user query. If the user query is transmitted and a model query response is received from the generative AI model, the output filter determines an output risk score based on which the model query response may be transmitted to the user. The input filter and the output filter each include a pre-trained language model as a base with additional layers trained to estimate the corresponding risk scores.

Artificial intelligence (AI) based data filters

Aspects of the present disclosure provide systems, methods, and computer-readable storage media that support cooperative training of machine learning (ML) models that preserves privacy in untrusted environments using distributed executable file packages. The executable file packages may include files, libraries, scripts, and the like that enable a cloud service provider configured to provide server-side ML model training to also support cooperative ML model training with multiple clients, particularly for a fraud prediction model for financial transactions. Because the cooperative training includes the clients training respective ML models and the server aggregating the trained ML models, private client data such as financial transaction data may be used to train the fraud prediction model without exposing the client data to others. Such cooperative ML model training enables offloading of computing resource-intensive training from client devices to the server and may train a more robust fraud detection model.

Privacy-preserving collaborative machine learning training using distributed executable file packages in an untrusted environment

A device may receive a machine learning model, training data, a pipeline configuration for the machine learning model, and impact costs associated with customer preferences, and may perform assessments of the machine learning model to identify attacks associated with the machine learning model and vulnerabilities associated with the attacks. The device may map the vulnerabilities to threats, may map the threats to the impact costs, and may determine success rates of the threats. The device may calculate probabilities of the threats based on the vulnerabilities and the success rates, and may calculate risk costs of the attacks based on the probabilities and the impact costs. The device may identify controls for limiting the vulnerabilities and control costs. The device may determine a total cost for eliminating the risk costs based on the risk costs and the control costs, and may perform actions based on the total cost.

Identifying and assessing costs associated with correcting vulnerabilities in machine learning models

Aspects of the present disclosure provide systems, methods, and computer-readable storage media that support secure training of machine learning (ML) models that preserves privacy in untrusted environments using distributed executable file packages. The executable file packages may include files, libraries, scripts, and the like that enable a cloud service provider configured to provide ML model training based on non-encrypted data to also support homomorphic encryption of data and ML model training with one or more clients, particularly for a diagnosis prediction model trained using medical data. Because the training is based on encrypted client data, private client data such as patient medical data may be used to train the diagnosis prediction model without exposing the client data to the cloud service provider or others. Using homomorphic encryption enables training of the diagnosis prediction model using encrypted data without requiring decryption prior to training.

Privacy-preserving machine learning training based on homomorphic encryption using executable file packages in an untrusted environment

A device may receive digital content and may process the digital content, with at least one of an optimization-based poisoning model or a statistical-based poisoning model, to generate at least one of first poisoning data or second poisoning data, respectively. The device may generate new digital content based on the digital content and the at least one of the first poisoning data or the second poisoning data. The device may provide the new digital content to one or more devices to be accessed by at least one deepfake model used to create fake digital content and may perform one or more actions based on the new digital content.

Methods and systems for protecting digital content against artificial intelligence-based unauthorized manipulation of the digital content

Methods, systems and apparatus, including computer programs encoded on computer storage medium, for implementation of secret superposition protocols. In one aspect a method includes, performing, by a sender party, quantum operations on one or more qubits, comprising preparing, according to a predetermined secret superposition protocol, one or more qubits in respective uniform superposition quantum states; transmitting, by the sender party, to a recipient party, and through a secure channel, data indicating use of the predetermined secret superposition protocol; and transmitting, by the sender party and to the recipient party, one or more of the qubits, to wherein the recipient party performs one or more measurements on the qubits to verify use of the predetermined secret superposition protocol.

Secret superposition protocols for quantum computation

Methods, systems, and apparatus for transmitting qubits encoding quantum information with reduced risk of interception from an eavesdropper. In one aspect, a method includes encoding quantum information into an information qubit; encrypting the information qubit, comprising performing i) a parity operation on the information qubit and a parity control qubit and ii) a phase operation on the information qubit and a phase control qubit; performing, by a sender party, a sequence of one or more quantum logic gates on the phase control qubit; sending the information qubit, parity control qubit, and phase control qubit to a recipient party; and sending data identifying the sequence of one or more quantum logic gates to the recipient party, wherein the recipient party obtains the quantum information encoded into the information qubit using the information qubit, parity control qubit, phase control qubit, and data identifying the sequence of one or more quantum logic gates.

Quantum information interception prevention

A device may receive content data identifying content created by users and metadata associated with the content. The device may receive rules data identifying rules associated with utilization of the content. The device may utilize the metadata to generate digital DNA signatures for the content in near-real time. The device may store, in a repository, the rules data, the content, the digital DNA signatures, and relationships between the digital DNA signatures. The device may receive, from a client device, new content that is generated based on particular content of the content data and new metadata associated with the new content. The device may utilize the new metadata to generate a new digital DNA signature for the new content. The device may process the new digital DNA signature, the rules data, and the digital DNA signatures to determine whether the new content violates one or more rules of the rules data.

Utilizing machine learning to prevent intellectual property issues for content during different stages of a project lifecycle

Methods, systems and apparatus, including computer programs encoded on computer storage medium, for implementation of secret superposition protocols. In one aspect a method includes, performing, by a sender party, quantum operations on one or more qubits, comprising preparing, according to a predetermined secret superposition protocol, one or more qubits in respective uniform superposition quantum states; transmitting, by the sender party, to a recipient party, and through a secure channel, data indicating use of the predetermined secret superposition protocol; and transmitting, by the sender party and to the recipient party, one or more of the qubits, wherein the recipient party performs one or more measurements on the qubits to verify use of the predetermined secret superposition protocol.

A device may extract content, path data, and query data from API requests, and may identify events based on the extracted data. The device may combine a sequence of the events with the events to generate sequence-embedded events, and may train a neural network model with the sequence-embedded events to generate a trained neural network model. The device may receive an API request, may extract new content, new path data, and new query data from the API request, and may identify new events based on the newly extracted data. The device may process the new events, with the trained neural network model, to generate predicted events, and may calculate an anomaly score based on the predicted events. The device may compare the anomaly score with a threshold to determine a risk for the API request, and may cause the API request to be blocked or permitted based on the risk.

Utilizing a neural network model to determine risk associated with an application programming interface of a web application

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for service oriented software-defined security framework are disclosed. In one aspect, a system includes a security control device, one or more assets, and a security controller that communicates with the security control device and the one or more assets. The security controller includes a processing engine configured to register the security control device by creating a physical-logical attribute mapping for the security control device, and generating a security service description associated with the security control device. The processing engine is further configured to register the one or more assets by creating a physical-logical attribute mapping for each of the one or more assets, and generating security service requirements for each of the one or more assets. The processing engine is further configured to generate a security service binding based on a request for service.

Service oriented software-defined security framework

Examples of malware detection are provided. In an example, to detect malwares, a first subset of features may be determined from a binary file. The binary file may be analyzed based on machine learning model to determine a category of malware, which is based on a degree of detectability of the category. A first category may have a lower detectability of malware in the binary file and a second category may have a higher detectability than the first. A model may then be created to analyze the first category of malware and an analysis of the binary may be performed. The analysis may be performed using the model. Thereafter, a confidence score may be generated for the binary file. The confidence score may be indicative of certainty of determining whether the binary file is goodware or includes malware. Malware may be detected upon the confidence score exceeding a threshold value.

Malware detection

Growing community of inventors

Falls Church, VA, United States of America

Malek Ben Salem