Goto

Collaborating Authors

 transferability



Boosting Adversarial Transferability by Achieving Flat Local Maxima

Neural Information Processing Systems

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.


Learning Human Action Recognition Representations Without Real Humans

Neural Information Processing Systems

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.



Content-based Unrestricted Adversarial Attack

Neural Information Processing Systems

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