Other Approach: Use Hardware Support for Efficient Oblivious Data Processing
5
How to Support Data Obliviousness ??
6
Support for Basic Data Science
7
Experimental Evaluation
8
Comparison with ObliVM
9
Federated Learning: Privacy vs Robustness
10
Backdoor Attacks in FL context
11
Overview
12
Experiments
13
Comparison with Other Defenses - IID
14
Conclusion: FL Poisoning Attacks
15
Attacking models to improve privacy and fairness
16
Example: Attacking Image Classifiers
17
Domain constraint Example
18
Example: Prevent Gender Prediction
19
Change Images Using Glasses
20
Questions?
Description:
Explore the intersection of big data security and artificial intelligence in this 39-minute conference talk by Dr. Murat Kantarcioglu from the University of Texas at Dallas. Delve into the changing landscape of the big data revolution and its associated challenges. Examine hardware-supported approaches for efficient oblivious data processing and their applications in basic data science. Compare experimental evaluations with ObliVM and investigate the trade-offs between privacy and robustness in federated learning. Analyze backdoor attacks in the context of federated learning, including experiments and comparisons with other defenses. Conclude with insights on federated learning poisoning attacks and explore techniques for attacking models to enhance privacy and fairness, such as preventing gender prediction in image classifiers.
Securing Big Data in the Age of Artificial Intelligence