Can We Mitigate Adversarial Examples Without Affecting Model Accuracy?

Aditi Raghunathan - Tradeoffs between Robustness and AccuracyПодробнее

Adversarial Examples Improve Image RecognitionПодробнее

Eugene Vorobeychik: Adversarial Machine Learning: from Models to PracticeПодробнее

Uncertainty-aware Knowledge TracingПодробнее

Adversarial Finetuning with Latent Representation Constraint to Mitigate Accuracy-Robustness TradeoПодробнее

Lessons Learned from Evaluating the Robustness of Defenses to Adversarial ExamplesПодробнее

[ITW 2021] Towards Universal Adversarial Examples and DefensesПодробнее

Adversarial Examples for Models of CodeПодробнее

Ruth Urner | Robustness Should not be at Odds with AccuracyПодробнее

Defending Against Adversarial Model AttacksПодробнее

Adversarial Examples and Human-ML AlignmentПодробнее

1412.6572 - Explaining and Harnessing Adversarial ExamplesПодробнее

Adversarial Examples Are Not Bugs, They Are FeaturesПодробнее

Analyzing AI Model Internals for Debugging and Adversarial Sample Attack Detecti - Xiangyu ZhangПодробнее

CAP6412 21Spring-Fast is better than free: Revisiting adversarial trainingПодробнее

USENIX Security '21 - WaveGuard: Understanding and Mitigating Audio Adversarial ExamplesПодробнее

Day 41 of 100 Days of AI - Adversarial Machine LearningПодробнее

Adversarial examples for humansПодробнее

NDSS 2020 CloudLeak: Large-Scale Deep Learning Models Stealing Through Adversarial ExamplesПодробнее