Dmitrii Korzh

3 papers · 2025–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (13)

Venues

AAAI (1) ACL (1) Interspeech (1)

Top co-authors

Ivan Oseledets (2) Elvir Karimov (2) Oleg Rogov (2) Oleg Y. Rogov (1) Elena Tutubalina (1) Mikhail Pautov (1) Danil Ivanov (1) Alexander Varlamov (1) Denis Bobkov (1) Alexey Dontsov (1)

Research topics

Artificial Intelligence (3) Core AI (3) Machine Learning (2) Security & Privacy (2) Speech & Audio (2) Analysis (2) Learning Types · Machine Learning (2) Privacy (2) Deep Learning (1) Application Areas (1) Learning Types · Deep Learning (1) Optimization & Theory (1) Recognition (1)

Keywords

adversarial robustness (1) multimodal learning (1) privacy preservation (1) machine unlearning (1) model forgetting (1) speaker recognition (1) deep learning model (1) randomized smoothing (1) robustness certification (1) gradient ascent (1) audio quality (1) voice biometrics (1) data removal (1) additive perturbation (1) multimodal unlearning (1) text unlearning (1) speaker privacy (1) visual unlearning (1) universal adversarial patch (1) speaker obfuscation (1)

Papers

Certification of Speaker Recognition Models to Additive Perturbations AAAI 2025 CLEAR: Character Unlearning in Textual and Visual Modalities ACL 2025 Novel Loss-Enhanced Universal Adversarial Patches for Sustainable Speaker Privacy Interspeech 2025