AI ethics evidence index Search
Source-linked daily record
Evidence record 4290 · automatically gathered

On the Fragility of Data Attribution When Learning Is Distributed

Data attribution has become an important component of pricing, auditing, and governance in machine learning pipelines, yet most attribution methods implicitly assume that attribution values faithfully reflect participants' contributions. We show that this assumption can fail: a single participant in a standard distributed training workflow can substantially inflate its measured attribution value while preserving global utility. Our attribution-first attack uses latent optimization to inject smal

Record details

Published: 15 May 2026
Source: arXiv
Category: Research
Topics: Regulation · Transparency
Retrieved: 14 July 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: Regulation · Shared topic: Transparency

AI Knows When It's Being Watched: Functional Strategic Action and Contextual Register Modulation in Large Language Models

arXiv · 14 May 2026

Shared topic: Regulation · Shared topic: Transparency

Mechanical Enforcement for LLM Governance:Evidence of Governance-Task Decoupling in Financial Decision Systems

arXiv · 14 May 2026

Shared topic: Regulation · Shared topic: Transparency

AI Debris: Residual Risk and the Afterlife of Failed AI Systems

arXiv · 15 May 2026

Shared topic: Regulation · Shared topic: Transparency

Formal Methods Meet LLMs: Auditing, Monitoring, and Intervention for Compliance of Advanced AI Systems

arXiv · 15 May 2026

Shared topic: Regulation · Shared topic: Transparency

Iterative Audit Convergence in LLM-Managed Multi-Agent Systems: A Case Study in Prompt-Engineering Quality Assurance

arXiv · 12 May 2026

Shared topic: Regulation · Shared topic: Transparency

Native Explainability for Bayesian Confidence Propagation Neural Networks: A Framework for Trusted Brain-Like AI

arXiv · 12 May 2026

How to cite this record

ethics.ai (15 May 2026), “On the Fragility of Data Attribution When Learning Is Distributed,” evidence record 4290, https://ethics.ai/record/4290 (originally published by arXiv).

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.