Lead data scientist, Kaspersky. Alexey joined Kaspersky in 2010. In his current role, he leads the Detection Methods Analysis Group (DMAG). The group researches up-to-date machine learning techniques and implements these to detect security threats. Alexey has developed a variety of models for detecting executable files, created locality-sensitive hashing for PE files, and designed models for detecting intrusion methods. He holds patents to many of these innovations. Alexey also conducts research in the field of ML model security. His expertise is backed by a Ph.D. degree in the field of mathematics and software engineering for computers, complexes, and computer networks.
2 articles
We’ve revisited our study on the crackability of real-world passwords leaked on the dark web — originally conducted two years ago. The findings are sobering: nearly every other password can be cracked in under a minute, and three out of five take less than an hour. How can we move away from insecure passwords?
Almost six out of ten passwords can be cracked in less than an hour using either a modern graphics card or cloud services. All it costs is a few dollars and some free time. How this is possible and what to do about it is the topic of our study.
passwords