Samenvatting

Adversarial Robustness for Machine Learning summarizes the recent progress on this topic and introduces popular algorithms on adversarial attack, defense and verification. Sections cover adversarial attack, verification and defense, mainly focusing on image classification 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.

Specificaties

ISBN13:9780128240205
Taal:Engels
Bindwijze:Paperback

Lezersrecensies

Wees de eerste die een lezersrecensie schrijft!

Inhoudsopgave

1. White-box attack<br>2. Soft-label Black-box Attack<br>3. Decision-based attack<br>4. Attack Transferibility<br>5. Attacks in the physical world<br>6. Convex relaxation Framework<br>7. Layer-wise relaxation (primal algorithms)<br>8. Dual approach<br>9. Probabilistic verification<br>10. Adversarial training<br>11. Certified defense<br>12. Randomization<br>13. Detection methods<br>14. Robustness of other machine learning models beyond neural networks<br>15. NLP models<br>16. Graph neural network<br>17. Recommender systems<br>18. Reinforcement Learning<br>19. Speech models<br>20. Multi-modal models<br>21. Backdoor attack and defense<br>22. Data poisoning attack and defense<br>23. Transfer learning<br>24. Explainability and interpretability<br>25. Representation learning<br>26. Privacy and watermarking

Managementboek Top 100

Rubrieken

Populaire producten

    Personen

      Trefwoorden

        Adversarial Robustness for Machine Learning