A backdoor attack against LSTM-based text classification systems

Understand

With the widespread use of deep learning system in many applications, the adversary has strong incentive to explore vulnerabilities of deep neural networks and manipulate them.

• Backdoor attacks against deep neural networks have been reported to be a new type of threat.
• In this attack, the adversary will inject backdoors into the model and then cause the misbehavior of the model through inputs including backdoor triggers.
• Existed research mainly focuses on backdoor attacks in image classification based on CNN, little attention has been paid to the backdoor attacks in RNN.