SPIN Unprocessed October 28, 2026 ai_technology research
Augmentation-Guided Adversarial Training via Local Stability-Based Sample Selection
View original on arxiv.orgOverview
arXiv:2610.33331v1 Announce Type: new Abstract: Adversarial training remains one of the most effective defenses against adversarial attacks, but its standard PGD-based training is computationally expensive because adversarial examples are generated for every training sample. Selective adversarial training reduces this cost by perturbing only a subset of samples. However, existing selective techniques typically rely on point-wise difficulty signals such as loss, entropy, margin, or gradients. We
SpinGraph analysis pending — check back after processing.
Ask AI about this story
Opens with the SpinGraph .md URL and structured context — one click, prompt included.
More from arXiv Machine Learning
View all →- MLIPDiff: Guiding Denoising Diffusion Models for Structure-Based Drug Design via Machine-Learned Interatomic Potentials
- When Does Pre-Trained Capacity Help Causal Learning? From Scalar Prediction to Counterfactual Post-Training
- Tree Depth and Sample-Quality-Associated Features: Two Hidden Factors in Boruta Selection for RNA-Seq Data Classification
- All-in-One: A Composable Attack on LLM Transformations
- Individual Fairness via Local Predictive Consistency
- RadonBench: A Benchmark of Classical and Learning-Guided Search Techniques for Problems in Combinatorial Geometry
Markdown (.md) · JSON-LD schema (.json) · Machine-readable for AI & GEO