Privacy and Fairness

Parinaz discusses the emerging challenges in AI, particularly adversarial attacks and the importance of AI safety. She highlights her work on differential privacy, emphasizing how it can create value while ensuring user data protection. Additionally, she challenges the notion that accuracy and fairness are mutually exclusive, sharing insights on how improving sampling strategies can enhance both model performance and fairness for protected groups.

In this clip
From this podcast
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Trust and AI with Parinaz Sobhani - TWiML Talk #208
Related Questions
- Can you give examples of adversarial attacks on machine learning models?
- What are the challenges in machine learning as discussed in the episode Approaches to Fairness and XAI // Murtuza Shergadwala // MLOps Podcast #142 and the clip Alert Management Approaches?

Privacy and Fairness

In this clip

From this podcast

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

Trust and AI with Parinaz Sobhani - TWiML Talk #208

Related Questions

Can you give examples of adversarial attacks on machine learning models?

What are the challenges in machine learning as discussed in the episode Approaches to Fairness and XAI // Murtuza Shergadwala // MLOps Podcast #142 and the clip Alert Management Approaches?