# On Evaluating Neural Network Backdoor Defenses

arXiv: https://arxiv.org/abs/2010.12186 · HTML: https://mlsanity.com/paper/2010.12186/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Oct 2020.

## Built on by (most cited first, 4 of 4)

- [Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training](https://mlsanity.com/paper/2102.04716/) (2021)
- [Not All Poisons are Created Equal: Robust Training against Data Poisoning](https://mlsanity.com/paper/2210.09671/) (2022)
- [What Doesn't Kill You Makes You Robust(er): How to Adversarially Train against Data Poisoning](https://mlsanity.com/paper/2102.13624/) (2021)
- [On the Permanence of Backdoors in Evolving Models](https://mlsanity.com/paper/2206.04677/) (2022)

## Abstract (arXiv)

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. Finally, we layout some general guidelines to help researchers develop more robust defenses in the future and avoid common mistakes from the past.