← Search

Jiehang Zeng

2 accepted papers

2021

Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning

EMNLP 2021main

Pre-Trained Models have been widely applied and recently proved vulnerable under backdoor attacks: the released pre-trained weights can be maliciously poisoned with certain triggers. When the triggers are activated, even the fine-tuned model will predict pre-defined labels, causing a security threat…

Cited by 143SourcePDFScholar
2021

Searching for an Effective Defender: Benchmarking Defense against Adversarial Word Substitution

EMNLP 2021main

Recent studies have shown that deep neural network-based models are vulnerable to intentionally crafted adversarial examples, and various methods have been proposed to defend against adversarial word-substitution attacks for neural NLP models. However, there is a lack of systematic study on comparin…