On Adversarial Training & Robustness with Bhavna Gopal

08/05/2024 44 min
On Adversarial Training & Robustness with Bhavna Gopal

Listen "On Adversarial Training & Robustness with Bhavna Gopal"

Episode Synopsis


"Understanding what's going on in a model is important to fine-tune it for specific tasks and to build trust."Bhavna Gopal is a PhD candidate at Duke, research intern at Slingshot with experience at Apple, Amazon and Vellum.We discussHow adversarial robustness research impacts the field of AI explainability.How do you evaluate a model's ability to generalize?What adversarial attacks should we be concerned about with LLMs?