Advbox Family is a series of AI model security tools set of Baidu Open Source,including the generation, detection and protection of adversarial examples, as well as attack and defense cases for different AI applications.
- ABSTRACT:Cloud-based Image Classification Service Is Not Robust To Affine Transformation : A Forgotten Battlefield. CCSW 2019: The ACM Cloud Computing Security Workshop of CCS 2019
- TRANSFERABILITY OF ADVERSARIAL EXAMPLES TO ATTACK REAL WORLD PORN IMAGES DETECTION SERVICE.HITB CyberWeek 2019
- COMMSEC: Tracking Fake News Based On Deep Learning. HITB GSEC 2019
- COMMSEC: Hacking Object Detectors Is Just Like Training Neural Networks. HITB GSEC 2019
- COMMSEC: How to Detect Fake Faces (Manipulated Images) Using CNNs. HITB GSEC 2019
- Transferability of Adversarial Examples to Attack Cloud-based Image Classifier Service. Defcon China 2019
- Face Swapping Video Detection with CNN. Defcon China 2019
A Lightweight Adv SDK For PaddlePaddle to generate adversarial examples.
Advbox is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle、PyTorch、Caffe2、MxNet、Keras、TensorFlow and Advbox can benchmark the robustness of machine learning models.Advbox give a command line tool to generate adversarial examples with Zero-Coding.
ODD is a tool-box for attacking object detectors with mainstream attack methods. It provides users with convenience on doing experiment and benchmark. Users can place modified OD model and customize attack cost function according to attack goal in the framework.
For now, ODD only has a yolo(faster-yolo v2) model to play with. We welcome contributions for more models and attack methods to go onto the stage.
- It is Open Source for COMMSEC: Hacking Object Detectors Is Just Like Training Neural Networks. HITB GSEC 2019
- Recorded Video from 6:00:00
AdvDetect is a toolbox to detect adversarial examples from massive data.
Data poisoning
Homepage of Face Recogniztion Attack
On defcon, we demonstrated T-shirts that can disappear under smart cameras. Under this sub-project, we open-source the programs and deployment methods of smart cameras for demonstration.
The restful API is used to detect whether the face in the picture/video is a false face.
https://github.com/baidu/AdvBox/issues
AdvBox support Apache License 2.0
- Baidu xlab
If you instead use AdvBox in an academic publication, cite as:
@misc{advbox,
author= {Baidu X-lab},
title = {Advbox:a toolbox to generate adversarial examples that fool neural networks},
month = mar,
year = 2019,
url = {https://github.com/baidu/AdvBox}
}