Part II — Adversarial Machine Learning
5
Adversarial Machine Learning
Safe AI for Autonomous and Agentic Systems
Download PDF
Download ePub
Twitter
Facebook
Preface
Part I — Foundations of AI Security
1
Introduction to Time Series Analysis
2
Autoregressive Moving Average (ARMA) Models
3
Deep Learning Models Overview
Part II — Adversarial Machine Learning
4
Deep Learning Models Overview
5
Adversarial Machine Learning
6
White-box Evasion Attack
7
Black-box Evasion Attack
8
Poisoning Attacks
Part III — Red Teaming Large Language Models
9
Introduction to Red Teaming AI Systems
10
Defense against evasion attacks
11
Adversarial Machine Learning in Malware
12
Fundamental of AI and Cybersecurity
13
Adversarial LLMs
14
Adversarial LLMs1
15
Fundamental of AI and Cybersecurity
16
Multi-Turn and Conversational Attacks
17
Red Teaming Methodologies
18
Red Teaming Evaluation: Metrics, Benchmarks, and Frameworks
Part IV — Defenses for Large Language Models
19
Fundamental of AI and Cybersecurity
20
Fundamental of AI and Cybersecurity
21
Fundamental of AI and Cybersecurity
22
Fundamental of AI and Cybersecurity
23
Fundamental of AI and Cybersecurity
Part V — Mechanistic Interpretability
24
Introduction to Mechanistic Interpretability
25
Defense against evasion attacks
26
White-box Evasion Attack
Part VI — AI Alignment and Safe Agents
27
Deep Learning Models Overview
28
White-box Evasion Attack
29
Fundamental of AI and Cybersecurity
30
Autoregressive Moving Average (ARMA) Models
Preface
31
Fundamental of AI and Cybersecurity
Part VII — Safe AI for Cyber-Physical Systems
32
Introduction to Time Series Analysis
33
Fundamental of AI and Cybersecurity
34
Introduction to Time Series Analysis
35
Fundamental of AI and Cybersecurity
36
Fundamental of AI and Cybersecurity
37
Fundamental of AI and Cybersecurity
Part VIII — Research, Evaluation & Reproducibility
38
Fundamental of AI and Cybersecurity
39
Deep Learning Models Overview
40
Deep Learning Models Overview
41
Defense against evasion attacks
42
Adversarial LLMs1
References
Appendices
A
Weighted least squares
B
Generalized least squares
C
Synchrony of parametric trends
D
Analysis of precipitation extremes and climate projections
E
Practice exercises
Part II — Adversarial Machine Learning
5
Adversarial Machine Learning
5
Adversarial Machine Learning
4
Deep Learning Models Overview
6
White-box Evasion Attack