• ANTI REGULATION - GLOWS

• JGAAP: De-Anonymousposting (stylometry)

  • counter: remove all punctuation marks and make everything lower case

  • counter: purposeful grammatical and spelling errors (antigeographical location)

• RainbowTeaming: Open-Ended Generation of Diverse Adversarial Prompts

  • categorizing strings determining likelihood of prompt being unsafe using different attack-styles

• Towards ImplicitPrompt For Text-To-Image Models

  • implicit prompts: hint at a target without explicitly mentioning it

  • censorship can be bypassed with implicit prompts

DETECTING HUMAN

• DensePose From WiFithree wifis to get pose of human

• SoundCam A Dataset for Finding Humans Using Room Acoustics

SPOOFING

• Transparency Attacks How Imperceptible Image Layers Can Fool AI Perception

  • dataset poisoning using the attack to mislabel a collection, in background(hidden) layer in grayscale

  • cause mislabeling

  • use cases:evading facial recognition and surveillance, digital watermarking, content filtering, dataset curating, automotive and drone autonomy, forensic evidence tampering, and retail product misclassifying

VIDEO GLOW

• PRIME Protect Your Videos From Malicious Editing

DIFFUSION CENSOR

• parent: stable_diffusion

• AmbientDiffusion: train diffusion models given only corrupted images as input (copyrightless-ed)

• Seeing the Worldthrough Your Eyes (getting image from reflection of the eyes)

• LoRA Fine-tuningEfficiently Undoes Safety Training in Llama 2-Chat 70B

  • successfully undo the safety training using lora

• CheatingSuffix Targeted Attack to Text-To-Image Diffusion Models with Multi-Modal Priors

  • MMP-Attack, confusing a model into adding a target object into the image content while simultaneously removing the original object

DETECTING AI GENERATED

• AEROBLADE Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Error

  • does not require any training

• Organic orDiffused: Can We Distinguish Human Art from AI-generated Images?

ERASING CONCEPTS

• erasingconceptshttps://note.com/gcem156/n/n9f74d7d1417c

  • Using stable diffusioneraser to replace a concept in one model with the same concept from another

  • Forget-Me-Not Learning toForget in Text-to-Image Diffusion Models

  • All butOne: Surgical Concept Erasing with Model Preservation in Text-to-Image Diffusion Models

    • new approach without issues

• ORES Open-vocabulary Responsible Visual Synthesis

  • synthesize images avoiding concepts but following query as much as possible

  • using a llm

• One-dimensionalAdapter to Rule Them All: Concepts, Diffusion Models and Erasing Applications

  • solution to erase or edit concepts for diffusion models (DMs), 0.5% extra parameters of the DM

• EraseDiff Erasing Data Influence in Diffusion Models

• SepME Separable Multi-Concept Erasure from Diffusion Models

  • avoid unlearning substantial information

• MACE Mass Concept Erasure in Diffusion Models

  • successfully scaling the erasure scope up to 100 concepts and balancing generality and specificity

• RobustConcept Erasure Using Task Vectors

  • concept erasure that uses Task Vectors (TV) is more robust to unexpected user inputs

  • diverse inversion: used to estimate the required strength of the tv edit

    • apply a TV edit only to a subset of the model weights

LLM

• TOFU A Task of Fictitious Unlearning for LLMs

  • so that it truly behaves as if never trained on the forgeted data

• Scissorhands Scrub Data Influence via Connection Sensitivity in Networks

  • retrains the trimmed model through a optimization process

  • seeking parameters that preserve information on the remaining data while discarding information related to the forgetting data

FINGERPRINTING

• and watermarking

• CopyRNeRF Protecting the CopyRight of Neural Radiance Fields

  • replacing the original color representation in NeRF with a watermarked color representation

• Tree-Ring Watermarks Fingerprints for Diffusion Images that are Invisible and Robust

  • patterns hiddens in fourier space

• WOUAFWeight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Models

  • model fingerprinting that assigns responsibility for the generated images

• FLIRT Feedback Loop In-context Red Teaming

  • automatic framework that exposes unsafe, inappropriate, content generation and vulnerabilities

• ZoDiac Robust Image Watermarking using Stable Diffusion

  • inject a watermark into the trainable latent space, which are reliably detected in the latent vector

• RAW A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees

ANTI-GLOW

• MimicDiffusion Purifying Adversarial Perturbation via Mimicking Clean Diffusion Model

  • purification technique, approximates the clean image as input

• DisDet Exploring Detectability of Backdoor Attack on Diffusion Models

  • detecting poisoned input noise, 100% detection rate for trojan triggers