# Defending Against Stealthy Backdoor Attacks

arXiv: https://arxiv.org/abs/2205.14246 · HTML: https://mlsanity.com/paper/2205.14246/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 16 references that are in the map.
- First posted on arXiv 27 May 2022.

## Builds on (most cited first, 10 of 10)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [Weight Poisoning Attacks on Pre-trained Models](https://mlsanity.com/paper/2004.06660/) (2020)
- [ONION: A Simple and Effective Defense Against Textual Backdoor Attacks](https://mlsanity.com/paper/2011.10369/) (2020)
- [A backdoor attack against LSTM-based text classification systems](https://mlsanity.com/paper/1905.12457/) (2019)
- [Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger](https://mlsanity.com/paper/2105.12400/) (2021)
- [BadNL: Backdoor Attacks against NLP Models with Semantic-preserving Improvements](https://mlsanity.com/paper/2006.01043/) (2020)
- [Marian: Fast Neural Machine Translation in C++](https://mlsanity.com/paper/1804.00344/) (2018)
- [Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models](https://mlsanity.com/paper/2103.15543/) (2021)

## Built on by (most cited first, 2 of 2)

- [BadEdit: Backdooring large language models by model editing](https://mlsanity.com/paper/2403.13355/) (2024)
- [A Survey on Backdoor Attack and Defense in Natural Language Processing](https://mlsanity.com/paper/2211.11958/) (2022)

## Abstract (arXiv)

Defenses against security threats have been an interest of recent studies. Recent works have shown that it is not difficult to attack a natural language processing (NLP) model while defending against them is still a cat-mouse game. Backdoor attacks are one such attack where a neural network is made to perform in a certain way on specific samples containing some triggers while achieving normal results on other samples. In this work, we present a few defense strategies that can be useful to counter against such an attack. We show that our defense methodologies significantly decrease the performance on the attacked inputs while maintaining similar performance on benign inputs. We also show that some of our defenses have very less runtime and also maintain similarity with the original inputs.