Barracuda Networks, Inc.

Sookasa Inc.

Asaf Cidon

Lior Gavish

Israel Cidon

Marco Schweighauser

Prabandham Madan Gopal

Shetty Chandrashekhar

Barak Srour

Chandrashekhar Shetty

Mohamed Hosam Afifi Ibrahim

Itay Bleier

Gopal Madan Prabandham

A new approach is proposed to support account takeover (ATO) detection based on login attempts by users. The approach relies on assessing fraudulence confidence level of login IP addresses to classify the login attempts by the users. A plurality of attributes/features in one or more user login data logs are extracted and used to build a labeled dataset for training a machine learning (ML) model that relies on statistics of the login attempts to classify and detect fraudulent logins. These attributes make it possible to ascertain if a login attempt or instance by a user is suspicious based on the ML model. In some embodiments, the ML model is trained using anonymized user login data to preserve privacy of the users and a proper level of data anonymization is determined based on the ML model's accuracy in detecting the ATO attacks when trained with different versions of the anonymized data.

System and method for email account takeover detection and remediation utilizing anonymized datasets

System and method for email account takeover detection and remediation utilizing AI models

A new approach is proposed that contemplates systems and methods to support email account takeover detection and remediation by utilizing an artificial intelligence (AI) engine/classifier that detects and remediates such attacks in real time. The AI engine is configured to continuously monitor and identify communication patterns of a user on an electronic messaging system of an entity via application programming interface (API) calls. The AI engine is then configured to collect and utilize a variety of features and/or signals from an email sent from an internal email account of the entity. The AI engine combines these signals to automatically detect whether the email account has been compromised by an external attacker and alert the individual user of the account and/or a system administrator accordingly in real time. The AI engine further enables the parties to remediate the effects of the compromised email account by performing one or more remediating actions.

System and method for email account takeover detection and remediation

An approach is proposed that contemplates systems, methods, and computer-readable storage mediums to support receiving, from a computerized system, a first encrypted file entity key and signed access metadata, wherein the first encrypted file entity key is created by encrypting a file entity key using a first encryption key, the signed access metadata is signed by the file entity key and the encrypted file entity is created by encrypting a file entity using the file entity key. The approach then determines whether to facilitate the decryption of the encrypted file entity by the computerized system and sends a second encrypted file entity key to the computerized system if it is determined to facilitate the decryption. The approach prevents the computerized system to decrypt the encrypted file entity if it is determined not to facilitate the decryption of the encrypted file entity by the computerized system.

Distributed encryption and access control scheme in a cloud environment

Non-transitory computer readable medium that may store instructions that once executed by a computer may cause a computer to receive or generate multiple security questions, receive multiple security answers that were provided by an entity in response to the multiple security questions, receive or generate redundant information and calculate the passphrase by applying an error correction process on the redundant information and the multiple security answers; wherein the error correction process is configured to correct up to a predefined number of erroneous security answers.

Robust restoration of passphrases from partial information

System, computer readable medium and method for decryption. The method may include receiving, by a third computerized system and from a fourth computerized system, a first encrypted file entity key and signed access metadata. The first encrypted file entity key is created by encrypting a file entity key by a first computerized system using an encryption key of a second computerized system. The signed access metadata is signed by the file entity key. The encrypted file entity is created by encrypting a file entity by the first computerized system using the file entity key. Sending, by the third computerized system, the signed access metadata and the first encrypted file entity key to the second computerized system. Receiving a response from the second computerized system. Determining, based on the response from the second computerized system, whether to facilitate a decryption of the encrypted file entity by the fourth computerized entity.

A system, computer readable medium and a method for encrypting a file, the method may include retrieving the file from a storage service; segmenting the file into multiple file segments; calculating a file segment signature for each of the multiple file segments to provide multiple file segment signatures; encrypting each of the multiple file segments to provide multiple encrypted file segments by using encryption keys that are in response to the multiple file segment signatures; wherein the multiple encrypted file segments form an encrypted file; and sending the multiple encrypted file segments to the storage service.

Encrypting files within a cloud computing environment

A method for file management, the method may include: calculating, by a management server that is located within a cloud computing environment, signatures of multiple files that are stored at multiple storage entities; and finding, by the management server, groups of similar files out of the multiple files, wherein the finding is in response to similarities between signatures of the multiple files; wherein the multiple storage entities comprise at least a first storage entity that is managed by a first management entity and a second storage entity that is managed by a second management entity that differs from the first management entity.

System, method and computer readable medium for file management

A method for managing a virtual distributed file system includes maintaining by a master device located in a cloud computing environment, a metadata data structure that stores metadata about locations of most updated versions of multiple file portions and security levels of the file portions, at least one file portion being stored at a user device coupled to the cloud computing environment, and maintaining by the master device, transaction of file portions to user entities, at least one user entity being hosted by the user device, based on at least metadata stored in the metadata data structure about the file portions.

Growing community of inventors

San Francisco, CA, United States of America

Asaf Cidon