New DR-IS method boosts ML robustness against adversarial label corruption

Researchers have developed a new sub-sampling method called Disagreement-Regularized Importance Sampling (DR-IS) to improve robustness against adversarial label corruption in machine learning. This method leverages the disagreement in loss rankings across independent proxy ensembles to identify and down-weight corrupted data points. DR-IS provides theoretical guarantees on sample concentration and contamination bounds, demonstrating empirical superiority over magnitude-based methods like EL2N, particularly under targeted attacks. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Enhances machine learning model reliability by providing a robust method to handle noisy or intentionally corrupted labels.

RANK_REASON The cluster contains an academic paper detailing a new method for machine learning robustness. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• Disagreement-Regularized Importance Sampling
• Importance Sampling
• Adversarial Label Corruption
• Error L2-norm
• Area Under the Margin ranking

• paper
• safety