New MLSecOps community provides a collaborative space for experts and industry leaders to connect and shape the future of security in AI applications and ML systems.
Protect AI is proud to announce the launch of its MLSecOps community, an online gathering place dedicated to advancing the field of Machine Learning Security Operations (MLSecOps), and is unveiling MLSecOps.com; a new digital collective featuring original weekly podcasts, learning resources, hybrid events, and a Slack community. By engaging visionary thought leaders and subject matter experts in categories such as ML Supply Chain Vulnerability, Model Provenance, GRC, Trusted AI (Bias, Fairness, and Explainability), and Adversarial ML, members and visitors will find a range of interesting and engaging topics to improve their awareness of MLSecOps.
“Protect AI is dedicated to building a safer AI-powered world. This will take a broad community effort, and we see a need for a gathering place where ML engineers, data scientists, and security experts can connect to collaborate and develop new ways that advance security of AI applications and ML systems,” said Daryan “D” Dehghanpisheh, Co-Founder and President of Protect AI. “MLSecOps.com is an exciting milestone that advances the emerging field of MLSecOps, which is more critical by the day with the rapid implementation of large language models (LLM) like GPT, other foundational models, and the stunning popularity of Generative AI applications. We are excited to be leading this movement to MLSecOps.”
The MLSecOps community facilitates discussions on the challenges and opportunities that arise when integrating security into machine learning processes. The community helps to serve as the broadest platform for sharing best practices, identifying emerging threats, and discussing innovative solutions to unique MLSecOps challenges
“Machine learning is a new technology domain, and it has unique threats. Adversarial Machine Learning is a rapidly advancing set of attack methods that calls for a new approach to defences. A community where people can gather to easily discuss and understand the practical implications and applications of this is needed. MLSecOps.com offers a new way for researchers and security professionals to collaborate,” says Florian Tramèr, Assistant Professor of Computer Science at ETH Zürich.
“Beyond unique challenges, modifying existing security practices and procedures are needed to better secure ML systems,” says former Vice President of AWS Security Services and advisor to Protect AI, Dan Plastina. “ML systems are a new technology domain, and new threats will arise. Understanding how to detect, remediate, and further prevent these breaches is now critical. MLSecOps.com will help customers better plan and adapt their current practices and technologies to the rapidly growing mix of AI applications.”
As AI cyber threats continue to evolve and become more sophisticated, it’s clear that traditional approaches to security are no longer sufficient. To keep pace with this rapidly changing landscape, organisations need to adopt a more collaborative approach to security, one that brings together the best and brightest minds in the field. That’s why the creation of an MLSecOps community is so important. By working together and sharing knowledge, system builders and managers can stay ahead of attacks, bad actors and better protect everyone from new forms of digital harm. A leader in working to advance the security of ML systems and practices in MLSecOps is MITRE, a non-profit organisation supporting US government cybersecurity.
“MITRE is leading several efforts in the U.S. and internationally to reinforce the importance of AI Security and Assurance and provide tools like MITRE ATLAS to help organisations combat adversarial threats to their machine learning-enabled platforms,” said Dr Christina Liaghati, AI Strategy Execution & Operations Manager at MITRE. “We look forward to discussing opportunities for collaborative action, developing tools and capabilities, with others in the industry through the new MLSecOps community as the threat and vulnerability landscape continues to evolve.”
