# Manipulating and Mitigating Generative Model Biases without Retraining

arXiv: https://arxiv.org/abs/2404.02530 · HTML: https://mlsanity.com/paper/2404.02530/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Vision-language and text-to-image safety, one of 12 directions in LLM safety and security.
- Builds on 30 of its 41 references that are in the map.
- First posted on arXiv 3 Apr 2024.

## Placed in

- LLM safety and security / [Vision-language and text-to-image safety](https://mlsanity.com/safety/vision-language-and-text-to-image-safety/)

## Builds on (most cited first, 30 of 30)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Backdoor Learning: A Survey](https://mlsanity.com/paper/2007.08745/) (2020)
- [Shap-E: Generating Conditional 3D Implicit Functions](https://mlsanity.com/paper/2305.02463/) (2023)
- [VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation](https://mlsanity.com/paper/2303.08320/) (2023)
- [Diffusion Models already have a Semantic Latent Space](https://mlsanity.com/paper/2210.10960/) (2022)
- [DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models](https://mlsanity.com/paper/2202.04053/) (2022)
- [Stable Bias: Analyzing Societal Representations in Diffusion Models](https://mlsanity.com/paper/2303.11408/) (2023)
- [Advances in adversarial attacks and defenses in computer vision: A survey](https://mlsanity.com/paper/2108.00401/) (2021)
- [Social Biases through the Text-to-Image Generation Lens](https://mlsanity.com/paper/2304.06034/) (2023)
- [How to Backdoor Diffusion Models?](https://mlsanity.com/paper/2212.05400/) (2022)
- [Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning](https://mlsanity.com/paper/2305.04175/) (2023)
- [TrojDiff: Trojan Attacks on Diffusion Models with Diverse Targets](https://mlsanity.com/paper/2303.05762/) (2023)
- [VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models](https://mlsanity.com/paper/2306.06874/) (2023)
- [ITI-GEN: Inclusive Text-to-Image Generation](https://mlsanity.com/paper/2309.05569/) (2023)
- [Rickrolling the Artist: Injecting Backdoors into Text Encoders for Text-to-Image Synthesis](https://mlsanity.com/paper/2211.02408/) (2022)
- [Evaluating and Mitigating Bias in Image Classifiers: A Causal Perspective Using Counterfactuals](https://mlsanity.com/paper/2009.08270/) (2020)
- [Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models](https://mlsanity.com/paper/2312.04410/) (2023)
- [Interpolating between Images with Diffusion Models](https://mlsanity.com/paper/2307.12560/) (2023)
- [BAGM: A Backdoor Attack for Manipulating Text-to-Image Generative Models](https://mlsanity.com/paper/2307.16489/) (2023)
- [TrojViT: Trojan Insertion in Vision Transformers](https://mlsanity.com/paper/2208.13049/) (2022)
- [Quantifying Bias in Text-to-Image Generative Models](https://mlsanity.com/paper/2312.13053/) (2023)

## Abstract (arXiv)

Text-to-image (T2I) generative models have gained increased popularity in the public domain. While boasting impressive user-guided generative abilities, their black-box nature exposes users to intentionally- and intrinsically-biased outputs. Bias manipulation (and mitigation) techniques typically rely on careful tuning of learning parameters and training data to adjust decision boundaries to influence model bias characteristics, which is often computationally demanding. We propose a dynamic and computationally efficient manipulation of T2I model biases by exploiting their rich language embedding spaces without model retraining. We show that leveraging foundational vector algebra allows for a convenient control over language model embeddings to shift T2I model outputs and control the distribution of generated classes. As a by-product, this control serves as a form of precise prompt engineering to generate images which are generally implausible using regular text prompts. We demonstrate a constructive application of our technique by balancing the frequency of social classes in generated images, effectively balancing class distributions across three social bias dimensions. We also highlight a negative implication of bias manipulation by framing our method as a backdoor attack with severity control using semantically-null input triggers, reporting up to 100% attack success rate. Key-words: Text-to-Image Models, Generative Models, Bias, Prompt Engineering, Backdoor Attacks