In this episode of The BlueHat Podcast, host Nic Fillingham and Wendy Zenone share Ram Shankar Siva Kumar’s dynamic keynote from BlueHat India 2025, where he explores the evolving threat landscape of AI through the lens of the Microsoft AI Red Team. From adversarial machine learning to psychosocial harms and persuasive AI, Ram highlights real-world case studies, including prompt injection, content safety violations, and memory poisoning in AI agents. Ram underscores the urgent need for robust red teaming practices to secure AI systems against traditional security flaws and emerging threats across images, text, audio, and autonomous agents. 
 
In This Episode You Will Learn:  
  
Why old-school security flaws still break modern AI systems 
  
Real-world AI red teaming in action, from scams to memory hacks 
  
How small input tweaks can fool AI across images, audio, and text 
Some Questions We Ask: 
  
Can attackers fool AI using just slight image changes? 
  
Are generative AI systems vulnerable to prompt manipulation? 
  
Do you need to be an expert to break an AI model? 
   
Resources:      
Watch Ram’s BlueHat India 2025 Keynote: BlueHat India 2025 Day 2 Keynote - Ram Shankar Siva Kumar 
Listen to Ram’s Previous Appearance on The BlueHat Podcast: Not with a Bug but with a Sticker 
 
View Ram Shankar Siva Kumar on LinkedIn    
View Wendy Zenone on LinkedIn   
View Nic Fillingham on LinkedIn  
 
Related Microsoft Podcasts:   
  
Microsoft Threat Intelligence Podcast   
  
Afternoon Cyber Tea with Ann Johnson   
  
Uncovering Hidden Risks   
  
Discover and follow other Microsoft podcasts at microsoft.com/podcasts   
 
The BlueHat Podcast is produced by Microsoft and distributed as part of N2K media network.  
Show more...