Cylance Inc.

Hiddenlayer, Inc.

Andrew Davis

Matthew Wolff

Derek A Soeder

Ryan Permeh

Michael Thomas Wojnowicz

Xuan Zhao

John Brock

David Neill Beveridge

Brian Michael Wallace

Jian Luan

Glenn Chisholm

Mahdi Azarafrooz

Andy Wortman

Yaroslav Oliinyk

Julian Collado Umana

Eric G Petersen

Ming Jin

David Beveridge

Aditya Kapoor

Homer Valentine Strong

Gabriel Acevedo

Kevin Beets

Amelia Kawasaki

Matthew Maisel

Dinh Huu Nguyen

Andrew Wortman

Brian Wallace

A first password is received by a password encoder which uses the first password to generate a first key. This first key is used to modify weights and biases of an encoder to result in a modified encoder. Further, weights and biases of a decoder operating in tandem with the encoder based can be modified based on a second key to result in a modified decoder. First data is received which encapsulates second data in a hidden compartment. The first data is encoded by the modified encoder to result to generate an embedding. The modified decoder decodes the embedding to result in a representation of the second data which, in turn, can be provided to a consuming application or process. The first data can be input into the encoder and the decoder prior to those components being modified to result in a representation of the first data.

Machine learning model parameter based encryption

An encoder receives first data encapsulating second data in a hidden compartment along with a decoder identifier corresponding to either of a first decoder or a second decoder. The encoder then generates an embedding corresponding to the first data. The first decoder decodes the embedding to result in a representation of the first data when the decoder identifier corresponds to the first decoder. The second decoder decodes the embedding to result in a representation of the second data when the decoder identifier corresponds to the second decoder. The decoded embedding can be provided to a consuming application or process. Related apparatus, systems, techniques and articles are also described.

Data obfuscation using encoder-multi-decoder architecture

First data is received which encapsulates second data in a hidden compartment. Thereafter, a password is received by a password encoder which uses such password to generate a key. The first data and the key are combined to generate the second data (i.e., the hidden data). The second data is then provided to a consuming application or process. Related apparatus, systems, techniques and articles are also described.

Hidden compartments in data encrypted using machine learning

Data is received that characterizes artefacts associated with each of a plurality of layers of a first machine learning model. Fingerprints are then generated for each of the artefacts in the layers of the first machine learning model. These generated fingerprints collectively form a model indicator for the first machine learning model. It is then determined whether the first machine learning model is derived from another machine learning model by performing a similarity analysis between the model indicator for the first machine learning model and model indicators generated for each of a plurality of reference machine learning models each comprising a respective set of fingerprints. Data characterizing the determination can be provided to a consuming application or process. Related apparatus, systems, techniques and articles are also described.

Machine learning model fingerprinting

An analysis engine receives data characterizing a prompt for ingestion by a generative artificial intelligence (GenAI) model. An intermediate result of the GenAI model or a proxy of the GenAI model responsive to the prompt is obtained. The analysis engine, using a prompt injection classifier and the intermediate result, determines whether the prompt comprises or is indicative of malicious content or elicits malicious actions. Data characterizing the determination is provided to a consuming application or process. Related apparatus, systems, techniques and articles are also described.

Prompt injection classifier using intermediate results

In one respect, there is provided a system for training a neural network adapted for classifying one or more scripts. The system may include at least one processor and at least one memory. The memory may include program code which when executed by the at least one memory provides operations including: receiving a disassembled binary file that includes a plurality of instructions; processing the disassembled binary file with a convolutional neural network configured to detect a presence of one or more sequences of instructions amongst the plurality of instructions and determine a classification for the disassembled binary file based at least in part on the presence of the one or more sequences of instructions; and providing, as an output, the classification of the disassembled binary file. Related computer-implemented methods are also disclosed.

Malware detection

A system is provided for classifying an instruction sequence with a machine learning model. The system may include at least one processor and at least one memory. The memory may include program code that provides operations when executed by the at least one processor. The operations may include: processing an instruction sequence with a trained machine learning model configured to detect one or more interdependencies amongst a plurality of tokens in the instruction sequence and determine a classification for the instruction sequence based on the one or more interdependencies amongst the plurality of tokens; and providing, as an output, the classification of the instruction sequence. Related methods and articles of manufacture, including computer program products, are also provided.

Machine learning model for analysis of instruction sequences

Data is received that characterizes artefacts associated with each of a plurality of layers of a first machine learning model. Fingerprints are generated corresponding to each of the artefacts in each layer. The generated fingerprints can collectively form a model indicator for the first machine learning model. A second machine learning model then determines, based on the generated fingerprints, whether the first machine learning model is derived from another machine learning model. Data provided this characterization can be provided to a consuming application or process. This second machine learning model can be trained model with historical fingerprints having a known provenance classification. Related apparatus, systems, techniques and articles are also described.

Machine learning-based technique for model provenance

In some implementations there may be provided a system. The system may include a processor and a memory. The memory may include program code which causes operations when executed by the processor. The operations may include analyzing a series of events contained in received data. The series of events may include events that occur during the execution of a data object. The series of events may be analyzed to at least extract, from the series of events, subsequences of events. A machine learning model may determine a classification for the received data. The machine learning model may classify the received data based at least on whether the subsequences of events are malicious. The classification indicative of whether the received data is malicious may be provided. Related methods and articles of manufacture, including computer program products, are also disclosed.

Machine learning model for malware dynamic analysis

Presence of malicious code can be identified in one or more data samples. A feature set extracted from a sample is vectorized to generate a sparse vector. A reduced dimension vector representing the sparse vector can be generated. A binary representation vector of reduced dimension vector can be created by converting each value of a plurality of values in the reduced dimension vector to a binary representation. The binary representation vector can be added as a new element in a dictionary structure if the binary representation is not equal to an existing element in the dictionary structure. A training set for use in training a machine learning model can be created to include one vector whose binary representation corresponds to each of a plurality of elements in the dictionary structure.

Dictionary based deduplication of training set samples for machine learning based computer threat analysis

A system is provided for training a machine learning model to detect malicious container files. The system may include at least one processor and at least one memory. The memory may include program code which when executed by the at least one processor provides operations including: processing a container file with a trained machine learning model, wherein the trained machine learning is trained to determine a classification for the container file indicative of whether the container file includes at least one file rendering the container file malicious; and providing, as an output by the trained machine learning model, an indication of whether the container file includes the at least one file rendering the container file malicious. Related methods and articles of manufacture, including computer program products, are also disclosed.

Container file analysis using machine learning model

Data is analyzed using feature hashing to detect malware. A plurality of features in a feature set is hashed. The feature set is generated from a sample. The sample includes at least a portion of a file. Based on the hashing, one or more hashed features are indexed to generate an index vector. Each hashed feature corresponds to an index in the index vector. Using the index vector, a training dataset is generated. Using the training dataset, a machine learning model for identifying at least one file having a malicious code is trained.

Growing community of inventors

Portland, OR, United States of America

Andrew Davis