会员服务
OpenFact at CheckThat! 2024: Combining Multiple Attack Methods for Effective Adversarial Text Generation
Arxiv
0+阅读 · 9月4日
OpenFact at CheckThat! 2024: Combining Multiple Attack Methods for Effective Adversarial Text Generation
Arxiv
0+阅读 · 9月5日
The Impact of Quantization on the Robustness of Transformer-based Text Classifiers
Arxiv
0+阅读 · 3月8日
Accuracy of TextFooler black box adversarial attacks on 01 loss sign activation neural network ensemble
Arxiv
0+阅读 · 2月12日
Text Adversarial Purification as Defense against Adversarial Attacks
Arxiv
0+阅读 · 2023年5月3日
Contrasting Human- and Machine-Generated Word-Level Adversarial Examples for Text Classification
Contrasting Human- and Machine-Generated Word-Level Adversarial Examples for Text Classification
Arxiv
0+阅读 · 2021年9月9日
Experiments with adversarial attacks on text genres
Arxiv
0+阅读 · 2021年7月5日
FireBERT: Hardening BERT-based classifiers against adversarial attack
FireBERT: Hardening BERT-based classifiers against adversarial attack
Arxiv
0+阅读 · 2020年8月10日
Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment
Arxiv
0+阅读 · 2020年4月8日
Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment
Arxiv
0+阅读 · 2020年4月5日
Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment
Arxiv
0+阅读 · 2020年1月23日
Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment
Arxiv
0+阅读 · 2019年11月23日
Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment
Arxiv
0+阅读 · 2019年9月7日
Is BERT Really Robust? Natural Language Attack on Text Classification and Entailment
Arxiv
2+阅读 · 2019年7月27日
参考链接
微信扫码咨询专知VIP会员
Top