Search Results for author:
Found 4 papers, 0 papers with code
Sample Complexity of Robust Learning against Evasion Attacks
We then focus on learning problems with distributions on the input data that satisfy a Lipschitz condition and show that robustly learning monotone conjunctions has sample complexity at least exponential in the adversary's budget (the maximum number of bits it can perturb on each input).
When are Local Queries Useful for Robust Learning?
We finish by giving robust learning algorithms for halfspaces on $\{0, 1\}^n$ and then obtaining robustness guarantees for halfspaces in $\mathbb{R}^n$ against precision-bounded adversaries.
Sample Complexity Bounds for Robustly Learning Decision Lists against Evasion Attacks
A fundamental problem in adversarial machine learning is to quantify how much training data is needed in the presence of evasion attacks.
On the Hardness of Robust Classification
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).
