← authors · overview

• Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise
  2022 · 105 citations
• Certified Defenses for Adversarial Patches
  2020 · 79 citations
• Stacked U-Nets: A No-Frills Approach to Natural Image Segmentation
  2018 · 33 citations
• Understanding and Mitigating Copying in Diffusion Models
  2023 · 17 citations
• Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification
  2022 · 16 citations
• VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization
  2021 · 11 citations
• Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models
  2022 · 10 citations
• Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Models
  2021 · 7 citations
• Thinking Two Moves Ahead: Anticipating Other Users Improves Backdoor Attacks in Federated Learning
  2022 · 6 citations
• Identifying and Evaluating Inactive Heads in Pretrained LLMs
  2025 · 5 citations
• Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations
  2022 · 3 citations
• Universal Guidance for Diffusion Models
  2023 · 3 citations
• Execute Order 66: Targeted Data Poisoning for Reinforcement Learning
  2022 · 1 citations
• Seeing in Words: Learning to Classify through Language Bottlenecks
  2023 · 1 citations
• ODIN: Disentangled Reward Mitigates Hacking in RLHF
  2024 · 1 citations