Paper

A prior-free blind detection of information leakage from model predictions

Unreadunread

AI summary

arXiv:2606. 11267v1 Announce Type: new Abstract: Data leakage -- contamination of a model with information unavailable at baseline -- is the dominant reproducibility failure in machine-learning-based science, yet detection tools require training code, external data, or domain expertise.

Reading status

Priority

About this paper

Authors: Laurence A. Jacobs
Released: 2026-06-12 (27d ago)
Topic: Related to current project
Relation to my work: Read next because A prior-free blind detection of information leakage from model predictions overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: code, strong, class, under, line, rate, alone, leakage. Source: arxiv cs.LG (Machine Learning).
arXiv: 2606.11267

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to A prior-free blind detection of information leakage from model predictions. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.