# Detecting Semantic Backdoors in a Mystery Shopping Scenario

arXiv: https://arxiv.org/abs/2601.03805 · HTML: https://mlsanity.com/paper/2601.03805/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 44 of its 67 references that are in the map.
- First posted on arXiv 7 Jan 2026.

## Builds on (most cited first, 30 of 44)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks](https://mlsanity.com/paper/2003.01690/) (2020)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [How To Backdoor Federated Learning](https://mlsanity.com/paper/1807.00459/) (2018)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks](https://mlsanity.com/paper/1804.00792/) (2018)
- [STRIP: A Defence Against Trojan Attacks on Deep Neural Networks](https://mlsanity.com/paper/1902.06531/) (2019)
- [Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering](https://mlsanity.com/paper/1811.03728/) (2018)
- [Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation](https://mlsanity.com/paper/2010.16061/) (2020)
- [Hidden Trigger Backdoor Attacks](https://mlsanity.com/paper/1910.00033/) (2019)
- [Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks](https://mlsanity.com/paper/2007.02343/) (2020)
- [Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks](https://mlsanity.com/paper/2101.05930/) (2021)
- [Input-Aware Dynamic Backdoor Attack](https://mlsanity.com/paper/2010.08138/) (2020)
- [Label-Consistent Backdoor Attacks](https://mlsanity.com/paper/1912.02771/) (2019)
- [The Alignment Problem from a Deep Learning Perspective](https://mlsanity.com/paper/2209.00626/) (2022)
- [Adversarial Neuron Pruning Purifies Backdoored Deep Models](https://mlsanity.com/paper/2110.14430/) (2021)
- [Improving Robustness using Generated Data](https://mlsanity.com/paper/2110.09468/) (2021)
- [Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses](https://mlsanity.com/paper/2012.10544/) (2020)
- [Dynamic Backdoor Attacks Against Machine Learning Models](https://mlsanity.com/paper/2003.03675/) (2020)
- [Entangled Watermarks as a Defense against Model Extraction](https://mlsanity.com/paper/2002.12200/) (2020)
- [Universal Litmus Patterns: Revealing Backdoor Attacks in CNNs](https://mlsanity.com/paper/1906.10842/) (2019)
- [SPECTRE: Defending Against Backdoor Attacks Using Robust Statistics](https://mlsanity.com/paper/2104.11315/) (2021)

## Abstract (arXiv)

Detecting semantic backdoors in classification models--where some classes can be activated by certain natural, but out-of-distribution inputs--is an important problem that has received relatively little attention. Semantic backdoors are significantly harder to detect than backdoors that are based on trigger patterns due to the lack of such clearly identifiable patterns. We tackle this problem under the assumption that the clean training dataset and the training recipe of the model are both known. These assumptions are motivated by a consumer protection scenario, in which the responsible authority performs mystery shopping to test a machine learning service provider. In this scenario, the authority uses the provider's resources and tools to train a model on a given dataset and tests whether the provider included a backdoor. In our proposed approach, the authority creates a reference model pool by training a small number of clean and poisoned models using trusted infrastructure, and calibrates a model distance threshold to identify clean models. We propose and experimentally analyze a number of approaches to compute model distances and we also test a scenario where the provider performs an adaptive attack to avoid detection. The most reliable method is based on requesting adversarial training from the provider. The model distance is best measured using a set of input samples generated by inverting the models in such a way as to maximize the distance from clean samples. With these settings, our method can often completely separate clean and poisoned models, and it proves to be superior to state-of-the-art backdoor detectors as well.