Abstract Model inversion (MI) attacks aim to infer and reconstruct private training data by
abusing access to a model. MI attacks have raised concerns about the leaking of sensitive …

Adversarial Training (AT) has become arguably the state-of-the-art algorithm for extracting
robust features. However, researchers recently notice that AT suffers from severe robust …

Adversarial training suffers from the issue of robust overfitting, which seriously impairs its
generalization performance. Data augmentation, which is effective at preventing overfitting …

In machine learning, generative modeling aims to learn to generate new data statistically
similar to the training data distribution. In this paper, we survey learning generative models …

With the prevalence of the Pretraining-Finetuning paradigm in transfer learning the
robustness of downstream tasks has become a critical concern. In this work we delve into …

Recent work have demonstrated that robustness (to" corruption") can be at odds with
generalization. Adversarial training, for instance, aims to reduce the problematic …

One prominent approach toward resolving the adversarial vulnerability of deep neural
networks is the two-player zero-sum paradigm of adversarial training, in which predictors are …

Adversarial training has shown promise in building robust models against adversarial
examples. A major drawback of adversarial training is the computational overhead …

Recently non-transferable learning (NTL) was proposed to restrict models' generalization
toward the target domain (s) which serves as state-of-the-art solutions for intellectual …

Single-step adversarial training (SSAT) has demonstrated the potential to achieve both
efficiency and robustness. However, SSAT suffers from catastrophic overfitting (CO), a …