Mobile fraud detection platform powered by threat intelligence and behavioral AI
ThreatFabric detects mobile fraud and malware threats using Python, Java, Kafka, and ML frameworks (TensorFlow, PyTorch, scikit-learn) paired with Android/iOS SDKs. The tech stack reveals a dual focus: streaming data processing (Kafka, PySpark, Pandas) for high-volume threat detection, and mobile client instrumentation (Android, Kotlin, Swift, JNI, C++) for on-device behavior analysis. Active projects on behavior biometrics AI and detection algorithm enhancement signal a shift toward predictive fraud prevention over reactive rule-based systems.
ThreatFabric detects fraud and malware threats across mobile channels by combining threat research with behavioral AI. The company serves financial institutions and digital services providers globally, protecting customer accounts and devices from account takeover, credential theft, and malicious applications. The platform ingests high volumes of mobile telemetry and threat signals through Kafka, processes them with Python/PySpark, and runs inference on TensorFlow and PyTorch models to identify fraudulent patterns in real time. Recent focus areas include architectural modernization, CI/CD pipeline improvements, and expanding behavior-based detection capabilities.
Primary languages are Python, Java, Kotlin, and Swift. Python powers backend processing (PySpark, pandas, scikit-learn, TensorFlow, PyTorch); Java and Kotlin run Spring Boot services and Android SDK development; Swift handles iOS instrumentation.
Active projects include next-generation behavior biometrics AI, mobile Android SDK development, improving fraud detection algorithms, CI/CD pipeline modernization, and integrations with new customers. Recent focus areas are architectural transitions and modern QA practices.
Other companies in the same industry, closest in size