How to Train your Antivirus: RL-based Hardening through the Problem-Space
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_ | 1866912016119103488 |
|---|---|
| author | Tsingenopoulos, Ilias Cortellazzi, Jacopo Bošanský, Branislav Aonzo, Simone Preuveneers, Davy Joosen, Wouter Pierazzi, Fabio Cavallaro, Lorenzo |
| author_facet | Tsingenopoulos, Ilias Cortellazzi, Jacopo Bošanský, Branislav Aonzo, Simone Preuveneers, Davy Joosen, Wouter Pierazzi, Fabio Cavallaro, Lorenzo |
| contents | ML-based malware detection on dynamic analysis reports is vulnerable to both evasion and spurious correlations. In this work, we investigate a specific ML architecture employed in the pipeline of a widely-known commercial antivirus company, with the goal to harden it against adversarial malware. Adversarial training, the sole defensive technique that can confer empirical robustness, is not applicable out of the box in this domain, for the principal reason that gradient-based perturbations rarely map back to feasible problem-space programs. We introduce a novel Reinforcement Learning approach for constructing adversarial examples, a constituent part of adversarially training a model against evasion. Our approach comes with multiple advantages. It performs modifications that are feasible in the problem-space, and only those; thus it circumvents the inverse mapping problem. It also makes possible to provide theoretical guarantees on the robustness of the model against a particular set of adversarial capabilities. Our empirical exploration validates our theoretical insights, where we can consistently reach 0% Attack Success Rate after a few adversarial retraining iterations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_19027 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | How to Train your Antivirus: RL-based Hardening through the Problem-Space Tsingenopoulos, Ilias Cortellazzi, Jacopo Bošanský, Branislav Aonzo, Simone Preuveneers, Davy Joosen, Wouter Pierazzi, Fabio Cavallaro, Lorenzo Cryptography and Security Artificial Intelligence ML-based malware detection on dynamic analysis reports is vulnerable to both evasion and spurious correlations. In this work, we investigate a specific ML architecture employed in the pipeline of a widely-known commercial antivirus company, with the goal to harden it against adversarial malware. Adversarial training, the sole defensive technique that can confer empirical robustness, is not applicable out of the box in this domain, for the principal reason that gradient-based perturbations rarely map back to feasible problem-space programs. We introduce a novel Reinforcement Learning approach for constructing adversarial examples, a constituent part of adversarially training a model against evasion. Our approach comes with multiple advantages. It performs modifications that are feasible in the problem-space, and only those; thus it circumvents the inverse mapping problem. It also makes possible to provide theoretical guarantees on the robustness of the model against a particular set of adversarial capabilities. Our empirical exploration validates our theoretical insights, where we can consistently reach 0% Attack Success Rate after a few adversarial retraining iterations. |
| title | How to Train your Antivirus: RL-based Hardening through the Problem-Space |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2402.19027 |