REVIEW 4 cited by
Adversarial Risk Bounds via Function Transformation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
We derive bounds for a notion of adversarial risk, designed to characterize the robustness of linear and neural network classifiers to adversarial perturbations. Specifically, we introduce a new class of function transformations with the property that the risk of the transformed functions upper-bounds the adversarial risk of the original functions. This reduces the problem of deriving bounds on the adversarial risk to the problem of deriving risk bounds using standard learning-theoretic techniques. We then derive bounds on the Rademacher complexities of the transformed function classes, obtaining error rates on the same order as the generalization error of the original function classes. We also discuss extensions of our theory to multiclass classification and regression. Finally, we provide two algorithms for optimizing the adversarial risk bounds in the linear case, and discuss connections to regularization and distributional robustness.
Forward citations
Cited by 4 Pith papers
-
Adversarial learning for nonparametric regression: Minimax rate and adaptive estimation
For smooth nonparametric regression under future X-attacks, the minimax adversarial Lq risk is the standard no-attack rate plus r^{q(1∧β)}, and a piecewise local polynomial estimator attains it.
-
Adversarial Training from Mean Field Perspective
A mean field framework for random ReLU networks yields adversarial-loss bounds and predicts that adversarial training shrinks weights, hurts vanilla depth, and is rescued by residual connections and width.
-
On the Generalization of Adversarially Trained Quantum Classifiers
For adversarially trained quantum classifiers, the excess sample complexity over standard training vanishes with input dimension for rotation embeddings under classical attacks, scales at least linearly for amplitude ...
-
Adversarially robust generalization theory via Jacobian regularization for deep neural networks
The paper derives Rademacher-complexity generalization bounds for Jacobian-regularized networks and argues the regularizer is an approximate surrogate for adversarial robustness.
Discussion (0). Continue with ORCID to comment.