Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger
arXiv:2105.12400
Abstract
Backdoor attacks are a kind of insidious security threat against machine learning models. After being injected with a backdoor in training, the victim model will produce adversary-specified outputs on the inputs embedded with predesigned triggers but behave properly on normal inputs during inference. As a sort of emergent attack, backdoor attacks in natural language processing (NLP) are investigated insufficiently. As far as we know, almost all existing textual backdoor attack methods insert additional contents into normal samples as triggers, which causes the trigger-embedded samples to be detected and the backdoor attacks to be blocked without much effort. In this paper, we propose to use the syntactic structure as the trigger in textual backdoor attacks. We conduct extensive experiments to demonstrate that the syntactic trigger-based attack method can achieve comparable attack performance (almost 100% success rate) to the insertion-based methods but possesses much higher invisibility and stronger resistance to defenses. These results also reveal the significant insidiousness and harmfulness of textual backdoor attacks. All the code and data of this paper can be obtained at https://github.com/thunlp/HiddenKiller.
arXiv commentAccepted by ACL-IJCNLP 2021 as a long paper. Camera-ready version
References in corpus (6)
- Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
- BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
- Generative Poisoning Attack Method Against Neural Networks
- Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbation
- Defending Neural Backdoors via Generative Distribution Modeling
- Weight Poisoning Attacks on Pre-trained Models