# Latent Diffusion Counterfactual Explanations Source: [Latent Diffusion Counterfactual Explanations]() Collection index: [llms.txt]() Data updated: 2025-10-27T06:27:18.233Z Authors: Karim Farid, Simon Schrodi, Max Argus, Thomas Brox Published: 2023-10-10T14:42:34.000Z ## Abstract Counterfactual explanations have emerged as a promising method for elucidating the behavior of opaque black-box models. Recently, several works leveraged pixel-space diffusion models for counterfactual generation. To handle noisy, adversarial gradients during counterfactual generation -- causing unrealistic artifacts or mere adversarial perturbations -- they required either auxiliary adversarially robust models or computationally intensive guidance schemes. However, such requirements limit their applicability, e.g., in scenarios with restricted access to the model's training data. To address these limitations, we introduce Latent Diffusion Counterfactual Explanations (LDCE). LDCE harnesses the capabilities of recent class- or text-conditional foundation latent diffusion models to expedite counterfactual generation and focus on the important, semantic parts of the data. Furthermore, we propose a novel consensus guidance mechanism to filter out noisy, adversarial gradients that are misaligned with the diffusion model's implicit classifier. We demonstrate the versatility of LDCE across a wide spectrum of models trained on diverse datasets with different learning paradigms. Finally, we showcase how LDCE can provide insights into model errors, enhancing our understanding of black-box model behavior. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Visual Counterfactual Explanation (Age) on CelebA-HQ](): Visual Counterfactual Explanation (Age); CelebA-HQ; FID: 14.2. - [Counterfactual Explanation on ImageNet Zebra - Sorrel](): Counterfactual Explanation; ImageNet Zebra - Sorrel; FID: 82.4. - [Counterfactual Explanation on ImageNet (Cheetah - Cougar)](): Counterfactual Explanation; ImageNet (Cheetah - Cougar); FID: 71. - [Counterfactual Explanation on ImageNet Egyptian Cat - Persian Cat](): Counterfactual Explanation; ImageNet Egyptian Cat - Persian Cat; FID: 102.7. - [Visual Counterfactual Explanation (Smile) on CelebA HQ](): Visual Counterfactual Explanation (Smile); CelebA-HQ; FID: 13.6. ## Original sources and implementation [Original paper]() [PDF]()