AI ethics evidence index Search
Source-linked daily record
Evidence record 18264 · automatically gathered

Confusion-Geometry Rebalancing for Long-Tailed Adversarial Training

Adversarial training under long tailed distributions suffers from a dual imbalance: the class imbalance skews the training objective toward head classes, and the adversarial inner maximization may further amplify this bias. Existing methods mitigate this issue by correcting class priors or adapting class wise robust supervision, yet they treat each class in isolation and fail to identify which boundaries drive long tailed collapse. We propose a Confusion Geometry Rebalancing method (CGRm) for lo

Record details

Published: 10 August 2026
Source: arXiv cs.AI
Category: Research
Topics: Bias & fairness
Retrieved: 11 August 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

Shared topic: Bias & fairness

Agentic Harnesses: LLM-Driven Verification Layers for Robot Autonomy

arXiv · 10 August 2026

Shared topic: Bias & fairness

Fairness in Link Prediction Beyond Demographic Parity: A Reproducibility Study

arXiv fairness query · 10 August 2026

Shared topic: Bias & fairness

Procedural Fairness Failures in RLHF from Preference Averaging

arXiv fairness query · 10 August 2026

Shared topic: Bias & fairness

Beyond Binary: Continuous State Optimization with Graph-Structured Objectives

arXiv fairness query · 10 August 2026

Shared topic: Bias & fairness

FedTVD: Balancing Data Quality and Quantity for Robust Federated Learning

arXiv · 10 August 2026

Shared topic: Bias & fairness

Let's Unlearn Stereotypes Before Decision-Making: Assessing the Impact of Intrinsic Bias Mitigation on Downstream Fairness in LLMs

arXiv cs.CY · 10 August 2026

How to cite this record

ethics.ai (10 August 2026), “Confusion-Geometry Rebalancing for Long-Tailed Adversarial Training,” evidence record 18264, https://ethics.ai/record/18264 (originally published by arXiv cs.AI).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.