On Adversarial Training & Robustness with Bhavna Gopal

Update: 2024-05-08

Description

"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 discuss

How 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?

Comments

In Channel

The Future is Fine Tuned (with Dev Rishi, Predibase)

2024-05-2452:28

Pre-training LLMs: One Model To Rule Them All? with Talfan Evans, DeepMind

2024-05-1837:36

On Adversarial Training & Robustness with Bhavna Gopal

2024-05-0844:05

On Emotionally Intelligent AI (with Chris Gagne, Hume AI)

2024-04-1939:53

Why Greatness Cannot Be Planned (with Joel Lehman)

2024-03-2247:07

Where are the good AI products? (with Varun Shenoy)

2024-03-1246:54

The End of RAG (with Donato Riccio)

2024-02-0940:13

GPUs and how the cloud is changing (with Cedana Founder, Neel Master)

2024-02-0242:48

Live Video Translation with AI

2024-01-2228:37

Is open-source AI safe? (with SafeLlama founder, Enoch Kan)

2024-01-1236:55

What is the future of AI-assisted or AI-driven software?

2024-01-0532:54

Is the Turing Test Outdated?

2023-12-1545:17

Prompt Engineering

2023-12-0838:48

AI for Investment Diligence

2023-11-2433:34

The Myth of Human-in-the-Loop

2023-11-1536:28

AI-Generated Content and the Boring Apocalypse

2023-11-0839:34

Programming for Machine Learning (Tech Talk)

2023-10-3033:11

AI's End of History Illusion

2023-10-2508:21

Design Driven Development at Slingshot

2023-10-1624:59

LLM Inference Speed (Tech Deep Dive)

2023-10-0639:36

00:00

On Adversarial Training & Robustness with Bhavna Gopal

#box-pro-ellipsis-172035007324119{-webkit-line-clamp:2;}On Adversarial Training & Robustness with Bhavna Gopal

On Adversarial Training & Robustness with Bhavna Gopal

Daniel Reid Cahn

On Adversarial Training & Robustness with Bhavna Gopal