3 papers
cs.LG2026
Compression Footprints as Security Signals for Model-Poisoning Defense in Federated Learning
Sachi Shome, William Eiers
Lossy compression is widely used in Federated Learning (FL) but is generally treated as an error source, while conventional poisoning defenses inspect update geometry. In this work…
cs.CE2026
VeriFin: A Neurosymbolic Framework for Verifying LLM-Generated Financial Claims
Bethel Hall, Sachi Shome, William Eiers
Large Language Models (LLMs) are being adopted in financial workflows, where accuracy and reliability are critical. One such application is financial question answering over public…
cs.SE2026
AutoCedar: An Agentic Framework for Verifier-Guided Access Control Policy Synthesis
Adarsh Vatsa, Sachi Shome, Yingming Zhou +1
Large Language Models are increasingly used to turn natural-language requirements into code. In access control, that shortcut is dangerous: a generated policy can compile and read…