The MIT startup, PatternEX, has developed an AI-human collaboration solution for security analysts to find security threats in their system in a matter of seconds.
‘The company has developed a closed loop approach whereby machine-learning models flag possible attacks and human experts provide feedback. The feedback is then incorporated into the models, improving their ability to flag only the activity analysts care about in the future.’ – MIT News Office
According to the startup’s website, PatternEx Virtual Analyst Platform enables the adoption of AI workflows:
- Generate alerts with AI detection models and embed the findings in analyst workflows
- Customize the deployment strategy to prioritize the best performing models
- Learn from alert resolutions to improve detection rates
- Assess model performance by comparing model findings and alert resolutions
Most AI startups use anomaly detection to find security threats, however, such a detection system ceases to work when the model cannot learn what ‘normal’ is in a chaotic situation. As PatternEX is providing human-machine collaboration, they have a higher chance of finding correct threats soon.
Isn’t this great news for the cybersecurity community? What do you think?