Fetching the paper…

Reading the bibliography…

On Evaluating Neural Network Backdoor Defenses · Around

2020

On Evaluating Neural Network Backdoor Defenses

Veldanda, Akshaj, Garg, Siddharth

Original
PDF
Post on X

Understand

Deep neural networks (DNNs) demonstrate superior performance in various fields, including scrutiny and security.

However, recent studies have shown that DNNs are vulnerable to backdoor attacks.
Several defenses were proposed in the past to defend DNNs against such backdoor attacks.
In this work, we conduct a critical analysis and identify common pitfalls in these existing defenses, prepare a comprehensive database of backdoor attacks, conduct a side-by-side evaluation of existing defenses against this database.

Built on

Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks
Kang Liu, Brendan Dolan-Gavitt, and Siddharth Garg · 2018
Earlier work this paper cites.
Spectral signatures in backdoor attacks
Brandon Tran, Jerry Li, and Aleksander Madry · 2018
Earlier work this paper cites.
Strip: A Defence Against Trojan Attacks on Deep Neural Networks
Yansong Gao, Change Xu, Derui Wang, Shiping Chen, Damith C Ranasinghe, and Surya Nepal · 2019
Earlier work this paper cites.

Similar

Badnets: Evaluating backdooring attacks on deep neural networks
Tianyu Gu, Kang Liu, Brendan Dolan-Gavitt, and Siddharth Garg · 2019
Cited alongside, same era.
Abs: Scanning neural networks for back-doors by artificial brain stimulation
Yingqi Liu, Wen-Chuan Lee, Guanhong Tao, Shiqing Ma, Yousra Aafer, and Xiangyu Zhang · 2019
Cited alongside, same era.
Defending Neural Backdoors via Generative Distribution Modeling
Ximing Qiao, Yukun Yang, and Hai Li · 2019
Cited alongside, same era.

Then

Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks
Bolun Wang, Yuanshun Yao, Shawn Shan, Huiying Li, Bimal Viswanath, Haitao Zheng, and Ben Y. Zhao · 2019
Later among the works it cites.
Poisoning the (data) well in ml-based cad: A case study of hiding lithographic hotspots
K. Liu, B. Tan, R. Karri, and S. Garg · 2020
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…