TY - CONF AU - Jafarzadeh, Hanieh AU - Klemme, Florian AU - Amrouch, Hussam AU - Hellebrand, Sybille AU - Wunderlich, Hans-Joachim ID - 52744 T2 - European Test Symposium, The Hague, Netherlands, May 20-24, 2024 TI - Time and Space Optimized Storage-based BIST under Multiple Voltages and Variations ER - TY - CONF AU - Jafarzadeh, Hanieh AU - Klemme, Florian AU - Amrouch, Hussam AU - Hellebrand, Sybille AU - Wunderlich, Hans-Joachim ID - 52742 T2 - IEEE Latin American Test Symposium (LATS), Maceió, Brazil, April 9-12, 2024 TI - Vmin Testing under Variations: Defect vs. Fault Coverage ER - TY - CONF AU - Hellebrand, Sybille AU - Sadeghi-Kohan, Somayeh AU - Wunderlich, Hans-Joachim ID - 52743 T2 - International Symposium of EDA (ISEDA), Xi'an, China, May 10-13, 2024 TI - Functional Safety and Reliability of Interconnects throughout the Silicon Life Cycle ER - TY - CONF AU - Lebedeva, Anastasia AU - Protte, Marius AU - van Straaten, Dirk AU - Fahr, René ID - 48387 T2 - Advances in Information and Communication TI - Involvement of domain experts in the AI training does not affect adherence – An AutoML study VL - 919 ER - TY - CONF AU - Wunderlich, Hans-Joachim AU - Jafarzadeh, Hanieh AU - Hellebrand, Sybille ID - 52745 T2 - International Symposium of EDA (ISEDA), Xi’an, China, May 10-13, 2024 TI - Robust Test of Small Delay Faults under PVT-Variations ER - TY - GEN AU - Stiballe, Alisa AU - Reimer, Jan Dennis AU - Sadeghi-Kohan, Somayeh AU - Hellebrand, Sybille ID - 50284 TI - Modeling Crosstalk-induced Interconnect Delay with Polynomial Regression ER - TY - GEN AU - Ustimova, Magdalina AU - Sadeghi-Kohan, Somayeh AU - Hellebrand, Sybille ID - 51799 TI - Crosstalk-Aware Simulation of Interconnects Using Artificial Neural Networks ER - TY - JOUR AU - Harder, Hans AU - Peitz, Sebastian ID - 52758 TI - On the continuity and smoothness of the value function in reinforcement learning and optimal control ER - TY - CONF AU - Hu, Lijie AU - Habernal, Ivan AU - Shen, Lei AU - Wang, Di ED - Graham, Yvette ED - Purver, Matthew ID - 52827 T2 - Findings of the Association for Computational Linguistics: EACL 2024, St. Julian’s, Malta, March 17-22, 2024 TI - Differentially Private Natural Language Models: Recent Advances and Future Directions ER - TY - CONF AB - Neural machine translation (NMT) is a widely popular text generation task, yet there is a considerable research gap in the development of privacy-preserving NMT models, despite significant data privacy concerns for NMT systems. Differentially private stochastic gradient descent (DP-SGD) is a popular method for training machine learning models with concrete privacy guarantees; however, the implementation specifics of training a model with DP-SGD are not always clarified in existing models, with differing software libraries used and code bases not always being public, leading to reproducibility issues. To tackle this, we introduce DP-NMT, an open-source framework for carrying out research on privacy-preserving NMT with DP-SGD, bringing together numerous models, datasets, and evaluation metrics in one systematic software package. Our goal is to provide a platform for researchers to advance the development of privacy-preserving NMT systems, keeping the specific details of the DP-SGD algorithm transparent and intuitive to implement. We run a set of experiments on datasets from both general and privacy-related domains to demonstrate our framework in use. We make our framework publicly available and welcome feedback from the community. AU - Igamberdiev, Timour AU - Vu, Doan Nam Long AU - Kuennecke, Felix AU - Yu, Zhuo AU - Holmer, Jannik AU - Habernal, Ivan ED - Aletras, Nikolaos ED - De Clercq, Orphee ID - 52842 T2 - Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations TI - DP-NMT: Scalable Differentially Private Machine Translation ER -