Bitdefender Ipr Management Ltd.

Elena Burceanu

Emanuela Haller

Bogdan C Cebere

Madalina Bolboceanu

Georgiana M Rosca

Radu Titiu

Florin Brad

Dragos T Gavrilut

Vlad Bordianu

Razvan M Benchea

Vlad Valceanu

Traian Rebedea

Tiberius Axinte

Alexandru Novac

Andrei M Manolache

Stefan Smeu

Bogdan Cebere

A diverse collection of data samples harvested for computer security applications is divided into a plurality of training corpora according to criteria such as an identity of the data source, among others. An initial set of features for characterizing the collected data samples is reduced to an optimal subset. For each candidate feature, a frequency distribution of feature values is determined over each of the training corpora. A feature selection procedure favors features whose frequency distribution is relatively similar across multiple corpora. A detector module is then trained to detect computer security threats according to the reduced set of features.

Robust feature selection for computer security applications

Described systems and methods allow carrying out privacy-preserving DNS exchanges. In some embodiments, a client machine engages in a private information retrieval (PIR) exchange with a nameserver. In response to receiving an encrypted query from the client, the query formulated according to a domain name, the nameserver may extract a record (e.g., an IP address) from a domain name database without decrypting the respective query. Some embodiments achieve such information retrieval by the use of homomorphic encryption.

Privacy-preserving domain name services (DNS)

Some embodiments employ a novel procedure of training an artificial intelligence system (e.g., set of deep neural networks) for anomaly detection in applications such as natural language processing and computer security. Token sequences selected from a training corpus are distorted according to at least one of a plurality of pre-determined sequence transformations, before being fed to a sequence analyzer. In turn, the sequence analyzer is trained to correctly guess which transformation was used to generate the respective input token sequence.

Anomaly detection systems and methods

Some embodiments enable distributing data (e.g., recorded video, photographs, recorded audio, etc.) to a plurality of users in a manner which preserves the privacy of the respective users. Some embodiments leverage homomorphic encryption and proxy re-encryption techniques to manipulate the respective data so that selected portions of it are revealed according to an identity of the user currently accessing the respective data.

Privacy-preserving image distribution

Privacy-preserving domain name service (DNS)

Image distribution using composite re-encrypted images

Described systems and methods allow an automatic translation from a natural language (e.g., English) into an artificial language such as a structured query language (SQL). In some embodiments, a translator module includes an encoder component and a decoder component, both components comprising recurrent neural networks. Training the translator module comprises two stages. A first stage trains the translator module to produce artificial language (AL) output when presented with an AL input. For instance, the translator is first trained to reproduce an AL input. A second stage of training comprises training the translator to produce AL output when presented with a natural language (NL) input.

Systems and methods for translating natural language sentences into database queries

Described systems and methods allow a mobile device, such as a smartphone or a tablet computer, to protect a user of the respective device from fraud and/or loss of privacy. In some embodiments, the mobile device receives from a server a risk indicator indicative of whether executing a target application causes a privacy risk. Determining the risk indicator includes automatically supplying a test input to a data field used by the target application, the data field configured to hold a private item such as a password or a geolocation indicator. Determining the risk indicator further comprises determining whether a test device executing an instance of the target application transmits an indicator of the test input, such as the test input itself or a hash of the test input, to another party on the network.

Privacy protection for mobile devices

Growing community of inventors

Bucharest, Romania

Elena Burceanu