Advanced Adversarial Machine Learning
Chapter 1: Foundations of Adversarial ML Security
Review of Machine Learning Security Vulnerabilities
Threat Models in Machine Learning
Attack Surfaces: Training vs. Inference
Mathematical Formulation of Adversarial Examples
Taxonomy of Adversarial Attacks
Overview of Defense Strategies
Chapter 2: Advanced Evasion Attacks
Gradient-Based Attacks: FGSM, BIM, PGD Analysis
Optimization-Based Attacks: Carlini & Wagner Methods
Score-Based Attack Techniques
Decision-Based Attack Techniques
Transferability of Adversarial Examples
Attacking Ensemble Models
Implementing Evasion Attacks: Hands-on Practical
Chapter 3: Data Poisoning and Backdoor Attacks
Poisoning Attack Strategies: Availability vs Integrity
Targeted Data Poisoning Techniques
Backdoor Attack Mechanisms and Trigger Design
Clean-Label Poisoning Attacks
Analyzing Poisoning Impact on Model Training
Crafting Data Poisoning Attacks: Hands-on Practical
Chapter 4: Model Inference and Privacy Attacks
Membership Inference Attacks: Theory and Methods
Attribute Inference Techniques
Model Inversion and Reconstruction Attacks
Model Stealing: Functionality Extraction Methods
Relationship to Differential Privacy
Implementing Membership Inference: Hands-on Practical
Chapter 5: Robust Defense Mechanisms
Adversarial Training: Principles and Variations
Certified Defenses: Randomized Smoothing
Input Transformation Defenses
Gradient Masking and Obfuscation Issues
Defending Against Poisoning and Backdoors
Implementing Adversarial Training: Hands-on Practical
Chapter 6: Evaluating Model Robustness
Metrics for Adversarial Robustness
Benchmarking Tools and Frameworks
Adaptive Attacks: Evaluating Defenses Properly
Security Evaluations under Different Threat Models
Interpreting Robustness Evaluation Results
Setting up Robustness Benchmarks: Hands-on Practical
Chapter 7: Adversarial Examples in Specific Domains
Adversarial Attacks on Computer Vision Models
Generating Adversarial Text for NLP Models
Attacks on Reinforcement Learning Agents
Physical Adversarial Attacks
Domain-Specific Attack Considerations
Generating Adversarial Text: Practice
Generating Adversarial Text for NLP Models
Was this section helpful?
- Generative Adversarial Examples for Text Classification, Moustafa Alzantot, Yash Sharma, Ahmed Elgohary, Bo-Jhang Ho, Mani Srivastava, Kai-Wei Chang, 2018 EMNLP 2018 (Conference on Empirical Methods in Natural Language Processing) DOI: 10.48550/arXiv.1804.07998 - Introduces a pioneering word-level adversarial attack (TextFooler) using a genetic algorithm for synonym substitution based on word embeddings.
- Is BERT Really Robust? A Strong Baseline for Text Adversarial Attacks, Di Jin, Zhijing Jin, Joey Tianyi Zhou, Peter Szolovits, 2020 Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34 DOI: 10.48550/arXiv.1907.11932 - Presents a strong baseline attack (PWWS) for text classification, effectively leveraging contextual embeddings like BERT for more semantic-preserving word substitutions.