ML AND AI - WHAT IS IT? MACHINE LEARNING Algorithmic ways to describe data Supervised
5
MACHINE LEARNING USES IN SECURITY
6
FAMOUS AI (ALGORITHM) FAILURES
7
WHAT MAKES ALGORITHMS DANGEROUS? ALGORITHMS MAKE ASSUMPTIONS ABOUT THE DATA
8
COGNITIVE BIASES
9
THE DANGERS WITH DEEP LEARNING - WHEN NOT TO USE IT
10
ADVERSARIAL MACHINE LEARNING
11
DEEP LEARNING - THE SOLUTION TO EVERYTHING
12
UNSUPERVISED TO THE RESCUE?
13
UNDERSTAND AND CLEAN THE DATA
14
ENGINEERING DISTANCE FUNCTIONS
15
CHOOSING THE RIGHT UNSUPERVISED ALGORITHM
16
CHOOSING THE CORRECT ALGORITHM PARAMETERS
17
INTERPRETING THE DATA
18
A DIFFERENT APPROACH - PROBABILISTIC INFERENCE Rather than running algorithms the model the shape of data, we need to take expert knowledge/ domain expertise into account
19
ST STEP-BUILD THE GRAPH
20
ND STEP - GROUP NODES
21
RD STEP - INTRODUCE DEPENDENCIES
22
TH STEP - ESTIMATE PROBABILITIES
23
TH STEP-GOAL COMPUTATION
24
TH STEP-OBSERVE ACTIVITIES
25
TH STEP-EXPERT INPUT Strengthen the network by introducing expert knowledge
26
BELIEF NETWORKS - SOME OBSERVATIONS
Description:
Explore the limitations and potential dangers of machine learning and artificial intelligence in cybersecurity in this Black Hat conference talk. Delve into the issues of explainability in algorithms and learn where deep learning applications may be inappropriate. Examine real-world examples demonstrating how blind application of algorithms, including deep learning, can lead to incorrect results. Discover the importance of understanding data, choosing appropriate algorithms, and incorporating expert knowledge in cybersecurity applications. Gain insights into alternative approaches like probabilistic inference and belief networks for more robust security solutions.
AI & ML in Cyber Security - Why Algorithms Are Dangerous