Скачать с ютуб RomHack 2024 - Lorenzo Cavallaro - Trustworthy AI… for Systems Security в хорошем качестве

RomHack 2024 - Lorenzo Cavallaro - Trustworthy AI… for Systems Security

Lorenzo Cavallaro Trustworthy AI… for Systems Security slides: https://romhack.io/wp-content/uploads... No day goes by without reading machine learning (ML) success stories across various application areas. Systems security is no exception, where ML’s tantalizing performance leave one to wonder whether there are any unsolved problems left. However, machine learning has no real clairvoyant abilities and once the magic wears off, we’re left in uncharted territory. Is machine learning truly capable of ensuring systems security? After sharing its foundation, in this talk, Lorenzo will illustrate some of the challenges in the context of adversarial ML evasion attacks against malware classifiers. He’ll first see that the classic formulation is ill-suited for reasoning about how to generate realizable evasive malware. Then, he’ll provide a deep dive into recent work that provides a reformulation of the problem and enables more principled attack designs and defenses. Implications are interesting, as the framework facilitates reasoning around end-to-end attacks that can generate real-world adversarial malware, at scale, that evades both vanilla and hardened classifiers, thus calling for novel defenses. Ultimately, Lorenzo’s aim is to foster a deeper understanding of machine learning’s role in systems security and its potential for future advancements. https://romhack.io/romhack-conference...