"CyLab Faculty, Students to Present at the 32nd USENIX Security Symposium"

Carnegie Mellon University (CMU) faculty and students are presenting their research at the 32nd USENIX Security Symposium. The event brings together experts focused on highlighting the latest advancements in the security and privacy of computer systems and networks. CyLab has compiled a list of papers co-authored by members of the CyLab Security and Privacy Institute being presented at the event. One of the papers being presented is titled "Adversarial Training for Raw-Binary Malware Classifiers." Machine Learning (ML) models have demonstrated promise in accurately classifying raw executable files (binaries) as malicious or benign. This has resulted in the growing influence of ML-based classification methods in academic and real-world malware detection. However, previous research prompted caution by creating adversarial examples, which are variants of malicious binaries transformed in a functionality-preserving way to avoid detection. In this study, researchers explore the effectiveness of using adversarial training methods to develop malware classification models that are more robust to some advanced attacks. This article continues to discuss the CyLab research being presented at the 32nd USENIX Security Symposium.

CyLab reports "CyLab Faculty, Students to Present at the 32nd USENIX Security Symposium"