💻 computer science
BadDet+: Robust Backdoor Attacks for Object Detection
BadDet+ is a robust, penalty-based framework that unifies region misclassification and object disappearance attacks to overcome the unrealistic assumptions and lack of physical validation in existing backdoor methods for object detection, achieving superior synthetic-to-physical transfer while preserving clean model performance.
Original paper licensed under CC BY 4.0 (http://creativecommons.org/licenses/by/4.0/). This is an AI-generated explanation of the paper below. It is not written or endorsed by the authors. For technical accuracy, refer to the original paper. Read full disclaimer
Drowning in papers in your field?
Get daily digests of the most novel papers matching your research keywords — with technical summaries, in your language.