publications

Publications by Liv G. d'Aliberti on reinforcement learning, AI reasoning, interpretable decision-making, privacy-preserving computation, and applied machine learning.

2026

  1. Behavior-Consistent Deep Reinforcement Learning
    Marcel Hussing ,  Liv G. d’Aliberti ,  Claas Voelcker, and 2 more authors
    In Workshop on Automated Reinforcement Learning at RLC, 2026
    Accepted
  2. The Illusion of Insight in Reasoning Models
    Liv G. d’Aliberti  and  Manoel Horta Ribeiro
    In Findings of the Association for Computational Linguistics: ACL 2026, Jul 2026

2025

  1. Explainability for Unmanned Aerial Vehicle Control via Multi-Objective Reinforcement Learning
    Christian A. Clark ,  Kevin M. Albarado ,  Joshua P. Wilson, and 3 more authors
    In 2025 IEEE Aerospace Conference, Jul 2025
  2. cifar_stacked_recs.png
    BlindFL: Segmented Federated Learning with Fully Homomorphic Encryption
    E. Gronberg ,  L. d’Aliberti ,  M. Saebo, and 1 more author
    Pre-Print, Jul 2025
    Pre-print
  3. Grounded-Retrieval Adversarial Imitation Loop: Integrating Language, Agent, and World Models
    Liv G. d’Aliberti  and  Manoel Horta Ribeiro
    In NeurIPS 2025 Workshop on Bridging Language, Agent, and World Models for Reasoning and Planning, Jul 2025

2024

  1. pets.png
    Privacy-Enhancing Technologies for AI Systems: A Tutorial
    Liv Galliker d’Aliberti ,  Evan Gronberg , and  Joseph Kovba
    In Proceedings of the 10th ACM International Workshop on Security and Privacy Analytics, Porto, Portugal, Jul 2024
  2. pets.png
    Privacy-Enhancing Technologies for Artificial Intelligence-Enabled Systems
    Liv d’Aliberti ,  Evan Gronberg , and  Joseph Kovba
    arXiv preprint arXiv:2404.03509, Jul 2024
    Preprint
  3. nitro.png
    Large Language Model Inference over Confidential Data Using AWS Nitro Enclaves
    J. Miles ,  L. d’Aliberti ,  C. Renzo, and 1 more author
    AWS Machine Learning Blog, Jul 2024

2023

  1. homo.png
    Enabling Fully Homomorphic Encryption with Amazon SageMaker Endpoints for Secure, Real-Time Inferencing
    L. d’Aliberti ,  J. Kovba ,  M. Gulati, and 2 more authors
    AWS Machine Learning Blog, Jul 2023
  2. pets2.png
    Privacy-Enhancing Technologies: Protecting Data In Use
    L. d’Aliberti ,  E. Gronberg , and  J. Kovba
    Leidos Insights Blog, Jul 2023
  3. bryce.png
    Leidos Researchers Compete to Develop the Best Unmanned Surface Vessel Models
    L. d’Aliberti  and  T. Boggs
    Leidos Insights Blog, Jul 2023

2022

  1. space.png
    Preserving Patient Privacy during Computation over Shared Electronic Health Record Data
    L. d’Aliberti  and  M. Clark
    Springer Nature Journal of Medical Systems, Jul 2022
  2. hyperdim.png
    Hyperdimensional Computing Encoding Schemes for Improved Image Classification
    V. Miranda  and  L. d’Aliberti
    IEEE 2022 International Symposium on Technologies for Homeland Security, Jul 2022

2020

  1. effects.png
    Effects of a Resident-Led Subject Exam Review on Mean Scores of Internal Medicine Subject Exam: A Case-Control Study
    S. Kareff ,  L. d’Aliberti , and  N. Duong
    Med. Scie. Edu., Jul 2020
  2. clinical.jpeg
    Pre-Endoscopic Intubation for Emergent GI Bleeding Associated With Increased Adverse Outcomes
    S. Woo ,  K. Johnson ,  R. Xi, and 3 more authors
    The American Journal of Gastroenterology, Jul 2020
  3. clinical.jpeg
    S0625 Post-Procedural Outcomes After Emergent Endoscopy for GI Bleed Based on Etiology of Cirrhosis
    K. A. Johnson ,  W. D. Davis ,  K. P. Muzzi, and 3 more authors
    The American Journal of Gastroenterology, Jul 2020

2019

  1. clinical.jpeg
    Pre-Endoscopic Risk Stratification Scores Associated With Intubation for Emergent Endoscopy for Severe Gastrointestinal Hemorrhage: 520
    N. Duong ,  S. Woo ,  R. Xi, and 2 more authors
    The American Journal of Gastroenterology, Jul 2019