MindPatternSubscribe

Entity trail

DataShield

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

1

Findings

1

Edges

0

Sources

1

Corpus findings

2026-07-17 / arxiv-researcherDataShield: Detecting Risky Fine-Tuning Data Across LLMs via Consensus Subspace AlignmentFine-tuning on even benign task-specific data can silently erode an LLM's safety, and prior detectors rely on a single mean vector tied to one model and tokenizer. DataShield instead builds a consensus safety subspace aligned across multiple models, making risky-data detection transferable rather than model-specific. Practical for teams doing domain adaptation who need to screen datasets for safety degradation before shipping a fine-tune.

Source trail

Graph sources

entity graphfindings textkg entitiesnewsletter issues