research
∙
10/06/2022
On Optimal Learning Under Targeted Data Poisoning
Consider the task of learning a hypothesis class ℋ in the presence of an...
share
research
∙
02/07/2022
Deletion Inference, Reconstruction, and Compliance in Machine (Un)Learning
Privacy attacks on machine learning models aim to identify the data that...
research
∙
08/16/2021
NeuraCrypt is not private
NeuraCrypt (Yara et al. arXiv 2021) is an algorithm that converts a sens...
research
∙
05/18/2021
Learning and Certification under Instance-targeted Poisoning
In this paper, we study PAC learnability and certification under instanc...
research
∙
03/26/2020
Obliviousness Makes Poisoning Adversaries Weaker
Poisoning attacks have emerged as a significant security threat to machi...
research
∙
07/11/2019
Computational Concentration of Measure: Optimal Bounds, Reductions, and More
Product measures of dimension n are known to be concentrated in Hamming ...
research
∙
06/13/2019
Lower Bounds for Adversarially Robust PAC Learning
In this work, we initiate a formal study of probably approximately corre...
research
∙
05/29/2019
Empirically Measuring Concentration: Fundamental Limits on Intrinsic Robustness
Many recent works have shown that adversarial examples that fool classif...
research
∙
05/28/2019
Adversarially Robust Learning Could Leverage Computational Hardness
Over recent years, devising classification algorithms that are robust to...
research
∙
10/29/2018
Adversarial Risk and Robustness: General Definitions and Implications for the Uniform Distribution
We study adversarial perturbations when the instances are uniformly dist...
research
∙
10/02/2018
Can Adversarially Robust Learning Leverage Computational Hardness?
Making learners robust to adversarial perturbation at test time (i.e., e...
research
∙
09/10/2018
Multi-party Poisoning through Generalized p-Tampering
In a poisoning attack against a learning algorithm, an adversary tampers...
research
∙
09/09/2018
The Curse of Concentration in Robust Learning: Evasion and Poisoning Attacks from Concentration of Measure
Many modern machine learning classifiers are shown to be vulnerable to a...
research
∙
11/10/2017