Analyzing the Security of Machine Learning for Algorithmic Trading

Explore the security vulnerabilities of machine learning models in algorithmic trading systems through this 29-minute conference talk from the Toronto Machine Learning Series. Delve into the research of Avi Schwarzschild, a PhD student at the University of Maryland, as he examines the robustness of deep learning models used in automated trading. Discover new domain-specific adversarial attacks designed to exploit these systems while minimizing costs. Learn how these attacks serve as valuable tools for analyzing and evaluating the resilience of financial models. Investigate the real-world implications of adversarial traders manipulating automated systems to produce inaccurate predictions. Gain insights into the intersection of machine learning, cybersecurity, and finance, and understand the potential risks and challenges facing the future of algorithmic trading.

Analyzing the Security of ML for Algorithmic Trading