4 papers
Detection and Resolution of Periodic Artifacts in OpenDP's Discrete Laplace Sampler
Cesare Gerolimetto Fabrello, Valeria Rossi, Alberto Trombetta +1
Differential privacy implementations rely on precise sampling from noise distributions to provide formal privacy guarantees. We report the discovery of systematic artifacts in Open…
Empirical Analysis of Randomness Quality in Differential Privacy Mechanisms
Cesare Gerolimetto Fabrello, Valeria Rossi, Alberto Trombetta +1
Differential Privacy (DP) relies on carefully calibrated random noise to protect individual privacy in statistical analyses. While theoretical work has analyzed DP under weakened r…
Categorical Prior Lock-in: Why In-Context Learning Fails for Structured Data
Antonio Pelusi, Stefano Braghin, Alberto Trombetta
Large language models (LLMs) are increasingly used as conditional generators for structured data, relying on in-context learning (ICL) to adapt to new distributions without paramet…
On-line Anomaly Detection and Qualification of Random Bit Streams
Cesare Gerolimetto Fabrello, Valeria Rossi, Kamil Witek +2
Generating random bit streams is required in various applications, most notably cyber-security. Ensuring high-quality and robust randomness is crucial to mitigate risks associated…