← Back to all news

AI safety and alignment

Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.

17,808 stories · RSS feed

arXiv AI
Sep 15

Privacy-enhanced federated learning via asynchronous aggregation and local differential perturbation

arXiv:2609.15885v1 Announce Type: cross Abstract: This study proposes a privacy-enhanced federated learning framework to address secure collaborative training in distributed data environments. The fr...

By Zhen Zhong (Georgetown University, Washington, D.C., USA), Shini Yang (LinkedIn, CA, USA), Liesheng Wei (Shanghai Ocean University, Shanghai, China)
benchmarkssafety
More like this →
arXiv AI
Sep 15

Certifiably Interpretable Training of ReLU-MLPs for Boolean Tasks with Guaranteed Truth-Table Generalization

The paper introduces MACCHIATO, a training algorithm that builds a ReLU‑MLP from partial truth‑table data while simultaneously constructing an explicit Boolean circuit over AND, OR, and XOR gates that certifies the network’s computation. The method iteratively projects residuals onto low‑dimensional Boolean classes, compiles the resulting circuit into a ReLU‑MLP, and uses logic minimization and influence‑based variable selection to achieve a six‑layer network with provable truth‑table error bounds. Experiments on synthetic random‑junta tasks show that these certified networks outperform Adam‑trained MLPs in data‑sparse or projection‑aligned regimes and complete faster than flat ESPRESSO in certain settings.

By Hrad Ghoukasian, Anastasis Kratsios
safety
More like this →