arxiv
PublishedApril 6, 2026 at 4:00 AM
—neutral
Learning the Signature of Memorization in Autoregressive Language Models
Publisher summary· verbatim
arXiv:2604.03199v1 Announce Type: cross Abstract: All prior membership inference attacks for fine-tuned language models use hand-crafted heuristics (e.g., loss thresholding, Min-K\%, reference calibration), each bounded by the designer's intuition. We introduce the first transferable learned attack,
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivReverso: Efficient Time Series Foundation Models for Zero-shot Forecasting5harxivMultinex: Lightweight Low-light Image Enhancement via Multi-prior Retinex5harxivMarket Design for AI: Beyond the Copyright Binary5harxivWho Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents5hThe Bubble Brief
WEEKLYRead membership inference insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗