Adversarial Robustness for Machine Learning summarizes the recent progress on this topic and introduces popular algorithms on adversarial attack, defense and veri?cation. Sections cover adversarial attack, veri?cation and defense, mainly focusing on image classi?cation applications which are the standard benchmark considered in the adversarial robustness community. Other sections discuss adversarial examples beyond image classification, other threat models beyond testing time attack, and applications on adversarial robustness. For researchers, this book provides a thorough literature review that summarizes latest progress in the area, which can be a good reference for conducting future research. In addition, the book can also be used as a textbook for graduate courses on adversarial robustness or trustworthy machine learning. While machine learning (ML) algorithms have achieved remarkable performance in many applications, recent studies have demonstrated their lack of robustness against adversarial disturbance. The lack of robustness brings security concerns in ML models for real applications such as self-driving cars, robotics controls and healthcare systems. Summarizes the whole field of adversarial robustness for Machine learning models Provides a clearly explained, self-contained reference Introduces formulations, algorithms and intuitions Includes applications based on adversarial robustness INDICE: 1. White-box attack2. Soft-label Black-box Attack3. Decision-based attack4. Attack Transferibility5. Attacks in the physical world6. Convex relaxation Framework7. Layer-wise relaxation (primal algorithms)8. Dual approach9. Probabilistic veri?cation10. Adversarial training11. Certi?ed defense12. Randomization13. Detection methods14. Robustness of other machine learning models beyond neural networks15. NLP models16. Graph neural network17. Recommender systems18. Reinforcement Learning19. Speech models20. Multi-modal models21. Backdoor attack and defense22. Data poisoning attack and defense23. Transfer learning24. Explainability and interpretability25. Representation learning26. Privacy and watermarking
- ISBN: 978-0-12-824020-5
- Editorial: Academic Press
- Encuadernacion: Rústica
- Páginas: 425
- Fecha Publicación: 01/09/2022
- Nº Volúmenes: 1
- Idioma: Inglés