The Trustworthy GenAI Series

• Tutorials on Diffusion Models
• Tutorials on Adversarial Machine Learning
• Machine Unlearning - Erasing Concepts
• Other posts

Tutorials on Diffusion Models

• Part 1: Denoising Diffusion Probabilistic Models (DDPM)
• Part 2: DDIM, Diffusion Inversion and Accelerating Inference
• Implementation: DDPM with Tensorflow 2
• Implementation: DDIM and Diffusion Inversion

Tutorials on Adversarial Machine Learning

• Part 1: The Good, The Bad, The Ugly
• Part 2: Adversarial Attacks
• List of research groups and notable researchers in the field of Adversarial Machine Learning

Machine Unlearning - Erasing Concepts

• Fantastic Targets for Concept Erasure in Diffusion Models and Where to Find Them
• Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation
• Fake Taylor Swift and the Adversarial Game of Concept Erasure and Injection
• Erasing Concepts from Diffusion Models
• Lesson Learned from NeurIPS 2023 Machine Unlearning Challenge

Other posts

• What is Safety Checker in Stable Diffusion
• Connection between Flatness and Generalization
• Comparing Implementations of Diffusion Models - HuggingFace Diffusers vs. CompVis Stable Diffusion
• AdvPrompter - Fast Adaptive Adversarial Prompting for LLMs
• Unsolvable Problem Detection - Evaluating Trustworthiness of Vision Language Models
• Universal and Transferable Adversarial Attacks on Aligned Language Models
• Cold Diffusion - Inverting Arbitrary Image Transforms Without Noise
• Tree-Ring Watermarks - Fingerprints for Diffusion Images that are Invisible and Robust
• Flow Matching for Generative Modeling
• Diffusion Models Beat GANs on Image Synthesis
• Fairness in Machine Learning
• Anti-Personalization in Generative Models
• Textual Inversion
• Anti-Dreambooth