A Short History of Learning-Based Defence

A real timeline from Paul Graham's 2002 statistical spam filter to adversarial attacks against deployed classifiers, showing that offensive and defensive machine learning milestones have always pushed each other forward.

~5 min total·4 quadrants of structured content

By the end of this topic, you will

Place at least three real, named milestones on this course's machine-learning-in-security timeline
Explain why offensive and defensive milestones in this field tend to alternate rather than one side winning permanently
Preview which later unit each timeline milestone is covered in depth

Quadrant 1 · e-Tutorial

Video lectures and walkthroughs

Video content coming soon.

Quadrant 2 · e-Content

Articles and case studies

A Short History of Learning-Based Defence

Every defensive milestone in this course's own timeline was eventually followed by an offensive one. That is not a flaw in machine learning for security, it is the same arms race security has always had, one level higher.

Quadrant 3 · Web Resources