Model-agnostic clean-label backdoor mitigation in cybersecurity environments
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908348052406272 |
|---|---|
| author | Severi, Giorgio Boboila, Simona Holodnak, John Kratkiewicz, Kendra Izmailov, Rauf De Lucia, Michael J. Oprea, Alina |
| author_facet | Severi, Giorgio Boboila, Simona Holodnak, John Kratkiewicz, Kendra Izmailov, Rauf De Lucia, Michael J. Oprea, Alina |
| contents | The training phase of machine learning models is a delicate step, especially in cybersecurity contexts. Recent research has surfaced a series of insidious training-time attacks that inject backdoors in models designed for security classification tasks without altering the training labels. With this work, we propose new techniques that leverage insights in cybersecurity threat models to effectively mitigate these clean-label poisoning attacks, while preserving the model utility. By performing density-based clustering on a carefully chosen feature subspace, and progressively isolating the suspicious clusters through a novel iterative scoring procedure, our defensive mechanism can mitigate the attacks without requiring many of the common assumptions in the existing backdoor defense literature. To show the generality of our proposed mitigation, we evaluate it on two clean-label model-agnostic attacks on two different classic cybersecurity data modalities: network flows classification and malware classification, using gradient boosting and neural network models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_08159 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Model-agnostic clean-label backdoor mitigation in cybersecurity environments Severi, Giorgio Boboila, Simona Holodnak, John Kratkiewicz, Kendra Izmailov, Rauf De Lucia, Michael J. Oprea, Alina Cryptography and Security Machine Learning The training phase of machine learning models is a delicate step, especially in cybersecurity contexts. Recent research has surfaced a series of insidious training-time attacks that inject backdoors in models designed for security classification tasks without altering the training labels. With this work, we propose new techniques that leverage insights in cybersecurity threat models to effectively mitigate these clean-label poisoning attacks, while preserving the model utility. By performing density-based clustering on a carefully chosen feature subspace, and progressively isolating the suspicious clusters through a novel iterative scoring procedure, our defensive mechanism can mitigate the attacks without requiring many of the common assumptions in the existing backdoor defense literature. To show the generality of our proposed mitigation, we evaluate it on two clean-label model-agnostic attacks on two different classic cybersecurity data modalities: network flows classification and malware classification, using gradient boosting and neural network models. |
| title | Model-agnostic clean-label backdoor mitigation in cybersecurity environments |
| topic | Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2407.08159 |