LUMIA uses per-layer linear probes on LLM activations to detect training-data membership, outperforming output-based attacks and extending to multimodal models.
In: The 2024 ACM Conference on Fairness, Accountability, and Transparency
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LUMIA: Linear probing for Unimodal and MultiModal Membership Inference Attacks leveraging internal LLM states
LUMIA uses per-layer linear probes on LLM activations to detect training-data membership, outperforming output-based attacks and extending to multimodal models.