Adrian Wood

Adrian Wood, aka threlfall, is a security researcher. At BT6, he performs AI danger research with frontier labs.

At Dropbox, he builds offensive AI capabilities, and researches topics like supply chain attacks on CI/CD and ML systems. This includes maintaining the offsec ml playbook and the 'stealthbench' adversarial benchmark. He has presented on these topics at BLACK HAT ASIA & USA, DEFCON 30, 31, the DEFCON AI village, Cackalackycon and more.

Speaker / Contributor: This individual participates in SANS events, presentations, written content, or other community resources as an external contributor. They are not a SANS employee, instructor, or affiliate.