OtherVerified
Reviewed and published by trentmaziarz, April 22, 2026. Discovered and drafted by our automated research pipeline.
Nightshade offers artists a free, downloadable tool that uses machine learning to alter pixels in artwork so that any AI model trained on those images learns incorrect visual associations — for example, interpreting a dog as a cat. The tool was first released on January 18, 2024, and has been downloaded more than 2.5 million times globally.
Details
Nightshade takes an artist's digital image as input and applies a computed perturbation — a set of pixel-level changes invisible to the human eye but visible to AI — that causes generative AI image models to mislearn the associations between text prompts and visual content. Technically, it is a prompt-specific poisoning attack on text-to-image diffusion models, designed as a multi-objective optimization to minimize perceptible changes while maximizing disruption to model training. The tool runs entirely offline on the user's own machine; no image data is sent to the researchers. Version 1.1 was released on April 20, 2026, with bug fixes.
Products affected
Nightshade
Sources & Evidence
Company Disclosure
Cite this record
Trace Foundation. (2026). Nightshade: Nightshade offers artists a free, downloadable tool that uses machine learning to alter pixels in artwork so that any AI model trained on those images learns incorrect visual associations — for example, interpreting a dog as a cat. The tool was first released on January 18, 2024, and has been downloaded more than 2.5 million times globally (data as of 2026-04-22) [Data set record]. AI Trace. https://www.aitrace.org/r/practice/c2a42464-6698-4c68-b818-a4d02d248171. Accessed September 13, 2026.
- Stable link
- https://www.aitrace.org/r/practice/c2a42464-6698-4c68-b818-a4d02d248171
- Data as of
- April 22, 2026
- Last verified
- April 22, 2026
Other practices by Nightshade
Data AnalysisThe Glaze Project deployed a research study that uses AI-based classifiers to analyze whether images were created by a human artist or generated by an AI model, publishing findings on the accuracy of both automated detectors and human reviewers. This work was published in October 2024.OtherThe Glaze Project offers artists a free, downloadable tool called Glaze that uses machine learning to add imperceptible pixel-level changes to artwork, causing AI image models to misidentify the artist's style and preventing accurate style mimicry. Glaze was first released in March 2023 and has been downloaded more than 8.5 million times globally.
Have evidence about Nightshade's AI practices? Submit a report.
Report a Sighting →