Beneath the Prompt: The Hidden Risks Powering GenAI
Date: September 25, 2025 (GMT +8)
Time: 11:30
TRACK 1
SPEEDTALK
As LLMs power more applications across industries, firmware and hardware security is now mission-critical. The attack surface has shifted downward, making Al infrastructure itself the new battleground. Securing GenAl involves both:
- Traditional cybersecurity controls (monitoring, patching, access controls)
- Al-specific governance frameworks (model integrity, supply chain verification)
The message is clear: securing the model is not enough—you must secure the machine it runs on. This talk will highlight the vulnerabilities in the infrastructure powering large language models (LLMs) and generative Al systems. It will focus on the hardware, firmware, and cloud components that support Al, revealing how these foundational layers are increasingly targeted by sophisticated attacks
Speaker
Alex BazhaniukAlex is one of the industry's foremost authorities in the fields of firmware security, research, and product development. Over his career, he has led teams and innovation at leading organisations including Eclypsium, Intel, and McAfee. He has also been an active contributor in the open-source community and was one of the original core developers for CHIPSEC. At Eclypsium, Alex leads both the Eclypsium research and development teams, driving a variety of industry innovations and discoveries. During his work with the Eclypsium Research Labs team, he has led some of the most significant firmware discoveries in recent years, for example, TrickBoot malware module, the BootHole, and Screwed Drivers vulnerabilities.
« Back