# Backdoor Attack against One-Class Sequential Anomaly Detection Models

arXiv: https://arxiv.org/abs/2402.10283 · HTML: https://mlsanity.com/paper/2402.10283/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 17 references that are in the map.
- First posted on arXiv 15 Feb 2024.

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

- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning](https://mlsanity.com/paper/1712.05526/) (2017)
- [MINE: Mutual Information Neural Estimation](https://mlsanity.com/paper/1801.04062/) (2018)
- [Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger](https://mlsanity.com/paper/2105.12400/) (2021)
- [LogBERT: Log Anomaly Detection via BERT](https://mlsanity.com/paper/2103.04475/) (2021)
- [Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution](https://mlsanity.com/paper/2106.06361/) (2021)
- [BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learning](https://mlsanity.com/paper/2205.13383/) (2022)
- [Marksman Backdoor: Backdoor Attacks with Arbitrary Target Class](https://mlsanity.com/paper/2210.09194/) (2022)
- [Imperceptible Backdoor Attack: From Input Space to Feature Representation](https://mlsanity.com/paper/2205.03190/) (2022)
- [Multi-Scale One-Class Recurrent Neural Networks for Discrete Event Sequence Anomaly Detection](https://mlsanity.com/paper/2008.13361/) (2020)

## Built on by (most cited first, 1 of 1)

- [BadSAD: Clean-Label Backdoor Attacks against Deep Semi-Supervised Anomaly Detection](https://mlsanity.com/paper/2412.13324/) (2024)

## Abstract (arXiv)

Deep anomaly detection on sequential data has garnered significant attention due to the wide application scenarios. However, deep learning-based models face a critical security threat - their vulnerability to backdoor attacks. In this paper, we explore compromising deep sequential anomaly detection models by proposing a novel backdoor attack strategy. The attack approach comprises two primary steps, trigger generation and backdoor injection. Trigger generation is to derive imperceptible triggers by crafting perturbed samples from the benign normal data, of which the perturbed samples are still normal. The backdoor injection is to properly inject the backdoor triggers to comprise the model only for the samples with triggers. The experimental results demonstrate the effectiveness of our proposed attack strategy by injecting backdoors on two well-established one-class anomaly detection models.