Robust Backdoor Attacks on Object Detection in Real World
This addresses a security problem for applications using object detection, but it is incremental as it builds on existing backdoor attack research by focusing on real-world physical factors.
The paper tackles the vulnerability of object detection models to backdoor attacks in real-world conditions by proposing a variable-size trigger and malicious adversarial training, resulting in enhanced attack success rates.
Deep learning models are widely deployed in many applications, such as object detection in various security fields. However, these models are vulnerable to backdoor attacks. Most backdoor attacks were intensively studied on classified models, but little on object detection. Previous works mainly focused on the backdoor attack in the digital world, but neglect the real world. Especially, the backdoor attack's effect in the real world will be easily influenced by physical factors like distance and illumination. In this paper, we proposed a variable-size backdoor trigger to adapt to the different sizes of attacked objects, overcoming the disturbance caused by the distance between the viewing point and attacked object. In addition, we proposed a backdoor training named malicious adversarial training, enabling the backdoor object detector to learn the feature of the trigger with physical noise. The experiment results show this robust backdoor attack (RBA) could enhance the attack success rate in the real world.