AH
Anisa Halimi
cs.CRcs.LGcs.SIPrivacyComputer Securitycs.CYcs.DCdata preprocessingdifferential privacyFederated learning
On Valency
published · living versionsW_ebbegyeg·v1 · currentpublished
Post-Training Large Language Models with LLMON
with Basel Shbita, Michael Hind, Chad DeLuca, Nathan Fulton +6
1 version
Preprints & journals
20 papers in the corpus · 2017–2026SoK: Privacy Attacks on Machine Learning via Explainable AI2609.10627v1 · Abdullah Caglar Oksuz, Anisa Halimi, Erman Ayday2026 · 0 citationsarXiv
PrivFusion: A Privacy-preserving Multi-Agent Framework for Harmonizing Distributed Datasets2605.24249v1 · Anisa Halimi, Liubov Nedoshivina, Kieran Fraser et al.2026 · 0 citationsarXiv
Persona-Conditioned Adversarial Prompting: Multi-Identity Red-Teaming for Adversarial Discovery and Mitigation2605.11730v1 · Cristian Morasso, Anisa Halimi, Muhammad Zaid Hameed et al.2026 · 0 citationsarXiv
Persona-Conditioned Adversarial Prompting (PCAP): Multi-Identity Red-Teaming for Enhanced Adversarial Prompt Discovery2605.12565v1 · Cristian Morasso, Anisa Halimi, Muhammad Zaid Hameed et al.2026 · 0 citationsarXiv
Privacy-preserving verification of preprocessing in federated learning for genomic data.41907170 · Li, Wenbiao, Halimi, Anisa, Vaidya, Jaideep et al.2026 · 0 citationsJAMIA open. 2026;9(2):ooag040
LoMime: Query-Efficient Membership Inference using Model Extraction in Label-Only Settings2602.18934v3 · Abdullah Caglar Oksuz, Anisa Halimi, Erman Ayday2026 · 0 citationsarXiv
PQFed: A Privacy-Preserving Quality-Controlled Federated Learning Framework2509.21704v1 · Weiqi Yue, Wenbiao Li, Yuzhou Jiang et al.2025 · 0 citationsarXiv
In-Context Bias Propagation in LLM-Based Tabular Data Generation2506.09630v3 · Pol G.Recasens, Alberto Gutierrez, Jordi Torres et al.2025 · 0 citationsarXiv
Privacy-Preserving Model and Preprocessing Verification for Machine Learning2501.08236v1 · Wenbiao Li, Anisa Halimi, Xiaoqian Jiang et al.2025 · 0 citationsarXiv
Pragmatic De-Identification of Cross-Domain Unstructured Documents: A Utility-Preserving Approach with Relation Extraction Filtering.38827069 · Nedoshivina, Liubov, Halimi, Anisa, Bettencourt-Silva, Joao et al.2024 · 0 citationsAMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science. 2024;2024:85-94
FairSISA: Ensemble Post-Processing to Improve Fairness of Unlearning in LLMs2312.07420v1 · Swanand Ravindra Kadhe, Anisa Halimi, Ambrish Rawat et al.2023 · 2 citationsarXiv
Privacy preserving identification of population stratification for collaborative genomic research.37387172 · Dervishi, Leonard, Li, Wenbiao, Halimi, Anisa et al.2023 · 5 citationsBioinformatics (Oxford, England). 2023;39(39 Suppl 1):i168-i176
Facilitating Federated Genomic Data Analysis by Identifying Record Correlations while Ensuring Privacy.37128365 · Dervishi, Leonard, Wang, Xinyue, Li, Wentao et al.2023 · 12 citationsAMIA ... Annual Symposium proceedings. AMIA Symposium. 2022;2022:395-404
AUTOLYCUS: Exploiting Explainable AI (XAI) for Model Extraction Attacks against Interpretable Models2302.02162v3 · Abdullah Caglar Oksuz, Anisa Halimi, Erman Ayday2023 · 15 citationsarXiv
Federated Unlearning: How to Efficiently Erase a Client in FL?2207.05521v3 · Anisa Halimi, Swanand Kadhe, Ambrish Rawat et al.2022 · 52 citationsarXiv
ShareTrace: Contact Tracing with the Actor Model2203.12445v3 · Ryan Tatton, Erman Ayday, Youngjin Yoo et al.2022 · 1 citationarXiv
Privacy-Preserving and Efficient Verification of the Outcome in Genome-Wide Association Studies.36212774 · Halimi, Anisa, Dervishi, Leonard, Ayday, Erman et al.2026 · 15 citationsProceedings on Privacy Enhancing Technologies. Privacy Enhancing Technologies Symposium. 2022;2022(3):732-753
Efficient Quantification of Profile Matching Risk in Social Networks2009.03698v1 · Anisa Halimi, Erman Ayday2020 · 0 citationsProceedings of the 25th European Symposium on Research in Computer Security (ESORICS 2020)
Profile Matching Across Online Social Networks2008.09608v1 · Anisa Halimi, Erman Ayday2020 · 13 citationsProceedings of the 22nd International Conference on Information and Communications Security (ICICS 2020)
Profile Matching Across Unstructured Online Social Networks: Threats and Countermeasures1711.01815v1 · Anisa Halimi, Erman Ayday2017 · 6 citationsarXiv
Career total: 35 works. 20 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.