# kandinsky

Published articles for kandinsky.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Mirage: Targeted Jailbreaks Against Post-Generation Safety Checkers in Multimodal Diffusion Models

DevFeed: [Mirage: Targeted Jailbreaks Against Post-Generation Safety Checkers in Multimodal Diffusion Models](<https://devfeed.tech/articles/mirage-targeted-jailbreaks-against-post-generation-safety-checkers-in-multimodal-diffusion-models-96575.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.30348>)

Author: Shanghao Shi, Chaoyu Zhang, Heng Jin, Hao Li, Ning Zhang, Y. Thomas Hou, Wenjing Lou

Published: 2026-10-23T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [ai security](<https://devfeed.tech/topics/ai-security.md>), [stable-diffusion](<https://devfeed.tech/topics/stable-diffusion.md>), [ai-image-generator](<https://devfeed.tech/topics/ai-image-generator.md>)

Tags: [1-5](<https://devfeed.tech/tags/1-5.md>), [2-2](<https://devfeed.tech/tags/2-2.md>), [adversarial](<https://devfeed.tech/tags/adversarial.md>), [alignment](<https://devfeed.tech/tags/alignment.md>), [attack](<https://devfeed.tech/tags/attack.md>), [concepts](<https://devfeed.tech/tags/concepts.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [diffusion-models](<https://devfeed.tech/tags/diffusion-models.md>), [evasion](<https://devfeed.tech/tags/evasion.md>), [generated-content](<https://devfeed.tech/tags/generated-content.md>), [generation](<https://devfeed.tech/tags/generation.md>), [image](<https://devfeed.tech/tags/image.md>), [image-generation](<https://devfeed.tech/tags/image-generation.md>), [image-to-image](<https://devfeed.tech/tags/image-to-image.md>), [jailbreak](<https://devfeed.tech/tags/jailbreak.md>), [jailbreaks](<https://devfeed.tech/tags/jailbreaks.md>), [kandinsky](<https://devfeed.tech/tags/kandinsky.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [safety](<https://devfeed.tech/tags/safety.md>)

### AI overview

Mirage is a targeted jailbreak attack that embeds an adversarial image or text target in an imperceptible perturbation to a benign input image. It aligns the perturbed image with the target in multimodal encoders' shared representation space while separating it from commonly filtered NSFW concepts; this separation can transfer across representation spaces. Lightweight black-box query refinement helps improve evasion near an unknown safety boundary, without access to checker internals. The authors implemented Mirage on Stable Diffusion 1.5, Stable Diffusion XL, and Kandinsky 2.2, evaluating it on two cross-modal NSFW datasets across text-to-image and image-to-image scenarios. They report strong targeted jailbreak performance across diverse post-generation safety checkers with limited queries and high semantic alignment to targets.

### Source excerpt

arXiv:2610.30348v1 Announce Type: new Abstract: Post-generation safety checkers are widely employed in diffusion-model pipelines to prevent unsafe generated content from reaching users. In this paper, we show that these safety checkers can still be bypassed by our proposed multimodal jailbreak attack, Mirage. Given an adversarial target, which can be either a reference NSFW image or a malicious text description, Mirage conceals the target within an imperceptible perturbation applied to a benign input image. Mirage exploits the shared representation space of multimodal encoders to jointly align the perturbed image with the cross-modal adversarial target while repelling its representation from commonly filtered NSFW concepts. Such semantic separation can transfer across representation spaces, enabling Mirage to evade heterogeneous safety checkers without accessing their internal details. We further employ lightweight black-box query refinement to improve evasion near the unknown safety boundary. We implemented Mirage on Stable Diffusion 1.5, Stable Diffusion XL, and Kandinsky 2.2, and evaluated it on two cross-modal NSFW datasets, covering both text-to-image and image-to-image generation scenarios. The experimental results demonstrate that Mirage achieves strong targeted jailbreak performance across diverse post-generation safety checkers with limited black-box queries while preserving high semantic alignment with the adversarial targets.

## Kandinsky 2.1 uses CLIP and diffusion to generate artwork up to 1024x1024

DevFeed: [Kandinsky 2.1 uses CLIP and diffusion to generate artwork up to 1024x1024](<https://devfeed.tech/articles/unveiling-kandinsky-2-1-the-revolutionary-ai-powered-art-generator-78109.md>)

Original publisher: [Read original article](<https://www.runpod.io/blog/kandinsky-2-1-ai-art-generator>)

Author: Madiator2011

Published: 2026-09-13T15:06:30Z

Content type: article

Language: en

Sources: [Runpod Blog.](<https://devfeed.tech/sources/runpod-blog.md>)

Topics: [stable-diffusion](<https://devfeed.tech/topics/stable-diffusion.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-powered](<https://devfeed.tech/tags/ai-powered.md>), [api](<https://devfeed.tech/tags/api.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [diffusion-models](<https://devfeed.tech/tags/diffusion-models.md>), [digital-art](<https://devfeed.tech/tags/digital-art.md>), [generator](<https://devfeed.tech/tags/generator.md>), [image-generation](<https://devfeed.tech/tags/image-generation.md>), [kandinsky](<https://devfeed.tech/tags/kandinsky.md>)

### AI overview

Runpod presents Kandinsky 2.1 as an API-accessible model that combines CLIP encoders with a diffusion image prior to generate and manipulate artwork. It says the model can produce images up to 1024x1024 pixels and provides a sample cURL request.

### Source excerpt

Kandinsky 2.1 combines CLIP and diffusion models to generate high-resolution, AI-driven artwork up to 1024x1024 pixels, available now on Runpod via API.