Search Results for author:
Found 7 papers, 0 papers with code
Knowledge Pursuit Prompting for Zero-Shot Multimodal Synthesis
To address this question, we propose Knowledge Pursuit Prompting (KPP), a zero-shot framework that iteratively incorporates external knowledge to help generators produce reliable visual content.
Zero-shot Model Diagnosis
Extensive experiments demonstrate that our method is capable of producing counterfactual images and offering sensitivity analysis for model diagnosis without the need for a test set.
Semantic Image Attack for Visual Model Diagnosis
Rather than relying on a carefully designed test set to assess ML models' failures, fairness, or robustness, this paper proposes Semantic Image Attack (SIA), a method based on the adversarial attack that provides semantic adversarial images to allow model diagnosis, interpretability, and robustness.
Inconspicuous Adversarial Patches for Fooling Image Recognition Systems on Mobile Devices
The patches are encouraged to be consistent with the background images with adversarial training while preserving strong attack abilities.
Recent Advances in Adversarial Training for Adversarial Robustness
Adversarial training is one of the most effective approaches defending against adversarial examples for deep learning models.
Recent Advances in Understanding Adversarial Robustness of Deep Neural Networks
Adversarial examples are inevitable on the road of pervasive applications of deep neural networks (DNN).
Generating Adversarial yet Inconspicuous Patches with a Single Image
Through extensive experiments, our ap-proach shows strong attacking ability in both the white-box and black-box setting.
