Defensive Distillation is Not Robust to Adversarial Examples

We show that defensive distillation is not secure: it is no more resistant to targeted misclassification attacks than unprotected neural networks.

cs.CR cs.CV Computer Science Mathematics

Paper

Similar papers

Towards Evaluating the Robustness of Neural NetworksNicholas Carlini, D. Wagner2016 · IEEE Symposium on Security and Privacy · 10k citations In Library

Towards Evaluating the Robustness of Neural NetworksNicholas Carlini, David Wagner2017 In Library

Extending Defensive DistillationNicolas Papernot, P. Mcdaniel2017 · arXiv.org · 124 citations In Library

Distillation as a Defense to Adversarial Perturbations against Deep Neural NetworksNicolas Papernot, P. Mcdaniel, Xi Wu et al.2015 · IEEE Symposium on Security and Privacy · 3.3k citations In Library

Evaluating Defensive Distillation For Defending Text Processing Neural Networks Against Adversarial ExamplesMarcus Soll, T. Hinz, S. Magg et al.2019 · International Conference on Artificial Neural Networks · 25 citations In Library

Enhanced Attacks on Defensively Distilled Deep Neural NetworksYujia Liu, Weiming Zhang, Shaohua Li et al.2017 · arXiv.org · 6 citations In Library

Advanced defensive distillation with ensemble voting and noisy logitsYuting Liang, Reza Samavi2022 · Applied Intelligence · 10 citations In Library

Denoising Autoencoder-Based Defensive Distillation as an Adversarial Robustness Algorithm Against Data Poisoning AttacksBakary Badjie, José Cecílio, António Casimiro2024 · ACM SIGAda Ada Letters In Library

Denoising Autoencoder-based Defensive Distillation as an Adversarial Robustness AlgorithmBakary Badjie, José Cecílio, António Casimiro2023 · arXiv (Cornell University) · 9 citations In Library

Improving Defensive Distillation using Teacher AssistantManiratnam Mandal, Suna Gao2023 · arXiv (Cornell University) In Library

Source of record

arXiv

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal