Research Article
Binary Black-Box Adversarial Attacks with Evolutionary Learning against IoT Malware Detection
Table 3
The evasion rate of different attack methods against different detection engines.
| | Detector | Adversarial attack methods | | DQEAF | Aut. | Our method |
| | ClamAV | 19.2% | 17.3% | 18.5% | | Cylance | 39.5% | 42.5% | 47.8% | | Endgame | 21.3% | 22.6% | 23.5% | | Trapmine | 20.6% | 18.8% | 19.2% |
|
|
