Breakpoint Security Podcast
Breakpoint-'Exploring the depths of Defensive Security'. The defensive side of Security is a world in itself with teams achieving amazing feats that involve excellent engineering practices and smart optimisation for scale. This is not talked about enough in the industry. Join me in the br3akp0int podcast as we reflect on the methods and approaches these smart teams use to solve practical challenges in information security and innovate their way into the future. Who is this meant for? : This podcast is for anyone in InfoSec willing to know more about advances in security techniques. This includes security researchers or professionals, product owners, compliance or cloud, AI/ML, threat intel, SecOps automation, Security Leaders, development teams, pentesters and security practitioners. A bit about me: I am a technical security enthusiast and have been dabbling my hands at both offensive and defensive security. I am passionate about growing security communities and have spoken and trained at various security conferences.
Breakpoint Security Podcast
S04EP02 | Reversing Large Deep Learning Models | Yashodhan Mandke
Have you ever thought about how an attacker might reverse-engineer an AI model? Our guest today is doing just that, going beyond passwords and keys to unpack the very DNA of deep learning!
In this segment, we're diving into the groundbreaking work of reversing large deep learning models. Our guest reveals how it's possible to reverse an AI model's entire mathematical structure, exposing its architecture, critical hyperparameters, and even the internal weights and biases that define its behavior. We'll explore this new frontier of security research in the context of different model formats and major models like GoogleNet and Llama. This isn't just about finding vulnerabilities; it's about understanding how a malicious actor could exploit the sparsity of a tensor or reverse a tokenizer, fundamentally subverting an AI's core logic. This is next-level threat intelligence, showing us how to defend AI by understanding its deepest secrets.
Guest: Yashodhan Mandke, Research Scholar MIT-WPU
Yashodhan is a Security Researcher with over 13 years of cutting-edge experience at the intersection of IoT and AI innovation. A tech visionary currently pursuing a doctorate in Satellite and Security, Yashodhan’s academic journey spans M.Tech in Satellite Communication, M.Tech in Signal Processing, and a B.E. in Electronics & Telecommunication.
Recommended reading/viewing, Paper(in this topic) for practitioners
https://goa2025.nullcon.net/doc/goa-2025/nullcon_2025_rev_dl.pdf
--
Follow us on LinkedIn: https://www.linkedin.com/company/breakpoint-security-podcast
Audio on Buzzsprout: https://breakpoint.buzzsprout.com
If you like to see more like this, please Subscribe to Breakpoint Youtube!
Please Share with others in the community. It always means a lot!
Follow us on LinkedIn: @breakpoint-security-podcast
Audio on Buzzsprout: https://breakpoint.buzzsprout.com
Buzz me on Twitter or LinkedIn Connect with me on -
- Twitter: @NeeluTripathy
- LinkedIn: @neelutripathy
