DeepAI AI Chat
Log In Sign Up

Adaptive Image Transformations for Transfer-based Adversarial Attack

by   Zheng Yuan, et al.
Institute of Computing Technology, Chinese Academy of Sciences

Adversarial attacks provide a good way to study the robustness of deep learning models. One category of methods in transfer-based black-box attack utilizes several image transformation operations to improve the transferability of adversarial examples, which is effective, but fails to take the specific characteristic of the input image into consideration. In this work, we propose a novel architecture, called Adaptive Image Transformation Learner (AITL), which incorporates different image transformation operations into a unified framework to further improve the transferability of adversarial examples. Unlike the fixed combinational transformations used in existing works, our elaborately designed transformation learner adaptively selects the most effective combination of image transformations specific to the input image. Extensive experiments on ImageNet demonstrate that our method significantly improves the attack success rates on both normally trained models and defense models under various settings.


Admix: Enhancing the Transferability of Adversarial Attacks

Although adversarial attacks have achieved incredible attack success rat...

Learnability Lock: Authorized Learnability Control Through Adversarial Invertible Transformations

Owing much to the revolution of information technology, the recent progr...

Where Does the Robustness Come from? A Study of the Transformation-based Ensemble Defence

This paper aims to provide a thorough study on the effectiveness of the ...

Sibylvariant Transformations for Robust Text Classification

The vast majority of text transformation techniques in NLP are inherentl...

Boosting Adversarial Transferability by Block Shuffle and Rotation

Adversarial examples mislead deep neural networks with imperceptible per...

Input-specific Attention Subnetworks for Adversarial Detection

Self-attention heads are characteristic of Transformer models and have b...

Improving the Transferability of Adversarial Examples with Arbitrary Style Transfer

Deep neural networks are vulnerable to adversarial examples crafted by a...