On the Hardness of Robust Classification

09/12/2019
by   Pascale Gourdeau, et al.
0

It is becoming increasingly important to understand the vulnerability of machine learning models to adversarial attacks. In this paper we study the feasibility of robust learning from the perspective of computational learning theory, considering both sample and computational complexity. In particular, our definition of robust learnability requires polynomial sample complexity. We start with two negative results. We show that no non-trivial concept class can be robustly learned in the distribution-free setting against an adversary who can perturb just a single input bit. We show moreover that the class of monotone conjunctions cannot be robustly learned under the uniform distribution against an adversary who can perturb ω(log n) input bits. However if the adversary is restricted to perturbing O(log n) bits, then the class of monotone conjunctions can be robustly learned with respect to a general class of distributions (that includes the uniform distribution). Finally, we provide a simple proof of the computational hardness of robust learning on the boolean hypercube. Unlike previous results of this nature, our result does not rely on another computational model (e.g. the statistical query model) nor on any hardness assumption other than the existence of a hard learning problem in the PAC framework.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/23/2023

Sample Complexity of Robust Learning against Evasion Attacks

It is becoming increasingly important to understand the vulnerability of...
research
05/12/2022

Sample Complexity Bounds for Robustly Learning Decision Lists against Evasion Attacks

A fundamental problem in adversarial machine learning is to quantify how...
research
01/20/2021

From Local Pseudorandom Generators to Hardness of Learning

We prove hardness-of-learning results under a well-studied assumption on...
research
03/07/2019

Quantum hardness of learning shallow classical circuits

In this paper we study the quantum learnability of constant-depth classi...
research
06/07/2023

Free Fermion Distributions Are Hard to Learn

Free fermions are some of the best studied quantum systems. However, lit...
research
07/22/2021

Griddings of permutations and hardness of pattern matching

We study the complexity of the decision problem known as Permutation Pat...
research
05/24/2023

Adaptive Data Analysis in a Balanced Adversarial Model

In adaptive data analysis, a mechanism gets n i.i.d. samples from an unk...

Please sign up or login with your details

Forgot password? Click here to reset