Publications

Veronica Rammouz, Aaron Gonzalez, Carlos Cruzportillo, Adrian Tan, Nicole Beebe, Ke Yang, Anthony Rios (2026). Absolute Error is Not Enough: Ranking Model Performance without Labels to Estimate Disparities at Scale. Accepted to AACL-IJCNLP Main
Veronica Rammouz, Dorde Klisura, Ram Krishnan, Anthony Rios (2026). Embarrassingly Simple Access Control for Large Language Models. Accepted to AACL-IJCNLP Main
Xingmeng Zhao, Tongnian Wang, Dan Schumacher, Veronica Rammouz, Anthony Rios (2026). Telling Speculative Stories to Help Humans Imagine the Harms of Healthcare AI. Findings of the Association for Computational Linguistics: ACL 2026, 8476-8516
Veronica Rammouz, Joseph Khoury, Ðorđe Klisura, Morteza Safaei Pour, Mostafa Safaei Pour, Claude Fachkha, Elias Bou-Harb (2023). Helium-based IoT Devices: Threat Analysis and Internet-scale Exploitations. 19th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob).

Veronica Rammouz, Aaron Gonzalez, Carlos Cruzportillo, Adrian Tan, Nicole Beebe, Anthony Rios (2025). Can We Reliably Rank Model Performance across Domains without Labeled Data?.
Xingmeng Zhao, Dan Schumacher, Veronica Rammouz, Anthony Rios (2025). Speculative Model Risk in Healthcare AI: Using Storytelling to Surface Unintended Harms.