To speed up ACL, this paper proposes a robustness-aware coreset selection (RCS) method.

Specifically, we randomly sample an example and adopt a first-order procedure to approximate the Hessian/vector product, which makes computing more efficient by interpolating two neighboring gradients.

Existing work has attempted to alleviate these problems by blurring faces, downsampling videos, or training on synthetic data. On the other hand, analysis on the transferability of privacy-preserving pre-trained models to downstream tasks has been limited.

Unrestricted adversarial attacks typically manipulate the semantic content of an image ( e.g., color or texture) to create adversarial examples that are both effective and photorealistic, demonstrating their ability to deceive human perception

Recently, pre-trained vision-language models have been increasingly used to tackle the challenging zero-shot segmentation task.