Influencer Backdoor Attack on Semantic Segmentation

Understand

When a small number of poisoned samples are injected into the training dataset of a deep neural network, the network can be induced to exhibit malicious behavior during inferences, which poses potential threats to real-world applications.

• While they have been intensively studied in classification, backdoor attacks on semantic segmentation have been largely overlooked.
• Unlike classification, semantic segmentation aims to classify every pixel within a given image.
• In this work, we explore backdoor attacks on segmentation models to misclassify all pixels of a victim class by injecting a specific trigger on non-victim pixels during inferences, which is dubbed Influencer Backdoor Attack (IBA).