ASCEND
BY NTHRYS

NTHRYS › PhD Assistance › Synthetic Intelligence

Synthetic Intelligence

Field
▾
Category
▾

Synthetic Intelligence

Select a category to explore research frontiers

Loading categories...

Research Frontiers in Adversarial Robustness and Certified Defense Mechanisms

Development of provably robust AI systems that withstand adversarial attacks and provide formal security guarantees.

Adversarial Perturbations in High-Dimensional Latent Spaces
Certified Defenses Against Compositional Attack Sequences
Robustness Verification at the Continuous-Discrete Boundary
Transferability and Generalization of Adversarial Examples
Geometric Properties of Decision Boundaries Under Certification
Adaptive Attacks Against Provably Robust Neural Networks
Certified Defenses in Multimodal and Cross-Domain Systems
Scalable Verification Methods for Large-Scale Deep Models
Adversarial Robustness in Dynamically Evolving Threat Models
Trade-offs Between Certifiable Robustness and Model Expressivity

All Synthetic Intelligence PhD categories