← Search

Bahar Dibaei Nia

2 accepted papers

2025

Towards an Explainable Comparison and Alignment of Feature Embeddings

ICML 2025poster

While several feature embedding models have been developed in the literature, comparisons of these embeddings have largely focused on their numerical performance in classification-related downstream applications. However, an interpretable comparison of different embeddings requires identifying and a…

2024

Scanning Trojaned Models Using Out-of-Distribution Samples

NeurIPS 2024poster

Scanning for trojan (backdoor) in deep neural networks is crucial due to their significant real-world applications. There has been an increasing focus on developing effective general trojan scanning methods across various trojan attacks. Despite advancements, there remains a shortage of methods that…