search

git-disl / TOG

Real-time object detection is one of the key applications of deep neural networks (DNNs) for real-world mission-critical systems. While DNN-powered object detection systems celebrate many life-enriching opportunities, they also open doors for misuse and abuse. This project presents a suite of adversarial objectness gradient attacks, coined as TOG, which can cause the state-of-the-art deep object detection networks to suffer from untargeted random attacks or even targeted attacks with three types of specificity: (1) object-vanishing, (2) object-fabrication, and (3) object-mislabeling. Apart from tailoring an adversarial perturbation for each input image, we further demonstrate TOG as a universal attack, which trains a single adversarial perturbation that can be generalized to effectively craft an unseen input with a negligible attack time cost. Also, we apply TOG as an adversarial patch attack, a form of physical attacks, showing its ability to optimize a visually confined patch filled with malicious patterns, deceiving well-trained object detectors to misbehave purposefully.
121 stars 41 forks source link

too many wrong outcomes #25

Open xc3217 opened 1 year ago

xc3217 commented 1 year ago

I don't know how to solve it.I create the virtual environment as the requirements.txt.when I run,the picture is full of wrong boxes.

khchow-gt commented 1 year ago

Did you run the attack? TOG is designed to confuse the object detection system to produce wrong results.

xc3217 commented 1 year ago

begin no attack also has too many wrong results,i don't know why

zth1100 commented 6 months ago

I met the same question, is it solved?

zth1100 commented 6 months ago

when I ran on the win11 system, this problem comes out, but change to the linux and win 10, the output is correct.