Главная
Study mode:
on
1
Intro
2
Alex Polyakov
3
Adverse AI
4
Agenda
5
Why Secure AI
6
Confidentiality Integrity Availability
7
AI Applications
8
Who is affected
9
History of AI attacks
10
Top 10 AI attacks
11
Real applications
12
Real attacks
13
AI Red Teaming
14
Report
15
Air teaming
16
Problem
17
Attack Goal
18
Attack Form
19
Attack Actor
20
Attack Conditions
21
Attack Methods
22
Success Criteria
23
Results
24
Home Task
25
Digital Attack
26
Physical Facial Recognition
27
Goals
28
Existing research
29
Why test in the real environment
30
Device features
31
Approaches
32
Tricks
33
Example
34
Result
35
Defenses
36
The biggest problem
37
Highlevel approaches
38
Secure AI lifecycle
39
Next steps
40
Conclusion
Description:
Explore practical AI red teaming techniques in this conference talk focusing on facial recognition systems. Dive into the details of a real-world engagement testing both software and hardware solutions to identify critical vulnerabilities. Learn about the creation of an attack taxonomy and evaluation of recent approaches to compromising facial recognition algorithms. Discover insights from research conducted in authentic environments using various cameras and algorithms. Gain understanding of the prevalence of facial recognition technology, its vulnerabilities to adversarial attacks, and the cybersecurity implications. Examine the effectiveness of different attack methods, both digital and physical, against facial recognition systems. Consider defensive strategies and approaches to securing AI throughout its lifecycle. Benefit from the expertise of Alex Polyakov, a trusted AI and cybersecurity expert, as he shares findings from over 18 years of practical experience in the field.

Practical AI Red Teaming - A Facial Recognition Case Study

Hack In The Box Security Conference
Add to list
0:00 / 0:00