On the Effectiveness of Defensive Distillation
Not on the map. Why?
Abstract (arXiv)
We report experimental results indicating that defensive distillation successfully mitigates adversarial samples crafted using the fast gradient sign method, in addition to those crafted using the Jacobian-based iterative attack on which the defense mechanism was originally evaluated.
Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Jul 2016.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 4; 2022: 0; 2023: 0; 2024: 2.
6 papers.
- 2021Survey: Leakage and Privacy at Inference Timecited by 44
- 2024On the Robustness of Kolmogorov-Arnold Networks: An Adversarial Perspectivecited by 11
- 2021Resilient Machine Learning for Networked Cyber Physical Systems: A Survey for Machine Learning Security to Securing Machine Learning for CPScited by 10
- 2021Robustness against Adversarial Attacks in Neural Networks using Incremental Dissipativitycited by 7
- 2024PuriDefense: Randomized Local Implicit Adversarial Purification for Defending Black-box Query-based Attackscited by 5
- 2021DiPSeN: Differentially Private Self-normalizing Neural Networks For Adversarial Robustness in Federated Learningcited by 2
- 2024On the Robustness of Kolmogorov-Arnold Networks: An Adversarial Perspective25 Aug 2024
- 2024PuriDefense: Randomized Local Implicit Adversarial Purification for Defending Black-box Query-based Attacks19 Jan 2024
- 2021Robustness against Adversarial Attacks in Neural Networks using Incremental Dissipativity25 Nov 2021
- 2021Survey: Leakage and Privacy at Inference Time4 Jul 2021
- 2021Resilient Machine Learning for Networked Cyber Physical Systems: A Survey for Machine Learning Security to Securing Machine Learning for CPS14 Feb 2021
- 2021DiPSeN: Differentially Private Self-normalizing Neural Networks For Adversarial Robustness in Federated Learning8 Jan 2021