FairSISA: Ensemble Post-Processing to Improve Fairness of Unlearning in LLMs
- 2023
- NeurIPS 2023
Publications
This is our catalog of publications authored by IBM researchers, in collaboration with the global research community. It’s an ever-growing body of work that shows why IBM is one of the most important contributors to modern computing.
Date
Featured collections
Popular topics
48 results for Nathalie Baracaldo
Benchmarking the Effect of Poisoning Defenses on the Security and Bias of Deep Learning Models
- Nathalie Baracaldo Angel
- Farhan Ahmed
- et al.
- 2023
- S&P 2023
Benchmarking the Effect of Poisoning Defenses on the Security and Bias of the Final Model
- 2022
- NeurIPS 2022
Federated Unlearning: How to Efficiently Erase a Client in FL?
- 2022
- ICML 2022
FLoRA: Single-shot Hyper-parameter Optimization for Federated Learning
- Yi Zhou
- Parikshit Ram
- et al.
- 2021
- NeurIPS 2021
Reconciling end-to-end confidentiality and data reduction in cloud storage
- Nathalie Baracaldo
- Elli Androulaki
- et al.
- 2014
- CCS 2014
Federated Learning: Recent Advances and New Challenges
- 2022
- NeurIPS 2022
Machine Learning Security and Privacy
- Nathalie Baracaldo
- Alina Oprea
- 2021
- IEEE Security and Privacy
WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models
- Jinghan Jia
- Jiancheng Liu
- et al.
- 2024
- NeurIPS 2024
Enhancing In-context Learning via Linear Probe Calibration
- Momin Abbas
- Yi Zhou
- et al.
- 2024
- AISTATS 2024