EPISODE 02 – Securing the AI Frontier

The adoption of artificial intelligence and large language models (LLMs) presents a significant opportunity for business innovation, but also introduces a new and complex attack surfaces. Balancing the drive for AI integration with robust security measures is essential for long-term strategic success and risk mitigation. 

Key Insights 

Gain a strategic advantage by understanding the vulnerabilities inherent in AI and how to address them. This episode provides crucial insights to enhance your risk management framework: 

• The Evolving AI Threat Landscape: Understand how attackers are adapting their methods to target AI and LLMs, and what this means for your organization’s risk profile. 
• Actionable Testing Strategies: Learn about the go-to techniques for evaluating a new AI application, ensuring your team can proactively identify and address vulnerabilities before they impact business outcomes. 
• The Human-AI Intersection: Explore the convergence of social engineering and AI testing, a new frontier for potential exploits that requires a holistic security approach. 

About the Speakers 

Host: Karl Fosaaen | VP, Research 

As a VP of Research, Karl is part of a team developing new services and product offerings at NetSPI. Karl previously oversaw the Cloud Penetration Testing service lines at NetSPI and is one of the founding members of NetSPI’s Portland, OR team. Karl has a Bachelors of Computer Science from the University of Minnesota and has been in the security consulting industry for over 15 years. Karl spends most of his research time focusing on Azure security and contributing to the NetSPI blog. As part of this research, Karl created the MicroBurst toolkit (https://github.com/NetSPI/Microburst) to house many of the PowerShell tools that he uses for testing Azure. In 2021, Karl co-authored the book “Penetration Testing Azure for Ethical Hackers” with David Okeyode. 

Guest: Kim Wiles | Director of AI Penetration Testing 
As Director of AI Penetration Testing at NetSPI, Kimberly Wiles is responsible for performing simulated adversarial attacks on AI-integrated client environments, structuring service offerings to ensure relevance, and maintaining clear communication with clients to deliver actionable insights. 

After earning a degree in mathematics, Kimberly began her career in cybersecurity and specializes in the security of AI implementations, focusing on vulnerabilities ranging from simple chatbot interactions to complex, application-wide chained exploits that take advantage processes including models.  

Kimberly is exceptionally proud of her leadership in growing NetSPI’s AI service line, guiding her team to deliver impactful results and scale their efforts in this emerging field. She has also contributed to the security community through local college recruiting presentations on AI testing and conducts internal research initiatives aimed at advancing NetSPI’s AI testing capabilities regarding AI tooling developments and orchestration framework implementations. 

Empower your strategic decisions with these additional resources: 

• Service Overview: NetSPI AI/ML Penetration Testing 
• Solution Brief: NetSPI AI/ML Pentesting 
• Technical Insights: Hack Responsibly Blog 
• Tools: NetSPI Open Source Tools 

Find more episodes on YouTube or wherever you listen to podcasts.