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
Gradient Masking and Obfuscation Issues
Was this section helpful?
- Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples, Anish Athalye, Nicholas Carlini, David Wagner, 2018 Proceedings of the 35th International Conference on Machine Learning (ICML), Vol. 80 (PMLR) DOI: 10.5555/3305381.3305469 - A core paper that systematically identifies and categorizes gradient obfuscation as a common failure mode in many adversarial defenses. It describes adaptive attacks to bypass these defenses, influencing adversarial robustness research.
- Towards Evaluating the Robustness of Neural Networks, Nicholas Carlini, David A. Wagner, 2017 2017 IEEE Symposium on Security and Privacy (SP) (IEEE Computer Society) DOI: 10.1109/SP.2017.49 - Introduces a set of strong, optimization-based adversarial attacks (C&W attacks) designed to overcome gradient masking and other defensive strategies. This work underscored the need for rigorous, adaptive evaluation.
- Gradient Estimation for Black-Box Adversarial Attacks, Andrew Ilyas, Logan Engstrom, Anish Athalye, Jessy Lin, 2018 Proceedings of the International Conference on Machine Learning (ICML) DOI: 10.48550/arXiv.1804.08598 - Discusses techniques for estimating gradients in black-box scenarios, including Backward Pass Differentiable Approximation (BPDA), a method for creating adaptive attacks against defenses that rely on non-differentiable or gradient-masking operations.