Poisoning Network Flow Classifiers
Not on the map. Why?
Abstract (arXiv)
As machine learning (ML) classifiers increasingly oversee the automated monitoring of network traffic, studying their resilience against adversarial attacks becomes critical. This paper focuses on poisoning attacks, specifically backdoor attacks, against network traffic flow classifiers. We investigate the challenging scenario of clean-label poisoning where the adversary's capabilities are constrained to tampering only with the training data - without the ability to arbitrarily modify the training labels or any other component of the training process. We describe a trigger crafting strategy that leverages model interpretability techniques to generate trigger patterns that are effective even at very low poisoning rates. Finally, we design novel strategies to generate stealthy triggers, including an approach based on generative Bayesian network models, with the goal of minimizing the conspicuousness of the trigger, and thus making detection of an ongoing poisoning campaign more challenging. Our findings provide significant insights into the feasibility of poisoning attacks on network traffic classifiers used in multiple scenarios, including detecting malicious communication and application classification.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 32 of its 97 references that are in the map. First posted on arXiv 2 Jun 2023.
Builds on
32 of 97 references.
References · 32
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
- 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
- 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,012
- 2019Modeling Tabular data using Conditional GANcited by 695
- 2018Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networkscited by 550
- 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 500
- 2018Spectral Signatures in Backdoor Attackscited by 457
- 2018Detecting Backdoor Attacks on Deep Neural Networks by Activation Clusteringcited by 429
- 2022TabDDPM: Modelling Tabular Data with Diffusion Modelscited by 373
- 2019Label-Consistent Backdoor Attackscited by 285
- 2016Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layerscited by 197
20 more
- 2021CTAB-GAN: Effective Table Data Synthesizingcited by 156
- 2022Bayesian Structure Learning with Generative Flow Networkscited by 153
- 2020Adversarial Machine Learning -- Industry Perspectivescited by 121
- 2021A survey of Bayesian Network structure learningcited by 85
- 2020Conditional Wasserstein GAN-based Oversampling of Tabular Data for Imbalanced Learningcited by 67
- 2017Mitigating Evasion Attacks to Deep Neural Networks via Region-based Classificationcited by 56
- 2020A Tutorial on Learning With Bayesian Networkscited by 56
- 2019FENCE: Feasible Evasion Attacks on Neural Networks in Constrained Environmentscited by 23
- 2020Relational Data Synthesis using Generative Adversarial Networks: A Design Space Explorationcited by 21
- 2022Machine Learning Security in Industry: A Quantitative Surveycited by 21
- 2022Jigsaw Puzzle: Selective Backdoor Attack to Subvert Malware Classifierscited by 14
- 2021Datasets are not Enough: Challenges in Labeling Network Trafficcited by 13
- 2021On the Robustness of Domain Constraintscited by 11
- 2021Launching Adversarial Attacks against Network Intrusion Detection Systems for IoTcited by 9
- 2014Intrusion Detection using Continuous Time Bayesian Networkscited by 3
- 2019On Designing Machine Learning Models for Malicious Network Traffic Classificationcited by 3
- 2020Feature Extraction for Novelty Detection in Network Trafficcited by 3
- 2021PORTFILER: Port-Level Network Profiling for Self-Propagating Malware Detectioncited by 3
- 2022CELEST: Federated Learning for Globally Coordinated Threat Detectioncited by 3
- 2022Towards Reproducible Network Traffic Analysiscited by 2
Built on by
Citing papers per year: 2024: 3.
3 papers.