7 papers
Safe Language Generation in the Limit
Antonios Anastasopoulos, Giuseppe Ateniese, Evgenios M. Kornaropoulos
Recent results in learning a language in the limit have shown that, although language identification is impossible, language generation is tractable. As this foundational area expa…
TENNOR: Trustworthy Execution for Neural Networks through Obliviousness and Retrievals
Zifan Qu, Vasileios P. Kemerlis, Giuseppe Ateniese +1
Training wide neural networks on sensitive data in untrusted cloud environments requires simultaneously achieving computational efficiency and rigorous privacy guarantees. Sparsifi…
How Query Distribution Knowledge Breaks Multidimensional Encrypted Range Queries, With Guarantees
Daniel Blackley, Nathaniel Moyer, Charalampos Papamanthou +1
In this work, we show how knowledge of the query distribution, combined with access-pattern leakage, is sufficient to break multi-dimensional encrypted range queries, with provable…
Exposing Privacy Risks in Anonymizing Clinical Data: Combinatorial Refinement Attacks on k-Anonymity Without Auxiliary Information
Somiya Chhillar, Mary K. Righi, Rebecca E. Sutter +1
Despite longstanding criticism from the privacy community, k-anonymity remains a widely used standard for data anonymization, mainly due to its simplicity, regulatory alignment, an…
When AIOps Become "AI Oops": Subverting LLM-driven IT Operations via Telemetry Manipulation
Dario Pasquini, Evgenios M. Kornaropoulos, Giuseppe Ateniese +3
AI for IT Operations (AIOps) is transforming how organizations manage complex software systems by automating anomaly detection, incident diagnosis, and remediation. Modern AIOps so…
LLMmap: Fingerprinting For Large Language Models
Dario Pasquini, Evgenios M. Kornaropoulos, Giuseppe Ateniese
We introduce LLMmap, a first-generation fingerprinting technique targeted at LLM-integrated applications. LLMmap employs an active fingerprinting approach, sending carefully crafte…