Source |
InformationSecurityBuzzNews |
Identifiant |
1215370 |
Date de publication |
2019-07-19 23:33:00 (vue: 2019-07-20 02:01:44) |
Titre |
Researchers Trick AI Algorithm Into Trusting Malware |
Texte |
Security researchers at Skylight Cyber have discovered a way to bypass a Machine Learning algorithm from Cylance, inserting code from a benign file that's been previously marked as safe. The algorithm is weighted to automatically trust this code, so will mark files containing it as safe, even if they contain malware or have been identified as malicious …
The ISBuzz Post: This Post Researchers Trick AI Algorithm Into Trusting Malware |
Envoyé |
Oui |
Condensat |
algorithm appeared at skylight automatically been benign buzz bypass code contain containing cyber have cylance discovered even file files first from have identified information inserting isbuzz learning machine malicious malware mark marked post post: previously researchers safe security that trick trust trusting way weighted will |
Tags |
Malware
|
Stories |
|
Notes |
|
Move |
|