Giovanni Cherubin — accepted AI-conference papers

2024

Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition

Edoardo Debenedetti, Javier Rando, Daniel Paleka, Silaghi Fineas Florin, Dragos Albastroiu, Niv Cohen +15

NeurIPS 2024spotlight

Large language model systems face significant security risks from maliciously crafted messages that aim to overwrite the system's original instructions or leak private data. To study this problem, we organized a capture-the-flag competition at IEEE SaTML 2024, where the flag is a secret string in th…

Cited by 13 Source ↗PDF ↗code ↗Scholar ↗

2023

Approximating Full Conformal Prediction at Scale via Influence Functions

Javier Abad Martinez, Umang Bhatt, Adrian Weller, Giovanni Cherubin

AAAI 2023technical

Conformal prediction (CP) is a wrapper around traditional machine learning models, giving coverage guarantees under the sole assumption of exchangeability; in classification problems, a CP guarantees that the error rate is at most a chosen significance level, irrespective of whether the underlying m…

Cited by 17 Source ↗PDF ↗code ↗Scholar ↗

2021

Exact Optimization of Conformal Predictors via Incremental and Decremental Learning

Giovanni Cherubin, Konstantinos Chatzikokolakis, Martin Jaggi

ICML 2021spotlight

Conformal Predictors (CP) are wrappers around ML models, providing error guarantees under weak assumptions on the data distribution. They are suitable for a wide range of problems, from classification and regression to anomaly detection. Unfortunately, their very high computational complexity limits…

Cited by 24 Source ↗PDF ↗code ↗Scholar ↗