Skip to content
conftrace_

Adam Dziedzic

26 papers · 2019–2026 · 6 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 ↓
+13 more ↓ πŸ—ΊοΈ Taxonomy Completionist (43) 🌍 Conference Polyglot Β· Silver πŸƒ Academic Marathon Β· Sprint πŸŒ‰ Interdisciplinary Bridge Β· Silver 🐣 Hot Topic Early Bird
πŸ† Grand Slam πŸ”¬ Deep Specialist (14) πŸ‘‘ Triple Crown 🧬 Topic Evolution πŸ† Keyword Champion (3) 🧭 Keyword Pioneer 🀝 Dynamic Duo (19) 🌈 Renaissance Researcher (5) πŸ”₯ Unstoppable Β· Bronze ❓ The Questioner ⚑ Prolific Year Β· Productive πŸ’Ž Century Club Β· Bronze πŸ—ƒοΈ Keyword Collector (112)

Venues

NeurIPS (9) ICLR (6) ICML (5) AAAI (4) ACL (1) CVPR (1)

Top co-authors

Franziska Boenisch (19) Nicolas Papernot (9) Muhammad Ahmad Kaleem (5) Michael Backes (5) Jan DubiΕ„ski (4) Christopher A. Choquette-Choo (3) Wenhao Wang (3) Pratyush Maini (2) Tom Blanchard (2) Somesh Jha (2)

Research topics

Machine Learning (24) Application Areas (21) Artificial Intelligence (12) Deep Learning (11) Core AI (11) Learning Types Β· Machine Learning (10) Security & Privacy (6) Models (6) Architectures (4) Core Methods (4) Optimization & Theory (4) Computer Vision (3) Natural Language Processing (3) Differential Privacy (3) Learning Types Β· Deep Learning (3)

Keywords

differential privacy (7) diffusion model (6) dataset inference (5) self-supervised learning (4) large language model (4) membership inference (3) federated learning (3) representation learning (3) model extraction (3) privacy-utility trade-off (3) membership inference attack (2) transfer learning (2) model stealing (2) memorization localization (2) image generation (2) convolutional neural network (2) privacy budget (2) secure multi-party computation (2) adversarial attack (2) intellectual property (2)

Papers

Beautiful Images, Toxic Words: Understanding and Addressing Offensive Text in Generated Images AAAI 2026 Demystifying Foreground-Background Memorization in Diffusion Models AAAI 2026 On Stealing Graph Neural Network Models AAAI 2026 Captured by Captions: On Memorization and its Mitigation in CLIP Models ICLR 2025 CDI: Copyrighted Data Identification in Diffusion Models CVPR 2025 Differentially Private Federated Learning with Time-Adaptive Privacy Spending ICLR 2025 Differentially Private Prototypes for Imbalanced Transfer Learning AAAI 2025 Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs ICML 2025 Precise Parameter Localization for Textual Generation in Diffusion Models ICLR 2025 Privacy Attacks on Image AutoRegressive Models ICML 2025 Unlocking Post-hoc Dataset Inference with Synthetic Data ICML 2025 Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models NeurIPS 2024 LLM Dataset Inference: Did you train on my dataset? NeurIPS 2024 Localizing Memorization in SSL Vision Encoders NeurIPS 2024 Memorization in Self-Supervised Learning Improves Downstream Generalization ICLR 2024 Open LLMs are Necessary for Current Private Adaptations and Outperform their Closed Alternatives NeurIPS 2024 Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders NeurIPS 2023 Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models NeurIPS 2023 Have it your way: Individualized Privacy Assignment for DP-SGD NeurIPS 2023 Robust and Actively Secure Serverless Collaborative Learning NeurIPS 2023 Dataset Inference for Self-Supervised Models NeurIPS 2022 Increasing the Cost of Model Extraction with Calibrated Proof of Work ICLR 2022 On the Difficulty of Defending Self-Supervised Learning against Model Extraction ICML 2022 CaPC Learning: Confidential and Private Collaborative Learning ICLR 2021 Pretrained Transformers Improve Out-of-Distribution Robustness ACL 2020 Band-limited Training and Inference for Convolutional Neural Networks ICML 2019