ASCEND
BY NTHRYS

NTHRYS › PhD Assistance › Artificial Intelligence

Artificial Intelligence

Field
▾
Category
▾

Artificial Intelligence

Select a category to explore research frontiers

Loading categories...

Research Frontiers in Adversarial Robustness and Attack Mitigation

Study of vulnerabilities in neural networks to adversarial perturbations and development of defensive strategies to improve model robustness.

Adversarial Perturbations in Latent Representation Spaces
Certified Robustness Through Computational Geometry
Transferability and Universality of Adversarial Examples
Backdoor Attacks and Trojan Detection in Deep Networks
Adversarial Robustness Under Distribution Shift
Neural Network Interpretability for Attack Vulnerability Analysis
Physical World Adversarial Robustness in Vision Systems
Adversarial Training Dynamics and Generalization Trade-offs
Poisoning Attacks on Machine Learning Training Data
Multimodal Adversarial Robustness in Federated Learning

All Artificial Intelligence PhD categories