Salt Security: Detecting Threats, Anomalies & Vulnerabilities in API Traffic with AI

With its accelerated growth, Salt Security expanded its Data Science team, leading to the generation of advanced ML models. However, transitioning these models to production presented multiple challenges:

• The AWS SageMaker framework demanded consistent involvement from the Infrastructure team for each new model deployment.
• Preliminary PoC experimentation often necessitated the expertise of a seasoned engineer.
• The data science teams, skilled in their field, lacked the engineering experience crucial for deployment.
• Integrating with Kafka's event-based architecture was intricate, especially when endpoints needed to manage and output prediction streams.

‍

Uniformity via Model Deployment: Introduced a standard code structure for all models, enabling Salt to systematically deploy them to production.

Clarity with Qwak's Interface: Through its streamlined terminology and interface, Qwak simplified the complexities of the ML infrastructure. The addition of a robust API ensured easy access to all functionalities.

Real-time Assessment with Model Monitoring: These tools, combined with feedback loops, allowed Salt's teams to promptly evaluate model behavior after deployment.

Integration Efficiency with Model Serving: Facilitated the deployment of model endpoints integrated with Kafka. This allowed Salt's personnel to deploy new model versions as endpoints adept at handling prediction streams.

The partnership with Qwak enhanced Salt Security's deployment efficiency, addressing key challenges and streamlining processes.