Ahmed Frikha
Scholar

Ahmed Frikha

Google Scholar ID: NiarLswAAAAJ
Cerebras Systems Inc.
Generative MLDomain GeneralizationContinual LearningMultimodal LearningPrivacy-Preserving ML
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
219
 
H-index
7
 
i10-index
7
 
Publications
20
 
Co-authors
9
list available
Contact
No contact links provided.
Publications
6 items
PrivacyScalpel: Enhancing LLM Privacy via Interpretable Feature Intervention with Sparse Autoencoders
2025
Cited
0
One-Class Domain Adaptation via Meta-Learning
2025
Cited
0
PII-Scope: A Benchmark for Training Data PII Leakage Assessment in LLMs
arXiv.org · 2024
Cited
3
PII-Compass: Guiding LLM training data extraction prompts towards the target PII via grounding
PRIVATENLP · 2024
Cited
12
IncogniText: Privacy-enhancing Conditional Text Anonymization via LLM-based Private Attribute Randomization
arXiv.org · 2024
Cited
1
ObfuscaTune: Obfuscated Offsite Fine-tuning and Inference of Proprietary LLMs on Private Datasets
arXiv.org · 2024
Cited
0
Resume (English only)
Co-authors
9 total
Denis Krompass
Denis Krompass
Siemens AG
Volker Tresp
Volker Tresp
Ludwig-Maximilians-Universität München (LMU Munich)
Xue Jiang
Xue Jiang
Technical University of Munich
Ricardo Mendes
Ricardo Mendes
Huawei Technologies Düsseldorf GmbH
Krishna Kanth Nakka
Krishna Kanth Nakka
EPFL
Haokun Chen
Haokun Chen
Amazon | LMU Munich
Jindong Gu
Jindong Gu
Google Research & DeepMind, University of Oxford
Nassim Walha
Nassim Walha
German Cancer Research Center, Siemens AG