Zobrazeno 1 - 3
of 3
pro vyhledávání: '"You, Wencong"'
Backdoor attacks manipulate model predictions by inserting innocuous triggers into training and test data. We focus on more realistic and more challenging clean-label attacks where the adversarial training examples are correctly labeled. Our attack,
Externí odkaz:
http://arxiv.org/abs/2310.18603
Autor:
Asthana, Kalyani, Xie, Zhouhang, You, Wencong, Noack, Adam, Brophy, Jonathan, Singh, Sameer, Lowd, Daniel
We introduce the Text Classification Attack Benchmark (TCAB), a dataset for analyzing, understanding, detecting, and labeling adversarial attacks against text classifiers. TCAB includes 1.5 million attack instances, generated by twelve adversarial at
Externí odkaz:
http://arxiv.org/abs/2210.12233
Autor:
Xie, Zhouhang, Brophy, Jonathan, Noack, Adam, You, Wencong, Asthana, Kalyani, Perkins, Carter, Reis, Sabrina, Singh, Sameer, Lowd, Daniel
The landscape of adversarial attacks against text classifiers continues to grow, with new attacks developed every year and many of them available in standard toolkits, such as TextAttack and OpenAttack. In response, there is a growing body of work on
Externí odkaz:
http://arxiv.org/abs/2201.08555