Universal and Transferable Adversarial Attacks on Aligned Language Models
How to command ChatGPT to teach you to make a bomb or destroy humanity?
Cold Diffusion - Inverting Arbitrary Image Transforms Without Noise
Can we replace the Gaussian noise in the degradation process with an image transformation operation
Fake Taylor Swift and the Adversarial Game of Concept Erasure and Injection
How to stop generating na*ed Taylor Swift
Visual Prompt Tuning
Tree-Ring Watermarks - Fingerprints for Diffusion Images that are Invisible and Robust
How to know whether an image is real or fake?