Episode 33
EP 32: Using ChatGPT To Perform Side Channel Attacks On Real Hardware
March 13, 202430m 56s
Audio is streamed directly from the publisher (mcdn.podbean.com) as published in their RSS feed. Play Podcasts does not host this file. Rights-holders can request removal through the copyright & takedown page.
Show Notes
There’s a lot of talk about using AI and LLM in security. For example, could ChatGPT detect the vulnerable spots for power for analysis in particular pieces of code using Advanced Encryption Standard? Witold Waligora, CEO of CloudVA, talks about his Black Hat Europe presentation, How We Taught ChatGPT-4 to Break mbedTLS AES With Side-Channel Attacks.