arXiv Machine Learning
On the Existence of Consistent Adversarial Attacks in High-Dimensional Linear Classification
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
4d ago
Exposing Vulnerability Monoculture Through Systemic Adversarial Robustness
arXiv:2610.27353v1 Announce Type: cross Abstract: Beneath the apparent diversity of foundation models lies an increasingly homogeneous technical stack of common training pipelines, distillation metho...
arXiv Machine Learning
Jun 26
The Role of Input Dimensionality in the Emergence and Targeted Control of Adversarial Examples
arXiv:2606. 26207v1 Announce Type: cross Abstract: Several theoretical works have tried to explain the adversarial vulnerability of deep neural networks through properties of high-dimensional geometry.
arXiv Machine Learning
Jul 7
Robustness Meets Uncertainty: Evidential Adversarial Training for Robust Selective Classification
arXiv:2607. 03075v1 Announce Type: new Abstract: Safety-critical applications require classifiers that are both robust and reliable.
arXiv AI
4d ago
Adversarial Benchmarks and BenchDoor Attacks: Exploiting Benchmark Incentives for Backdoor Attacks
arXiv:2610.27533v1 Announce Type: cross Abstract: Machine learning benchmarks act as guideposts for model development and spur the creation of training datasets intended to improve benchmark scores....
arXiv Machine Learning
Jun 26
Over-parameterization and Adversarial Robustness in Neural Networks: An Overview and Empirical Analysis
arXiv:2406. 10090v3 Announce Type: replace Abstract: Thanks to their extensive capacity, over-parameterized neural networks exhibit superior predictive capabilities and generalization.
arXiv Machine Learning
Jun 11
Categorical Robustness Assessment for Machine Learning based Network Intrusion Detection Systems
arXiv:2606. 12075v1 Announce Type: cross Abstract: Network Intrusion Detection Systems (NIDS) heavily utlize Machine Learning (ML) but ML models can be manipulated via adversarial attacks.