Protect AI

Thanks to all who joined us for the MLSecOps Meetup last week in San Francisco during RSA Conference! We had a fantastic time connecting with community members and the team from Protect AI and huntr. Find resources and replays of past community events here ➡️ https://hubs.ly/Q02xs4nS0 - and - join us for AI security conversations in Slack! ➡️ https://hubs.ly/Q02xs0ss0 #MLSecOps #meetup #aisecurity #MLSec #airisk #machinelearning #ai #llm #genai #cybersecurity #protectai Ken Huang, CISSP Chris Ancharski

🎧S2 Ep11: Practical Foundations for Securing AI In the newest episode of the MLSecOps Podcast, we delve further into the realm of practical security for AI and machine learning with our guest Ron F. Del Rosario, Chief Security Architect and AI/ML Security Lead at SAP ISBN. Ron is also a contributor to the OWASP Top 10 For Large Language Model Applications and Cloud Security Alliance research. The discussion highlights the contextual knowledge gap between ML practitioners and cybersecurity professionals, emphasizing the importance of cross-collaboration and foundational security practices. We explore the contrasts of security for AI to that for traditional software, along with the risk profiles of first-party vs. third-party ML models. Ron sheds light on the significance of understanding your AI system's provenance, having necessary controls, and audit trails for robust security. He also discusses the "Secure AI/ML Development Framework" initiative that he launched internally within his organization, featuring a lean security checklist to streamline processes. Listen, watch, or read the transcript here: https://hubs.ly/Q02x59V60 Thanks for joining us, Ron; we had a fantastic time talking with you! #MLSecOps #aisecurity #MLSec #airisk #machinelearning #ai #llm #genai #cybersecurity #protectai

Up next on the MLSecOps Podcast, we are proud to share insights from Ron F. Del Rosario, Chief Product Security Architect & AI/ML Security Lead at SAP ISBN. Ron is also a contributor to the OWASP Top 10 For Large Language Model Applications and Cloud Security Alliance Research. Here's a preview of the episode for you to enjoy. Be notified when the full episode drops by subscribing here ➡️ https://bit.ly/3wiXKgJ #MLSecOps #aisecurity #MLSec #airisk #machinelearning #ai #llm #genai #cybersecurity #protectai

We are honored to receive the Global InfoSec award from Cyber Defense Magazine for "Cutting Edge Machine Learning Security Operations (MLSecOps) Solution" at RSA Conference 2024. Join us at booth #1655 to learn more about how we can help you protect your AI! Learn more at https://bit.ly/4dyhI7G #RSAC #MLSecOps #AISecurity

Day 2 of RSAC 2024! Join us for hands on demos and fireside chats at our booth #1655. We have a great line up today!! ✅ 11 AM: Building your MLSecOps dream team by Diana Kelley Protect AICISO, with special guest Dr. Char Sample ✅1 2.30 PM: Building a (Real) AI/ML Red Team by Dan McInerney, Threat Researcher, Protect AI Marcello Salvati, Threat Researcher, Protect AI ✅ 1 PM: OKRs for MLSecOps by Daryan (D) Dehghanpisheh, President and Founder Protect AI with special guest Omar Khawaja, VP Security, Databricks ✅ 2 PM: In the Wild - Managing AI Security by Daryan (D) Dehghanpisheh, President and Founder Protect AI with special guest DJ Fuller, CEO, Pathfynder ✅ 3 PM: LLM Security 101 by Neal Swaelens, EMEA BD Director, Protect AI with Rachit Sood Core Team Member of OWASP® FoundationTop 10 for LLMs, and Ken Huang ✅ 4 PM: Risk Management: Meeting Federal AI Regulations by Daryan (D) Dehghanpisheh, President and Founder Protect AI #AISecurity #RSAC #MLSecOps

Introducing Sightline🚀 The first AI/ML Vulnerability Database that provides deep insights into both emerging and known vulnerabilities of AI and ML. Sightline is an industry leading early warning system to defend against threats an average of 30 days before they are publicly disclosed, Sightline also equips your teams with the ability to quickly detect, assess and remediate their network for associated AI risks. Stay ahead of AI adversaries with Sightline: ✅ Early access to fixed AI vulnerabilities before they are publicly disclosed ✅ User-friendly Web and API access to manage risks ✅ Proactive security research fortified by huntr community to secure your supply chain ✅ Nuclei templates to streamline your scanning process ✅ Security advisories with detailed descriptions & infographics, automated vulnerability scanners, and OSS maintainer provided fixes and remediation advice to understand threats. ✅ Seamless integration with Protect AI tools. Learn more Protect AI | Sightline https://bit.ly/4bmMDlC #huntr #aisecurity #MLSecOps #AIvulnerabilities

Online reservations for the upcoming MLSecOps Meetup have closed due to overwhelming demand, BUT you can still register to attend in person by visiting Protect AI's booth (#1655) at RSA Conference starting Monday, May 6, 2024. Stop by the booth to get a free ticket to the meetup and learn more about tools for #MLSecOps. In the meantime, check out our community site for educational resources at https://bit.ly/3QuaiJ0. See you there! 👋

The latest episode of Between Two Vulns is now live! Check out the summary of our April report, which unveiled the largest number of AI/ML Vulnerabilities to date, discovered by our thriving huntr community. See the full episode below, and contact us to learn more about how we can help you secure your AI from these threats. https://bit.ly/3QqtqHE #huntr #AISecurity #MLSecOps #AI

📣 New episode alert! 📣 MLSecOps Podcast S2Ep10 🎧 "Evaluating RAG and the Future of LLM Security: Insights with LlamaIndex" Hosts Neal Swaelens and Oleksandr Yaremchuk sit down with special guest Simon Suo, co-founder and CTO of LlamaIndex. The group discusses many topics, including: - Challenges and considerations of integrating LLMs into various applications, emphasizing the importance of contextualizing LLMs within specific environments. - The evolution of retrieval-augmented generation (RAG) techniques and the future trajectory of LLM-based applications, including the significance of balancing performance with cost and latency in leveraging LLM capabilities. - LLM security concerns and the critical need for robust input and output evaluation to mitigate potential risks. - The potential vulnerabilities associated with LLMs, including prompt injection attacks and data leakage, underscoring the importance of implementing strong access controls and data privacy measures. - Efforts within the community to address security challenges and foster a culture of education and awareness. Listen or read the transcript here to learn more about the ongoing innovation in large language model-based applications, while remaining vigilant about LLM security considerations ➡️ https://hubs.ly/Q02v63y60 Thanks again for joining us, Simon! #MLSecOps #aisecurity #MLSec #airisk #machinelearning #ai #llm #genai #llamaindex #protectai #cybersecurity #rag

Here's a preview from the upcoming MLSecOps Podcast episode with esteemed guest Simon Suo, Co-Founder and CTO at LlamaIndex. We were eager to hear Simon's thoughts on the growing adoption of Retrieval-Augmented Generation (RAG) in #LLM application development, along with perspectives on security concerns within the industry and many other valuable insights. The new episode will air this week! You can subscribe to the show here if you'd like to receive an email notification as soon as it drops: https://hubs.ly/Q02t-2Cq0 A heartfelt thank you to Simon for joining us, to our show hosts Neal Swaelens and Oleksandr Yaremchuk, and (as always) to our podcast audience for their enthusiasm & support. #MLSecOps #aisecurity #MLSec #airisk #machinelearning #ai #llm #genai #llamaindex #protectai #cybersecurity #rag