SDM is a new staged gradient attack that reconstructs the adversarial objective around probability differences and reports stronger performance than prior methods like APGD.
DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Neural decompositionality is defined via decision-boundary semantic preservation, and language transformers largely satisfy it under SAVED while vision models often do not.
MirrorCheck detects adversarial attacks on VLMs via T2I regeneration for semantic consistency checks, using stochastic model selection and one-time perturbations for robustness against adaptive attacks.
A reproducible pipeline produces physical adversarial traffic signs that successfully attack production-grade traffic sign recognition systems in a real car under black-box conditions.
NTGA is the first clean-label generalization attack under black-box settings but is vulnerable to adversarial training and image transformations, with newer attacks outperforming it.
citing papers explorer
-
SDM: A Powerful Tool for Evaluating Model Robustness
SDM is a new staged gradient attack that reconstructs the adversarial objective around probability differences and reports stronger performance than prior methods like APGD.
-
On the Decompositionality of Neural Networks
Neural decompositionality is defined via decision-boundary semantic preservation, and language transformers largely satisfy it under SAVED while vision models often do not.
-
MirrorCheck: Efficient Adversarial Defense for Vision-Language Models
MirrorCheck detects adversarial attacks on VLMs via T2I regeneration for semantic consistency checks, using stochastic model selection and one-time perturbations for robustness against adaptive attacks.
-
Fooling a Real Car with Adversarial Traffic Signs
A reproducible pipeline produces physical adversarial traffic signs that successfully attack production-grade traffic sign recognition systems in a real car under black-box conditions.
-
SoK: A Comprehensive Analysis of the Current Status of Neural Tangent Generalization Attacks with Research Directions
NTGA is the first clean-label generalization attack under black-box settings but is vulnerable to adversarial training and image transformations, with newer attacks outperforming it.