THE STATE OF
AI-ASSISTED FUZZING &
Fuzzing and program analysis are a security professional’s bread and butter. The faster we are able to find bugs in software, the more effectively we are able to secure systems. However, system and code complexity has been exponentially increasingly over time, and exhaustively analyzing programs is becoming an intractable task. In this talk, I analyze 10 of the most exciting research papers published in the last few years and try to identify trends of how this field is progressing. I will show that AI-assisted program analysis is the only way forward, and share some ideas of where the field is heading in the future.
ABOUT CLARENCE CHIO
Clarence Chio is an engineer and entrepreneur who has given talks, workshops, and trainings on machine learning and security at DEF CON, BLACK HAT, RSA, and other security/software engineering conferences/meetups across two dozen countries. He is a co-author of the O'Reilly Book "Machine Learning & Security", and teaches a course on machine learning at U.C. Berkeley. Clarence graduated from the Computer Science from Stanford University, specializing in data mining and artificial intelligence.