On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “AutoAttack”

MALT Powers Up Adversarial Attackscs.LG

MALT improves adversarial attacks by targeting classes more efficiently.

problem Naive targeting of adversarial attacks based on classifier confidence.

method MALT - Mesoscopic Almost Linearity Targeting, based on medium-scale almost linearity assumptions.

result MALT wins over AutoAttack on CIFAR-100 and ImageNet datasets, five times faster.

adversarial attacks classifier confidence mesoscopic almost linearity CIFAR-100 ImageNet

2024-07-02abs ↗pdf ↗

RobustBench: a standardized adversarial robustness benchmarkcs.LG

RobustBench aims to standardize adversarial robustness evaluation in image classification.

problem Lack of systematic understanding and error-prone robustness evaluations.

method Standardized benchmark with restricted models and adaptive attacks.

result Reflects current state of the art in adversarial robustness.

adversarial robustness image classification robustness benchmark AutoAttack adaptive attacks

2020-10-19abs ↗pdf ↗

Automated Discovery of Adaptive Attacks on Adversarial Defensescs.LG

Automated discovery of adaptive attacks improves adversarial defense evaluation.

problem Challenges in reliably evaluating adversarial defenses.

method Formalizes adaptive attacks as reusable building blocks in a search space for automatic discovery.

result Our tool discovers significantly stronger attacks than AutoAttack, improving adversarial defense evaluation.

Adversarial Defenses Adaptive Attacks Automated Evaluation Search Space Adversarial Examples

2021-02-23abs ↗pdf ↗

Robustness and Accuracy Could Be Reconcilable by (Proper) Definitioncs.LG

SCORE resolves the robustness vs accuracy trade-off by redefining robust error.

problem The inherent trade-off between robustness and accuracy in adversarial training.

method SCORE defines local equivariance as the ideal robust behavior, leading to a new robust error metric.

result SCORE reconciles robustness and accuracy, improving model performance on RobustBench.

adversarial training robustness accuracy trade-off local equivariance robust error

2022-02-21abs ↗pdf ↗

Optimal Transport Regularized Divergences: Application to Adversarial Robustnesscs.LG

New method enhances adversarial robustness of deep learning models.

problem Improving the robustness of deep learning models against adversarial attacks.

method Optimal transport regularized divergences applied to distributionally robust optimization.

result Improved adversarial robustness on CIFAR-10 and CIFAR-100 datasets.

Adversarial Robustness Distributionally Robust Optimization Optimal Transport Deep Learning CIFAR-10

2023-09-07abs ↗pdf ↗

Adversarial attacks on neural networks through canonical Riemannian foliationsstat.ML

New method uses Riemannian geometry to improve neural network adversarial attacks.

problem Improving robustness of neural networks against adversarial attacks.

method Proposes a new adversarial attack using Riemannian foliation theory and curvature of data space.

result The new attack is more efficient and accurate compared to existing methods.

Adversarial attacks Neural networks Riemannian geometry Foliation theory Curvature

2022-03-02abs ↗pdf ↗