Faculty
Adam Dziedzic ist Tenure-Track Faculty am CISPA, wo er die SprintML-Gruppe mit dem Forschungsschwerpunkt „Sicheres, privates, robustes, interpretierbares und vertrauenswürdiges maschinelles Lernen“ mitleitet. Bevor er zum CISPA kam, war er Postdoktorand am Vector Institute und an der University of Toronto sowie Mitglied des CleverHans Lab unter der Betreuung von Prof. Nicolas Papernot. Er promovierte in Informatik an der University of Chicago, wo er von Prof. Sanjay Krishnan betreut wurde und sich mit der Komprimierung von Eingaben und Modellen für adaptive und robuste neuronale Netze befasste.
International Conference on Learning Representations (ICLR)
Annual Meeting of the Association for Computational Linguistics (ACL) On the Privacy Risk of In-context Learning
Privacy Enhancing Technologies Symposium (PETS) Individualized PATE: Differentially Private Machine Learning with Individual Privacy Guarantees.
IEEE European Symposium on Security and Privacy (EuroS&P) Reconstructing Individual Data Points in Federated Learning Hardened with Differential Privacy and Secure Aggregation
IEEE European Symposium on Security and Privacy (EuroS&P) When the Curious Abandon Honesty: Federated Learning Is Not Private
International Conference on Learning Representations (ICLR) Sentence Embedding Encoders are Easy to Steal but Hard to Defend
Conference on Neural Information Processing Systems (NeurIPS) Have it your way: Individualized Privacy Assignment for DP-SGD
International Conference on Machine Learning (ICML) On the Difficulty of Defending Self-Supervised Learning against Model Extraction.
International Conference on Learning Representations (ICLR) Stealing and Defending Transformer-based Encoders
International Conference on Learning Representations (ICLR) A Perturbation Analysis of Input Transformations for Adversarial Attacks