Understanding Security Threats Against Machine/Deep Learning Applications by Abraham Kang

Machine Learning is the future and in some cases the present. Most developers and hackers alike are new to this area. At first blush, machine learning looks incredibly difficult. Linear algebra, calculus, statistics, probability, and advanced mathematics. Come to my talk to get a quick understanding of neural networks and the associated hacking methods used against them: trojaning, adversarial examples, adversarial patches, data poisoning, model extraction and training data leakage. Although this talk covers a complex topic, the ideas are explained such that all levels of developers will benefit. Abraham Kang is fascinated with the nuanced details associated with machine learning algorithms, programming languages and their associated APIs. Kang has a B.S. from Cornell University. He has worked for various companies helping to drive AI, security, and development. He also worked as Principal Security Researcher for Fortify in their Software Security Research group. Prior to this, Abraham worked in application security for over 10 years. He is focused on the security around AI/ML, application, framework, blockchain smart contracts, intelligent assistants, and mobile applications and has presented his findings at Black Hat USA, DEFCON, OWASP AppSec USA, RSA USA and BSIDES