# Februus: Input Purification Defense Against Trojan Attacks on Deep Neural Network Systems

arXiv: https://arxiv.org/abs/1908.03369 · HTML: https://mlsanity.com/paper/1908.03369/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Aug 2019.

## Built on by (most cited first, 27 of 27)

- [Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning](https://mlsanity.com/paper/2205.01992/) (2022)
- [BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learning](https://mlsanity.com/paper/2205.13383/) (2022)
- [Data-free Backdoor Removal based on Channel Lipschitzness](https://mlsanity.com/paper/2208.03111/) (2022)
- [Poison Ink: Robust and Invisible Backdoor Attack](https://mlsanity.com/paper/2108.02488/) (2021)
- [Simultaneously Optimizing Perturbations and Positions for Black-box Adversarial Patch Attacks](https://mlsanity.com/paper/2212.12995/) (2022)
- [Identifying a Training-Set Attack's Target Using Renormalized Influence Estimation](https://mlsanity.com/paper/2201.10055/) (2022)
- [Watermarking Graph Neural Networks based on Backdoor Attacks](https://mlsanity.com/paper/2110.11024/) (2021)
- [Defending Against Patch-based Backdoor Attacks on Self-Supervised Learning](https://mlsanity.com/paper/2304.01482/) (2023)
- [UMD: Unsupervised Model Detection for X2X Backdoor Attacks](https://mlsanity.com/paper/2305.18651/) (2023)
- [Trojan Signatures in DNN Weights](https://mlsanity.com/paper/2109.02836/) (2021)
- [Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free](https://mlsanity.com/paper/2205.11819/) (2022)
- [Jujutsu: A Two-stage Defense against Adversarial Patch Attacks on Deep Neural Networks](https://mlsanity.com/paper/2108.05075/) (2021)
- [Backdoor Attack and Defense in Federated Generative Adversarial Network-based Medical Image Synthesis](https://mlsanity.com/paper/2210.10886/) (2022)
- [Towards Effective and Robust Neural Trojan Defenses via Input Filtering](https://mlsanity.com/paper/2202.12154/) (2022)
- [Dispersed Pixel Perturbation-based Imperceptible Backdoor Trigger for Image Classifier Models](https://mlsanity.com/paper/2208.09336/) (2022)
- [Salient Conditional Diffusion for Defending Against Backdoor Attacks](https://mlsanity.com/paper/2301.13862/) (2023)
- [WaNet -- Imperceptible Warping-based Backdoor Attack](https://mlsanity.com/paper/2102.10369/) (2021)
- [Invisible Backdoor Attacks Using Data Poisoning in the Frequency Domain](https://mlsanity.com/paper/2207.04209/) (2022)
- [Influencer Backdoor Attack on Semantic Segmentation](https://mlsanity.com/paper/2303.12054/) (2023)
- [DHBE: Data-free Holistic Backdoor Erasing in Deep Neural Networks via Restricted Adversarial Distillation](https://mlsanity.com/paper/2306.08009/) (2023)
- [MISA: Online Defense of Trojaned Models using Misattributions](https://mlsanity.com/paper/2103.15918/) (2021)
- [Backdooring Explainable Machine Learning](https://mlsanity.com/paper/2204.09498/) (2022)
- [Backdoor Learning for NLP: Recent Advances, Challenges, and Future Research Directions](https://mlsanity.com/paper/2302.06801/) (2023)
- [FeSHI: Feature Map Based Stealthy Hardware Intrinsic Attack](https://mlsanity.com/paper/2106.06895/) (2021)
- [Pick your Poison: Undetectability versus Robustness in Data Poisoning Attacks](https://mlsanity.com/paper/2305.09671/) (2023)
- [Contributor-Aware Defenses Against Adversarial Backdoor Attacks](https://mlsanity.com/paper/2206.03583/) (2022)
- [Threats, Vulnerabilities, and Controls of Machine Learning Based Systems: A Survey and Taxonomy](https://mlsanity.com/paper/2301.07474/) (2023)

## Abstract (arXiv)

We propose Februus; a new idea to neutralize highly potent and insidious Trojan attacks on Deep Neural Network (DNN) systems at run-time. In Trojan attacks, an adversary activates a backdoor crafted in a deep neural network model using a secret trigger, a Trojan, applied to any input to alter the model's decision to a target prediction---a target determined by and only known to the attacker. Februus sanitizes the incoming input by surgically removing the potential trigger artifacts and restoring the input for the classification task. Februus enables effective Trojan mitigation by sanitizing inputs with no loss of performance for sanitized inputs, Trojaned or benign. Our extensive evaluations on multiple infected models based on four popular datasets across three contrasting vision applications and trigger types demonstrate the high efficacy of Februus. We dramatically reduced attack success rates from 100% to near 0% for all cases (achieving 0% on multiple cases) and evaluated the generalizability of Februus to defend against complex adaptive attacks; notably, we realized the first defense against the advanced partial Trojan attack. To the best of our knowledge, Februus is the first backdoor defense method for operation at run-time capable of sanitizing Trojaned inputs without requiring anomaly detection methods, model retraining or costly labeled data.