Recent years have seen the wide application of NLP models in crucial areas such as finance, medical treatment, and news media, raising concerns about the model robustness. Existing methods are mainly ...
As artificial intelligence (AI) continues to advance at an unprecedented pace, ensuring the fairness of deep neural networks (DNNs) has become a pressing concern. Adversarial sampling, initially ...
In the research, they analyze the relation of adversarial transferability and output consistency of different models, and observe that higher output inconsistency tends to induce lower transferability ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback