Publications

18 results for Anisa Halimi

Persona-Conditioned Adversarial Prompting (PCAP): Multi-Identity Red-Teaming for Enhanced Adversarial Prompt Discovery
- - Cristian Morasso
  - Anisa Halimi
  - et al.
- 2026
- ICML 2026
Workshop paper
PrivFusion: A Privacy-preserving Multi-Agent Framework for Harmonizing Distributed Datasets
- - Anisa Halimi
  - Liubov Nedoshivina
  - et al.
- 2026
- CBMS 2026
Conference paper
In-Context Bias Propagation in LLM-Based Tabular Data Generation
- - Pol Garcia Recasens
  - Alberto Gutierrez-torre
  - et al.
- 2025
- ICML 2025
Workshop paper
AUTOLYCUS: Exploiting Explainable Artificial Intelligence (XAI) for Model Extraction Attacks against Interpretable Models
- - Abdullah Caglar Oksuz
  - Anisa Halimi
  - et al.
- 2024
- PETS 2024
Conference paper
Privacy-Preserving Verification of Preprocessing in Machine Learning Models
- - Wenbiao Li
  - Anisa Halimi
  - et al.
- 2024
- PETS 2024
Poster
Data Forging Is Harder Than You Think
- - Mohamed Suliman
  - Swanand Ravindra Kadhe
  - et al.
- 2024
- ICLR 2024
Workshop paper
AI-driven Workload Management in Meta OS
- - Liubov Nedoshivina
  - Killian Levacher
  - et al.
- 2024
- EuroSys 2024
Workshop paper
Pragmatic De-Identification of Cross-Domain Unstructured Documents: A Utility-Preserving Approach with Relation Extraction Filtering
- - Liubov Nedoshivina
  - Anisa Halimi
  - et al.
- 2024
- AMIA Informatics Symposium 2024
Talk
FairSISA: Ensemble Post-Processing to Improve Fairness of Unlearning in LLMs
- - Swanand Ravindra Kadhe
  - Anisa Halimi
  - et al.
- 2023
- NeurIPS 2023
Workshop paper
Re-evaluating the Privacy Benefit of Federated Learning
- - Mohamed Suliman
  - Douglas Leith
  - et al.
- 2023
- ECML PKDD 2023
Workshop paper