# Hijacking Attacks against Neural Networks by Analyzing Training Data

arXiv: https://arxiv.org/abs/2401.09740 · HTML: https://mlsanity.com/paper/2401.09740/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Backdoor and data poisoning attacks, one of 12 directions in LLM safety and security.
- Builds on 39 of its 57 references that are in the map.
- First posted on arXiv 18 Jan 2024.

## Placed in

- LLM safety and security / [Backdoor and data poisoning attacks](https://mlsanity.com/safety/backdoor-and-data-poisoning-attacks/)

## Builds on (most cited first, 30 of 39)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification](https://mlsanity.com/paper/1909.06335/) (2019)
- [Universal adversarial perturbations](https://mlsanity.com/paper/1610.08401/) (2016)
- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks](https://mlsanity.com/paper/1805.12185/) (2018)
- [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)
- [Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks](https://mlsanity.com/paper/2101.05930/) (2021)
- [Label-Consistent Backdoor Attacks](https://mlsanity.com/paper/1912.02771/) (2019)
- [Scalable and accurate deep learning for electronic health records](https://mlsanity.com/paper/1801.07860/) (2018)
- [Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples](https://mlsanity.com/paper/2010.03593/) (2020)
- [Going Deeper in Spiking Neural Networks: VGG and Residual Architectures](https://mlsanity.com/paper/1802.02627/) (2018)
- [Fixing Data Augmentation to Improve Adversarial Robustness](https://mlsanity.com/paper/2103.01946/) (2021)
- [Feature Importance-aware Transferable Adversarial Attacks](https://mlsanity.com/paper/2107.14185/) (2021)
- [Robustness and Accuracy Could Be Reconcilable by (Proper) Definition](https://mlsanity.com/paper/2202.10103/) (2022)
- [Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch](https://mlsanity.com/paper/2106.08970/) (2021)
- [Handcrafted Backdoors in Deep Neural Networks](https://mlsanity.com/paper/2106.04690/) (2021)

## Abstract (arXiv)

Backdoors and adversarial examples are the two primary threats currently faced by deep neural networks (DNNs). Both attacks attempt to hijack the model behaviors with unintended outputs by introducing (small) perturbations to the inputs. Backdoor attacks, despite the high success rates, often require a strong assumption, which is not always easy to achieve in reality. Adversarial example attacks, which put relatively weaker assumptions on attackers, often demand high computational resources, yet do not always yield satisfactory success rates when attacking mainstream black-box models in the real world. These limitations motivate the following research question: can model hijacking be achieved more simply, with a higher attack success rate and more reasonable assumptions? In this paper, we propose CleanSheet, a new model hijacking attack that obtains the high performance of backdoor attacks without requiring the adversary to tamper with the model training process. CleanSheet exploits vulnerabilities in DNNs stemming from the training data. Specifically, our key idea is to treat part of the clean training data of the target model as "poisoned data," and capture the characteristics of these data that are more sensitive to the model (typically called robust features) to construct "triggers." These triggers can be added to any input example to mislead the target model, similar to backdoor attacks. We validate the effectiveness of CleanSheet through extensive experiments on 5 datasets, 79 normally trained models, 68 pruned models, and 39 defensive models. Results show that CleanSheet exhibits performance comparable to state-of-the-art backdoor attacks, achieving an average attack success rate (ASR) of 97.5% on CIFAR-100 and 92.4% on GTSRB, respectively. Furthermore, CleanSheet consistently maintains a high ASR, when confronted with various mainstream backdoor defenses.