Unpacking Multimodal Data Leakage, Broken Benchmarks, and the Hessian Fallacy
Epistemic Status: I recently co-authored a paper on Membership Inference Attacks accepted at EACL 2026. More theoretical contributions — specifically the gradient attribution and the findings regarding the Hessian/positive-definite theories — are unpublished findings that I believe have some interest for AI Safety, Developmental Interpretability, and evaluation design. I am...
Apr 186