News

Check out our new preprint Low-rank fine-tuning for LLMs: A fairness perspective ! In this paper we analyzed the effects of Low Rank fine-tuning (LoRA) on the fairness and bias of Large Language Models (LLMs).

Our paper Beyond the Norms: Detecting Prediction Errors in Regression Models was accepted to appear as a spotlight at the Forty-first International Conference on Machine Learning (ICML 2024)! In this paper we propose a framework to evaluate uncertainty in regression models!

Our paper Disparate Impact on Group Accuracy of Linearization for Private Inference was accepted to appear at the Forty-first International Conference on Machine Learning (ICML 2024)! In this paper we analyzed the effects on Fairness due to ReLU budgeting for Private Inference speedup.

Check out our new preprint Disparate Impact on Group Accuracy of Linearization for Private Inference! In this paper we analyzed the effects on Fairness due to ReLU budgeting for Private Inference speedup.

Our new paper On the (In)feasibility of ML Backdoor Detection has been accepted to appear at AISTATS 2024. In this paper we propose a theoretical framework that encompasses the problems of Backdoor and OOD detection, showing for the first time their intrinsic limitation which results in a ground breaking infeasibility theorem.

Our new paper Optimal Zero-Shot Detector for Multi-Armed Attacks has been accepted to appear at AISTATS 2024. In this paper we propose a minimum-regret optimal framework to aggregate adverarial attack detectors to minimize the worst-case risk.

Our new paper Retrieval-Guided Reinforcement Learning for Boolean Circuit Minimization has been accepted to appear at ICLR 2024. In this paper we proposed an OOD detection based strategy to inform the reward function for policies in RL, with specific applications to secure automated hardware design.

Our new paper A Data-Driven Measure of Relative Uncertainty for Misclassification Detection has been accepted to appear at ICLR 2024. In this paper we proposed a data-driven method, powered by a statistical diversity and dissimilarity metric, to detect incorrect classification at test time by assessing the uncertainty of a given model.

Our new paper MEAD: A Multi-Armed Approach for Evaluation of Adversarial Examples Detectors, which sets up a new evaluation framework for adversarial example detection mechanisms, has been accepted to appear at ECMLPKDD 2022.

I am excited to start a new position as Research Associate at NYU Tandon School of Engineering: Electrical and Computer Engineering.

I have been awarded the 2021 UFI/UIF Vinci best thesis award.

Our recent paper DOCTOR: A Simple Method for Detecting Misclassification Errors has been accepted as a spotlight presentation @ NeurIPS 2021. A huge congrats to my main coauthors: Pablo Piantanida who brilliantly supervised the project from the very beginning to the end, and Federica Granese whom I have been collaborating with since the beginning of my postdoc.

My Ph.D. thesis is online.

On November 11th, 2020 I will present the work Estimating g-Leakage via Machine Learning @ ACM CCS 2020. Stay tuned!