DeepAI AI Chat
Log In Sign Up

Sparse Adversarial Attack to Object Detection

by   Jiayu Bao, et al.
Tsinghua University

Adversarial examples have gained tons of attention in recent years. Many adversarial attacks have been proposed to attack image classifiers, but few work shift attention to object detectors. In this paper, we propose Sparse Adversarial Attack (SAA) which enables adversaries to perform effective evasion attack on detectors with bounded l_0 norm perturbation. We select the fragile position of the image and designed evasion loss function for the task. Experiment results on YOLOv4 and FasterRCNN reveal the effectiveness of our method. In addition, our SAA shows great transferability across different detectors in the black-box attack setting. Codes are available at


page 3

page 4


Fooling Object Detectors: Adversarial Attacks by Half-Neighbor Masks

Although there are a great number of adversarial attacks on deep learnin...

Transferable Sparse Adversarial Attack

Deep neural networks have shown their vulnerability to adversarial attac...

Using LIP to Gloss Over Faces in Single-Stage Face Detection Networks

This work shows that it is possible to fool/attack recent state-of-the-a...

Black-Box Attack against GAN-Generated Image Detector with Contrastive Perturbation

Visually realistic GAN-generated facial images raise obvious concerns on...

A Large-scale Multiple-objective Method for Black-box Attack against Object Detection

Recent studies have shown that detectors based on deep models are vulner...

Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attacks

Adversarial training (AT) with imperfect supervision is significant but ...

Can 3D Adversarial Logos Cloak Humans?

With the trend of adversarial attacks, researchers attempt to fool train...