Hiddenlayer Develops A Threat Intelligence Squad To Tackle ML Attacks

The Synaptic Adversarial Intelligence (SAI) team at HiddenLayer will investigate and reveal the ML/AI threat environment.

Fremont, CA: A threat intelligence analyst (TIA) investigates and discovers cyber dangers and viruses that affect businesses. They examine the severity of an attack and, as a result, help firms make educated cyber security-based business decisions. These specialists are aware of the cybersecurity dangers that affect various industrial verticals and assist in securing vital assets that require protection. Analysts of threat intelligence select threats and concentrate on the most serious ones.

"Alongside our commitment to increasing awareness of ML security, we will also actively assist in the development of countermeasures to thwart ML adversaries through the monitoring of deployed models, as well as providing mechanisms to allow defenders to respond to attacks," said Tom Bonner, Senior Director of Adversarial Machine Learning Research at HiddenLayer. "There has been a tremendous effort from several organizations, such as MITRE and NIST, to better understand and quantify the risks associated with ML/AI. We look forward to working alongside these industry leaders to broaden the pool of knowledge, define threat models, drive policy and regulation, and most critically, prevent attacks."

HiddenLayer, the creator of a one-of-a-kind security platform that protects the machine learning models that enterprise organizations use behind their most critical products, has formed Synaptic Adversarial Intelligence (SAI) team to raise awareness about the threats to machine learning (ML) and artificial intelligence (AI) systems.

The major objective of the SAI is to educate data scientists, MLDevOps teams, and cyber security experts on how to analyze the vulnerabilities and hazards connected with ML/AI in order to develop more secure implementations and deployments. The SAI team's findings help execute risk assessments and create intelligence reports that disclose the hostile ML threat environment. The interdisciplinary cyber security specialists and data scientists have decades of cyber security expertise and extensive backgrounds in malware detection, threat intelligence, reverse engineering, incident response, digital forensics, and adversarial machine learning.

Until recently, most adversarial ML/AI research concentrated on the mathematical component, intending to make algorithms more resistant in the face of malicious input. Now, security researchers are delving deeper into ML algorithms or how models are created, updated, packaged, and delivered, looking for flaws and vulnerabilities throughout the software ecosystem. They discovered many novel attack strategies and, as a result, gained a better grasp of how actual assaults gets carried out against real-world ML systems.