SDM is a new staged gradient attack that reconstructs the adversarial objective around probability differences and reports stronger performance than prior methods like APGD.
Towards Evaluating the Robustness of Neural Networks
6 Pith papers cite this work. Polarity classification is still indexing.
6
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.
LiDAR-Adv generates adversarial objects to fool LiDAR-based autonomous driving detection systems, tested on Baidu Apollo and with physical 3D prints.
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.
Longitudinal evaluation over yearly Android app slices shows temporal drift reduces adversarial robustness of malware detectors, with expanding-window retraining providing partial mitigation but not full recovery.
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.
-
Adversarial Objects Against LiDAR-Based Autonomous Driving Systems
LiDAR-Adv generates adversarial objects to fool LiDAR-based autonomous driving detection systems, tested on Baidu Apollo and with physical 3D prints.
-
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.
-
Adversarial Vulnerability Under Temporal Concept Drift: A Longitudinal Study of Android Malware Detection
Longitudinal evaluation over yearly Android app slices shows temporal drift reduces adversarial robustness of malware detectors, with expanding-window retraining providing partial mitigation but not full recovery.
-
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.