New Research: Machine Learning Classifiers Don't Need Negative Labels
John, new research has been published addressing a critical cybersecurity challenge. Security researchers typically have easy access to labeled malicious samples but lack sufficient labeled benign samples, leading to biased models when "known bad" samples are classified as malicious and everything else as benign.
Advantages from this research include: Detecting threats an average of 10 days sooner than competing technologies Implementing concepts to overcome traditional detection limitations Providing enhanced protection against malicious domains |
|
|
|
| Can't attend the event? Register anyway and we will let you know when it is available on-demand. |
|
|
|
|
