Shape Security, Inc.

Other

Bill Operations, LLC

Bei Zhang

Jarrod S Overson

Sergey Shekyan

Siying Yang

Ariya Hidayat

Ben Vinegar

Kenton Miller

Samir Shah

Justin David Call

Di Shi

Haifeng Li

Chunlei Xu

Michael J Ficarra

Carl Schroeder

Eitan Anzenberg

Ruisheng Diao

Siqi Wang

Desong Bian

Jiajun Duan

Haiwei Wu

Eli Mattson

Salman Saghafi

Lewis Ellis

Dalton Purnell

Corby Campbell

Darin Dooley

Amol Jayant Thatte

Jay Daniel Dunbar

Craig Jon Pickett

Derrick Jacob Hathaway

In an embodiment, a computer-implemented method for training a decision tree using a database system, the decision tree comprising a plurality nodes, comprises, by one or more computing devices: storing in a database input data for training the decision tree, the input data comprising a plurality of feature values corresponding to a plurality of features; generating a particular node of the plurality of decision nodes by: selecting a subset of the plurality of features and a subset of the input data; using one or more queries to the database system, for each feature of the subset of the plurality of features, calculating a variance value associated with the feature based on the subset of the input data; identifying a particular feature of the subset of the plurality of features associated with the highest variance value; associating the particular node with the particular feature, wherein the particular node causes the decision tree to branch based on the particular feature.

Decision tree training using a database system

Particular embodiments receive a plurality of values associated with a document. One or more keywords associated with the document are also received. A first score is generated for each value, of the plurality of values. The generation of the first score excluding sending, over a computer network, a first request to one or more remote computing devices to generate the first score. Based at least in part on the generating of the first score, each value, of the plurality of values is ranked. The ranking of each value excluding sending, over the computer network, a second request to the one or more remote computing devices to rank each value. Based on the ranking, at least one value, of the plurality of values, is selected. The selecting being indicative that the at least one value is a candidate to be a constituent of the one or more keywords. Based on the ranking, an indicator indicating that the at least one value is the candidate to be the constituent of the one or more keywords is presented.

Native automatic field extraction at a user device

In an embodiment, a computer-implemented method for training a decision tree using a database system, the decision tree comprising a plurality nodes, comprises, by one or more computing devices: storing in a database input data for training the decision tree, the input data comprising a plurality of feature values corresponding to a plurality of features; generating a particular node of the plurality of decision nodes by: selecting a subset of the plurality of features and a subset of the input data; using one or more queries to the database system, for each feature of the subset of the plurality of features, calculating an information gain associated with the feature based on the subset of the input data; identifying a particular feature of the subset of the plurality of features associated with the highest information gain; associating the particular node with the particular feature, wherein the particular node causes the decision tree to branch based on the particular feature.

Systems and methods are disclosed for control voltage profiles, line flows and transmission losses of a power grid by forming an autonomous multi-objective control model with one or more neural networks as a Deep Reinforcement Learning (DRL) agent; training the DRL agent to provide data-driven, real-time and autonomous grid control strategies; and coordinating and optimizing power controllers to regulate voltage profiles, line flows and transmission losses in the power grid with a Markov decision process (MDP) operating with reinforcement learning to control problems in dynamic and stochastic environments.

Multi-objective real-time power flow control method using soft actor-critic

Techniques are provided for proof-of-work based on runtime compilation. Key generation code is partitioned into a set of code blocks. The key generation code generates an expected key value when compiled and executed. A shuffled set of code blocks is generated by reordering the set of code blocks. A client computing device is provided the shuffled set of code blocks and problem-solving code that, when executed at the client computing device, reconstructs the key generation code to generate a submission value by performing one or more compiling iterations. Each compiling iteration comprising reordering the shuffled set of code blocks to generate test code, and attempting to compile and execute the test code to generate the submission value. It is determined that the client computing device fully executed the problem-solving code based on the verifying the submission value.

Proof-of-work based on runtime compilation

In an embodiment, a computer system is configured to improve security of server computers interacting with client computers through an intermediary computer, and comprising: a memory comprising processor logic; one or more processors coupled to the memory, wherein the one or more processors execute the processor logic, which causes the one or more processors to: intercept, from a server computer, one or more original instructions to be sent to a browser being executed on a client computer; inject, into the one or more original instructions, one or more browser detection instructions, which when executed cause one or more operations to be performed by an execution environment on the client computer and send a result that represents an internal state of the execution environment after performing the one or more operations to the intermediary computer; send the one or more original instructions with the one or more browser detection instructions to the browser; receive the result and determine whether the browser is a legitimate browser, or a headless browser, based, at least in part, on the result.

Systems for detecting a headless browser executing on a client computer

In an approach, an apparatus comprises: one or more processors; a processor logic coupled to the one or more processors and configured to: intercept, from a client computer, a request directed to a server computer that identifies a purported user agent executing on the client computer; send, to the server computer, the request from the client computer; intercept, from the server computer, one or more original instructions to be executed by the purported user agent of the client computer; determine one or more features supported by the purported user agent that are not utilized by the one or more original instructions; transform the one or more original instructions into one or more revised instructions which, when executed by the purported user agent, cause the purported user agent to utilize the one or more features; send, to the client computer, the one or more revised instructions.

Variable runtime transpilation

This document generally relates to systems, method, and other techniques for identifying and interfering with the operation of computer malware, as a mechanism for improving system security. Some implementations include a computer-implemented method by which a computer security server system performs actions including receiving a request for content directed to a particular content server system; forwarding the request to the particular content server system; receiving executable code from the particular content server system; inserting executable injection code into at least one file of the executable code; applying a security countermeasure to the combined executable code and executable injection code to create transformed code; and providing the transformed code to a client computing device.

Polymorphic obfuscation of executable code

A computer system configured to improve security of server computers interacting with client computers, the system comprising: one or more processors executing instructions that cause the one or more processors to: select, from the plurality of detection tests, one or more first detection tests to be performed by a client computer; send, to the client computer, a first set of detection instructions that define the one or more first detection tests, and which when executed causes generating a first set of results that identifies a first set of characteristics of the client computer; receive the first set of results from the client computer; select one or more first countermeasures from a plurality of countermeasures based on the first set of characteristics identified in the first set of results; send, to the client computer, a first set of countermeasure instructions that define the one or more first countermeasures.

Reverse proxy computer: deploying countermeasures in response to detecting an autonomous browser executing on a client computer

The automated, real-time detection of specific blocks of code within a larger body of source code is described. Specific implementations relate to the detection of known code libraries in web page code to improve the efficiency of the generation of polymorphic transformations of the web page code for the purpose of impeding automated cyber-attacks.

Automatic library detection

Growing community of inventors

Mountain View, CA, United States of America

Bei Zhang