PulseAugur
EN
LIVE 08:17:09

New scheme Fairis combats fairness poisoning in collaborative ML

By PulseAugur Editorial · [1 sources] ·

Researchers have developed Fairis, a novel server-side reweighting scheme designed to enhance fairness and robustness in collaborative machine learning, particularly for financial institutions. This method aims to prevent fairness poisoning attacks where malicious clients manipulate group fairness metrics while maintaining accuracy. Fairis achieves this by assigning weights based on a client's local fairness score, ensuring that adversaries attempting to game the system have their influence monotonically reduced. AI

IMPACT Introduces a new method to improve fairness and security in collaborative machine learning, potentially impacting financial applications.

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

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New scheme Fairis combats fairness poisoning in collaborative ML

COVERAGE [1]

  1. arXiv cs.LG TIER_1 English(EN) · Devharsh Trivedi, Nesrine Kaaniche, Nikos Triandopoulos, Maryline Laurent, Jackson Walters ·

    Fairis: Fairness-Aware Aggregation with Provable Influence Containment against Fairness Poisoning Attacks in Collaborative Machine Learning

    arXiv:2608.06469v1 Announce Type: cross Abstract: Collaborative machine learning among financial institutions must be both group-fair and robust against deliberate adversarial manipulation. Existing fairness-aware aggregation methods remain formally vulnerable to fairness poisoni…

RELATED TOPICS