Explore how prompt engineering and prompt hacking are reshaping AI security, with insights on safeguarding generative AI in this MLSecOps Podcast episode.

Generative AI Prompt Hacking and Its Impact on AI Security & Safety

This compilation contains highlights from every episode of Season 2 of the MLSecOps Podcast. Thanks to everyone who has supported this show, including our listeners, hosts, and stellar expert guests!

The MLSecOps Podcast Season 2 Finale

This free course equips organizations with the essential knowledge and practical strategies needed to seamlessly integrate AI Security into their processes. 

MLSecOps Foundations Certification Course

Welcome to "MLSecOps Connect: Ask the Experts," an educational live stream series from the MLSecOps Community where attendees have the opportunity to hear their own questions answered by a variety of insightful guest speakers. 

This is a recording of the session we held on August 28, 2024 with the Chief Architect at Protect AI, Sean Morgan. 
In prior roles, Sean led production AI/ML deployments in the semiconductor industry, evaluated adversarial machine learning defenses for DARPA research programs, and most recently scaled customers on interactive machine learning solutions at Amazon Web Services (AWS). In his free time, Sean is an active open-source contributor and maintainer, and is the special interest group lead for TensorFlow Addons.

During this MLSecOps Connect session, Sean fielded questions from the community related to security for AI & machine learning (ML), including the importance of ML model scanning and how to get started with scanning models.

Explore with us:
1. What are some solutions for model scanning?
2. How can enterprises protect their AI models from insider threat? 
3. Which three design principles are the most important for secure AI infrastructures?
4. What are some of the security threats we can't use automated scans for?
5. Which resources does Sean use and recommend to advance personal knowledge in the context of AI security? 
6. How can someone design a zero trust approach for the current large language model (LLM) architectures?
7. What are some recommendations for aligning best [AI security] practices and standards in a palatable, won't-slow-down-the-business way?
8. Does Protect AI provide both Red Teaming and Guardrails for LLMs?
9. What types of attacks does Protect AI's model scanning tool cover? Are the attacks domain specific (e.g., attacks on text vs image) or generic? Once the model vulnerabilities are detected, what defenses are available?
10. How can we follow a shift left approach for model security?
And more!

ML Model Security - Is Your AI Protected?

Welcome to "MLSecOps Connect: Ask the Experts," an educational live stream series from the MLSecOps Community where attendees have the opportunity to hear their own questions answered by a variety of insightful guest speakers. (Learn more about AI Security and MLSecOps <a href="https://mlsecops.com/" rel="noopener noreferrer" target="_blank">here</a>.)We're honored to host expert guest Ken Huang on September 11, 2024! Ken will field questions from the community related to security best practices for <a href="https://www.techtarget.com/searchenterpriseai/definition/generative-AI" rel="noopener noreferrer" target="_blank">Generative AI</a>, including questions related to themes from his book, "<a href="https://www.amazon.com/Generative-AI-Security-Theories-Practices/dp/3031542517" rel="noopener noreferrer" target="_blank">Generative AI Security: Theories and Practices (Future of Business and Finance)</a>."Learn more about Ken in his bio below.Ways to submit your questions for the session:<ol><li data-list="ordered">Use the field provided in the registration form for this event to submit your questions about the specified topics for the session. Questions will be collected, then read aloud and answered during the event.</li><li data-list="ordered">If you think of additional questions after submitting the registration form, <a href="https://community.mlsecops.com/home/messages" rel="noopener noreferrer" target="_blank">send them in a DM</a> to the MLSecOps Community Manager, Charlie McCarthy.</li><li data-list="ordered">Finally, you can also submit questions in realtime during the event via the live chat, and we'll address as many questions as we can before the end of the session.</li></ol>We look forward to seeing you there!Stay involved with the MLSecOps Community in the meantime by checking out the additional resources <a href="https://mlsecops.com/join" rel="noopener noreferrer" target="_blank">here in our learning hub</a> and by joining us in <a href="https://mlsecops.com/slack" rel="noopener noreferrer" target="_blank">Slack</a> :)

Generative AI Security (Replay available soon)

Join the MLSecOps Community for an evening of networking, delicious food and drink, and learning from today's top AI Security experts!Enjoy an illuminating presentation by Will Armiros and Sam Washko (Senior Software Engineers, <a href="https://protectai.com/" rel="noopener noreferrer" target="_blank">Protect AI</a>) about AI supply chain vulnerabilities, defenses, and why it is critical to ensure machine learning (ML) model and data integrity.Hang out with us after the presentation to mingle with fellow AI security-minded professionals and community members!***Event registration is required to attend. Ages 21+ only. Government issued ID will be required to enter the venue. FAQ:<ol><li data-list="bullet">What should I do when I arrive for the event?</li><li data-list="bullet" class="ql-indent-2">Upon arrival, please check in using your government-issued photo ID at the entrance of Civility &amp; Unrest; which is located on Floor 1 of Lincoln Square South, near the valet drop-off for W Hotel. When you see a colorful wall mural of a hand holding a camera-phone, you're in the right place (see photo below showing that part of the mural). Signage for the MLSecOps Meetup will also be posted at the entrance.</li><li data-list="bullet">What are the transportation and parking options?</li><li data-list="bullet" class="ql-indent-2">Bellevue has a wide variety of options available, including direct bus routes between Seattle &amp; Bellevue, and the 2 Line Light Rail between Redmond &amp; Bellevue. Visit <a href="https://www.visitbellevuewa.com/plan/transportation/buses-and-light-rail/" rel="noopener noreferrer" target="_blank">https://www.visitbellevuewa.com/plan/transportation/buses-and-light-rail/</a> and <a href="https://www.soundtransit.org/discover2line" rel="noopener noreferrer" target="_blank">https://www.soundtransit.org/discover2line</a> for more information about public transit.</li><li data-list="bullet" class="ql-indent-2">Information about available parking in Bellevue can be found here: <a href="https://www.visitbellevuewa.com/plan/transportation/parking/" rel="noopener noreferrer" target="_blank">https://www.visitbellevuewa.com/plan/transportation/parking/</a>. </li><li data-list="bullet" class="ql-indent-2">Lincoln Square South offers a convenient parking garage that has elevator access to Floor 1 where Civility &amp; Unrest is located. See the attached map for the location of the Lincoln Square South parking garage entrance marked with red arrows. Civility &amp; Unrest staff can validate your parking for up to three hours.</li><li data-list="bullet" class="ql-indent-1">Will there be food and beverages at the event?</li><li data-list="bullet" class="ql-indent-2">Yes! Complimentary heavy appetizers, beverages, and spirits prepared by the Civility &amp; Unrest team is included with your registration for the meetup. </li><li data-list="bullet" class="ql-indent-1">What time does the presentation start? </li><li data-list="bullet" class="ql-indent-2">The presentation delivered by our guest speakers will begin around 6:00pm PT and will conclude by 6:30pm PT. Attendees are invited to enjoy food, beverages, and networking both before and after the presentation. </li></ol>Please send any questions about the event to MLSecOps Community Manager, Charlie McCarthy, <a href="https://community.mlsecops.com/home/messages" rel="noopener noreferrer" target="_blank">in a DM</a> or via our <a href="https://mlsecops.com/contact-us" rel="noopener noreferrer" target="_blank">Contact Us</a> form. We look forward to seeing you!<img alt="some-file-38ea1140-e2f3-4007-abac-8f5b252c7023" src="https://d2xo500swnpgl1.cloudfront.net/uploads/mlsecops/some-file-38ea1140-e2f3-4007-abac-8f5b252c7023-1724278042321.png">

September 2024 MLSecOps Meetup

Welcome to the fresh online series, "MLSecOps Connect: Ask the Experts," where MLSecOps Community members have the opportunity to hear their own questions answered by a variety of insightful guest speakers.Joining as our expert guest on August 28th is the Chief Architect at Protect AI, Sean Morgan! Sean will field questions from the community related to security for AI &amp; machine learning (ML), including the importance of&nbsp;<a href="https://protectai.com/blog/announcing-modelscan" rel="noopener noreferrer" target="_blank">ML model scanning</a>&nbsp;and how to get started with scanning models. Learn more about Sean in his bio below.Ways to submit your questions for the session:<ol><li data-list="ordered">Use the field provided in the registration form for this event to submit your questions about the specified topics for the session. Questions will be collected, then read aloud and answered during the event.</li><li data-list="ordered">If you think of additional questions after submitting the registration form, <a href="https://community.mlsecops.com/home/messages" rel="noopener noreferrer" target="_blank">send them in a DM</a> to the MLSecOps Community Manager, Charlie McCarthy.</li><li data-list="ordered">Finally, you can also submit questions in realtime during the event via the live chat, and we'll select one or two questions from the chat to answer toward the end of the session.</li></ol>We look forward to seeing you there! Stay involved with the MLSecOps Community in the meantime by checking out the additional resources <a href="https://mlsecops.com/join" rel="noopener noreferrer" target="_blank">here in our learning hub</a> and by joining us in <a href="https://mlsecops.com/slack" rel="noopener noreferrer" target="_blank">Slack</a> :)

Welcome to the fresh online series, "MLSecOps Connect: Ask the Experts," where community members can hear their own questions answered by a variety of insightful guest speakers.We're honored to welcome our next guest, Scott M. Giordano, Esq., to the show! Scott is an attorney based in the USA with more than 25 years of legal, technology, and risk management consulting experience (see full bio below), and is a wealth of knowledge. He joins us to field your questions regarding topics like AI regulations, Executive Order impact on cybersecurity posture, court endorsements of cybersecurity standards, AI cybersecurity resources, and more.Ways to submit your questions for the session:<ol><li data-list="ordered">Use the field provided in the registration form for this event to submit your questions about the specified topics for the session. Questions will be collected, then read aloud and answered during the event.</li><li data-list="ordered">If you think of additional questions after submitting the registration form, <a href="https://community.mlsecops.com/home/messages" rel="noopener noreferrer" target="_blank">send them in a DM</a> to the MLSecOps Community Manager, Charlie McCarthy.</li><li data-list="ordered">Finally, you can also submit questions in realtime during the event via the live chat, and we'll select one or two questions from the chat to answer toward the end of the session.</li></ol>Even if you cannot attend this session in realtime, register to receive a notification when the on-demand recording is available.

Exploring AI Cybersecurity and Regulation

Join us for the first in a new online series, "MLSecOps Connect: Ask the Experts," where community members can hear their own questions answered by a variety of insightful guest speakers. Kicking things off, our first esteemed speaker is Ian Swanson, Co-founder and CEO of <a href="https://protectai.com/" rel="noopener noreferrer" target="_blank">Protect AI</a>. Ian will join us on June 26, 2024 to field questions about all things MLSecOps and security for AI &amp; machine learning.Ways to submit your questions for the session: <ol><li data-list="ordered">Use the field provided in the registration form for this event to submit your questions about the specified topic for the session. We'll curate a list of the most popular questions submitted, then read them aloud during the event while giving a shoutout to the MLSecOps Community members who submitted each question. (Due to limited time, not all questions submitted may be read aloud during the event but we'll do our best to get to as many as we can.)</li><li data-list="ordered">If you think of additional questions after submitting the registration form, <a href="https://community.mlsecops.com/home/messages" rel="noopener noreferrer" target="_blank">send them in a DM</a> to the MLSecOps Community Manager, Charlie McCarthy. </li><li data-list="ordered">Finally, you can submit questions in realtime during the event via the live chat, and we'll select one or two questions from the chat to answer toward the end of the session. </li></ol>Even if you cannot attend this session in realtime, be sure to register anyway to receive a notification when the on-demand recording is available.

Securing AI/ML with Ian Swanson

Welcome to the MLSecOps Community, the premier hub for educational information about building security into AI and machine learning life cycles end-to-end. We look forward to meeting you!

Events

Content