Machine_Learning_for_InfoSec.pdf

Transcript

1. Machine Learning for InfoSec Tanisha R. Bhayani (Associate AI Researcher @F(x) Data Labs Pvt Ltd)
2. Basics of Machine Learning
3. “Today's AI is about new ways of connecting people to computers, people to knowledge, people to the physical world, and people to people” — Patrick Winston, MIT AI Lab briefing, 1997
4. Machine Learning, Artificial Intelligence, Data Science
5. What is Machine Learning?
6. “In the early days, back in the 50s, leading figures like Von Neumann and Turing didn’t believe in Symbolic AI. They were far more inspired by the brain. Unfortunately, they both died very young and their voice wasn’t heard.” - Geoffrey Hinton in Heroes of Deep Learning
7. What is Artificial Intelligence?
8. Data Scientist skill set
10. Supervised Learning 1. Machine learning type based on what it learns and what kind of data is used to learn it. 2. Tries to capture the causality between the input variables and output variables. 3. Requires training features and labels.
11. Regression • Mapping of independent variables to the dependent variable. • Independent variable -> features • Dependent variable -> labels
12. Gradient Descent
13. Cost Function A function that maps an event or values of one or more variables onto a real number intuitively representing some “cost” associated with the event. (Wikipedia) Examples are MSE, Cross Entropy, KL Divergence, Hinge, MAE
14. Linear Regression Cost Function
15. Logistic Regression
16. “When we’re learning to see, nobody’s telling us what the right answers are — we just look. Every so often, your mother says “that’s a dog”, but that’s very little information. You’d be lucky if you got a few bits of information — even one bit per second — that way. The brain’s visual system has 10¹⁴ neural connections. And you only live for 10⁹ seconds. So it’s no use learning one bit per second. You need more like 10⁵ bits per second. And there’s only one place you can get that much information: from the input itself.” — Geoffrey Hinton, 1996
17. Neural Networks • Connectionistic approach to computation • Uses a mathematical or computational model for information processing • Learns by changing the strength of the connections • Perceptrons • Deep Neural Networks
18. “Our intelligence is what makes us human, and AI is an extension of that quality.” – Yann LeCun
19. MNIST: http://yann.lecun.com/exdb/mnist/ Code: https://github.com/RoshanTanisha/MNIST_ALL URL Classification: https://archive.ics.uci.edu/ml/datasets/URL+Reputation Code: https://github.com/RoshanTanisha/url-classification
20. Thank You!