REVIEW 4 cited by
Understanding and Mitigating the Tradeoff Between Robustness and Accuracy
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
Understanding and Mitigating the Tradeoff Between Robustness and Accuracy
read the original abstract
Adversarial training augments the training set with perturbations to improve the robust error (over worst-case perturbations), but it often leads to an increase in the standard error (on unperturbed test inputs). Previous explanations for this tradeoff rely on the assumption that no predictor in the hypothesis class has low standard and robust error. In this work, we precisely characterize the effect of augmentation on the standard error in linear regression when the optimal linear predictor has zero standard and robust error. In particular, we show that the standard error could increase even when the augmented perturbations have noiseless observations from the optimal linear predictor. We then prove that the recently proposed robust self-training (RST) estimator improves robust error without sacrificing standard error for noiseless linear regression. Empirically, for neural networks, we find that RST with different adversarial training methods improves both standard and robust error for random and adversarial rotations and adversarial $\ell_\infty$ perturbations in CIFAR-10.
Forward citations
Cited by 4 Pith papers
-
Homogenization of $\ell_2$-Adversarial Training in High-Dimensions: Exact Dynamics under Stochastic Gradient Descent
Derives ODE deterministic equivalents and an adversarial homogenized SDE for SGD iterates in high-dim ℓ2-adversarial training, showing no constant learning rate ensures monotone descent for single-class adversarial le...
-
Feature-level analysis and adversarial transfer in rotationally equivariant quantum machine learning
Rotationally equivariant quantum models can rely on vulnerable invariant statistics such as ring-averaged intensities, leaving them susceptible to classical transfer attacks, but suppressing the associated symmetry se...
-
Towards Generalized Certified Robustness with Multi-Norm Training
CURE is the first multi-norm certified training method that improves union robustness across l_p norms and unseen perturbations on MNIST, CIFAR-10 and TinyImagenet.
-
CLLAP: Contrastive Learning-based LiDAR-Augmented Pretraining for Enhanced Radar-Camera Fusion
CLLAP generates LiDAR-based pseudo-radar data and applies dual-modality contrastive pretraining to boost radar-camera fusion models for 3D detection, showing gains on NuScenes and Lyft datasets.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.