Resize-based input diversity boosts transfer attacks from standard surrogates but harms them from robust ones on ImageNet by 10.3% on average, traced to gradient alignment and mitigated by a local gradient consistency check.
Uncovering the limits of adversarial training against norm-bounded adversarial examples
9 Pith papers cite this work, alongside 144 external citations. Polarity classification is still indexing.
9
Pith papers citing it
144
external citations · external index
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
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.
Proposes spectral norm of Fisher Information Matrix as attack-agnostic robustness metric with closed-form bounds for common architectures and correlation to adversarial vulnerability.
A provable adversarial noise amplification theorem under sufficient conditions enables a custom-trained detector that identifies adversarial examples at inference time using enhanced layer-wise noise signals.
SAAD adaptively weights adversarial training samples by their transferability to the teacher, yielding higher AutoAttack robustness than prior distillation methods on CIFAR and Tiny-ImageNet without extra compute.
Nearest Neighbor Projection Removal Adversarial Training projects out inter-class dependencies in feature space during training, claims to reduce the Lipschitz constant and Rademacher complexity, and reports competitive robust accuracy on CIFAR-10, CIFAR-100, SVHN, and TinyImagenet.
TART improves clean accuracy in adversarial training by modulating perturbation bounds according to the tangential component of adversarial examples.
New adversarial surrogate losses and claimed consistency guarantees for one-stage learning-to-defer in classification and regression, with experiments suggesting improved robustness.
Thesis uses statistical mechanics to study DAM and RBM models for understanding memorization, low-dimensional learning, and adversarial robustness in neural networks.
citing papers explorer
-
The Scissors Effect: When Resize-Based Input Diversity Helps or Hurts Transfer Attacks
Resize-based input diversity boosts transfer attacks from standard surrogates but harms them from robust ones on ImageNet by 10.3% on average, traced to gradient alignment and mitigated by a local gradient consistency check.
-
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.
-
Measuring Model Robustness via Fisher Information: Spectral Bounds, Theoretical Guarantees, and Practical Algorithms
Proposes spectral norm of Fisher Information Matrix as attack-agnostic robustness metric with closed-form bounds for common architectures and correlation to adversarial vulnerability.
-
Detecting Adversarial Data via Provable Adversarial Noise Amplification
A provable adversarial noise amplification theorem under sufficient conditions enables a custom-trained detector that identifies adversarial examples at inference time using enhanced layer-wise noise signals.
-
Sample-wise Adaptive Weighting for Transfer Consistency in Adversarial Distillation
SAAD adaptively weights adversarial training samples by their transferability to the teacher, yielding higher AutoAttack robustness than prior distillation methods on CIFAR and Tiny-ImageNet without extra compute.
-
Nearest Neighbor Projection Removal Adversarial Training
Nearest Neighbor Projection Removal Adversarial Training projects out inter-class dependencies in feature space during training, claims to reduce the Lipschitz constant and Rademacher complexity, and reports competitive robust accuracy on CIFAR-10, CIFAR-100, SVHN, and TinyImagenet.
-
Improving Clean Accuracy via a Tangent-Space Perspective on Adversarial Training
TART improves clean accuracy in adversarial training by modulating perturbation bounds according to the tangential component of adversarial examples.
-
Adversarial Robustness in One-Stage Learning-to-Defer
New adversarial surrogate losses and claimed consistency guarantees for one-stage learning-to-defer in classification and regression, with experiments suggesting improved robustness.
-
Explaining Machine Learning and Memorization with Statistical Mechanics
Thesis uses statistical mechanics to study DAM and RBM models for understanding memorization, low-dimensional learning, and adversarial robustness in neural networks.