Raja Jurdak
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
eDySec introduces a deep learning framework for dynamic behavioral analysis that significantly improves the detection of malicious software packages in the PyPI ecosystem by enhancing stability and explainability.
The paper proposes a detection-aware adversarial fine-tuning framework to mitigate backdoor attacks in object detection models, achieving better defense while preserving clean detection performance compared to classification-based methods.
Papers
Backdoor Mitigation in Object Detection via Adversarial Fine-Tuning
Kealan Dunnett, Reza Arablouei, Dimity Miller, Volkan Dedeoglu +1 more
The paper proposes a detection-aware adversarial fine-tuning framework to mitigate backdoor attacks in object detection models, achieving better defense while preserving clean detection performance co…