Image Generation models are a trending topic nowadays, with many people utilizing Artificial Intelligence models in order to generate images. There are many such models which, given a prompt of a text, will generate an image which depicts said prompt. There are many image generation models, such as Latent Diffusion Models, Denoising Diffusion Probabilistic Models, Generative Adversarial Networks and many more. When generating images, these models can generate sensitive image data, which can be threatening to privacy or may violate copyright laws of private entities. Machine unlearning aims at removing the influence of specific data subsets from the trained models and in the case of image generation models, remove the influence of a concept such that the model is unable to generate said images of the concept when prompted. Conventional retraining of the model can take upto days, hence fast algorithms are the need of the hour. In this paper we propose an algorithm that aims to remove the influence of concepts in diffusion models through updating the gradients of the final layers of the text encoders. Using a weighted loss function, we utilize backpropagation in order to update the weights of the final layers of the Text Encoder componet of the Stable Diffusion Model, removing influence of the concept from the text-image embedding space, such that when prompted, the result is an image not containing the concept. The weighted loss function makes use of Textual Inversion and Low-Rank Adaptation.We perform our experiments on Latent Diffusion Models, namely the Stable Diffusion v2 model, with an average concept unlearning runtime of 50 seconds using 4-5 images.

Recent AI systems have shown extremely powerful performance, even surpassing human performance, on various tasks such as information retrieval, language generation, and image generation based on large language models (LLMs). At the same time, there are diverse safety risks that can cause the generation of malicious contents by circumventing the alignment in LLMs, which are often referred to as jailbreaking. However, most of the previous works only focused on the text-based jailbreaking in LLMs, and the jailbreaking of the text-to-image (T2I) generation system has been relatively overlooked. In this paper, we first evaluate the safety of the commercial T2I generation systems, such as ChatGPT, Copilot, and Gemini, on copyright infringement with naive prompts. From this empirical study, we find that Copilot and Gemini block only 12% and 17% of the attacks with naive prompts, respectively, while ChatGPT blocks 84% of them. Then, we further propose a stronger automated jailbreaking pipeline for T2I generation systems, which produces prompts that bypass their safety guards. Our automated jailbreaking framework leverages an LLM optimizer to generate prompts to maximize degree of violation from the generated images without any weight updates or gradient computation. Surprisingly, our simple yet effective approach successfully jailbreaks the ChatGPT with 11.0% block rate, making it generate copyrighted contents in 76% of the time. Finally, we explore various defense strategies, such as post-generation filtering and machine unlearning techniques, but found that they were inadequate, which suggests the necessity of stronger defense mechanisms.

On January 1, Mike Neville gave Midjourney the following prompt: "Steamboat Willie drawn in a vintage Disney style, black and white. He is dripping all over with white gel." There's no polite way to describe what this prompt conjured from the AI image generator. It looks, very much, like Mickey Mouse is drenched in ejaculate. At the start of every year, a crop of cultural works enters the public domain in the United States.

Craggy, grey-haired and 80 years old, Harrison Ford might seem a bit old to don his brown Fedora-style hat or crack his whip as Indiana Jones. But a trailer for his upcoming film Indiana Jones and the Dial of Destiny offers a flashback to Indy in his swashbuckling glory days. "That is my actual face at that age," the actor explained on CBS's The Late Show with Stephen Colbert. "They have this artificial intelligence (AI) programme. It can go through every foot of film that Lucasfilm owns because I did a bunch of movies for them and they have all this footage including film that wasn't printed: stock. They could mine it from where the light is coming from, the expression. Then I put little dots on my face and I say the words and they make it. Having discovered the secret of eternal youth, Ford joked: "That's what I see when I look in the mirror now." He is not the only actor to get a digital facelift with an assist from AI. Tom Hanks, Robin Wright and other cast members will play younger versions of themselves in Here, directed by Robert Zemeckis, thanks to a tool that the AI company Metaphysic says can create "high-resolution photorealistic faceswaps and de-ageing effects on top of actors' performances live and in real time without the need for further compositing or VFX work". Metaphysic's website proclaims: "We are world leaders in creating AI generated content that looks real" and suggests: "Use AI to create your own hyperreal avatar". The company has just struck a deal with the Creative Artists Agency "to develop generative AI tools and services for talent", according to the Hollywood Reporter. Just as the buzzy AI chatbot ChatGPT threatens to upend journalism, speechwriting and school essays, so AI could turn digital de-ageing from something that requires many months of highly skilled artists to something that many people can do in their bedrooms. And as the technology becomes ever more sophisticated, there are fears that deepfake technology could fall into the wrong hands and be weaponised. Olcun Tan, a German-born visual effects supervisor based in Los Angeles, reflects: "We're going through a big revolution.

Music is liquid architecture; architecture is frozen music.--Attributed to Goethe But Missa solemnis 2.0, a collaboration between pioneering media artist and director Refik Anadol and The Philadelphia Orchestra (April 7, 9, 10, supported by The Pew Center for Arts & Heritage), brings Goethe's pithy saying to stunning visual and sonic life in ways the German literary giant never could have imagined. Beethoven completed his Missa solemnis in 1823. Despite being regarded as one of his most stunning musical creations, the piece is rarely performed. The composer's partner in this century-spanning project, Refik Anadol, was born in Istanbul. In 2008, while still an undergrad there, he presented his first digital art installation.

We propose the task of Narrative Reordering(NAREOR) which involves rewriting a given story in a different narrative order while preserving its plot, semantic, and temporal aspects. We present a dataset, NAREORC, with over 1000 human rewritings of stories within ROCStories in non-linear orders, and conduct a detailed analysis of it. Further, we propose novel initial task-specific training methods and evaluation metrics. We perform experiments on NAREORC using GPT-2 and Transformer models and conduct an extensive human evaluation. We demonstrate that NAREOR is a challenging task with potential for further exploration.

Many techies may be wondering right now how Samsung managed to snag a deal with Disney behind Apple's back. Apple and Disney are known to have this long and close relationship, so it totally came as a shock when Samsung unveiled the Galaxy S9 and introduced Disney character emojis as part of the device's AR Emoji feature. Samsung's partnership with Disney for AR Emoji has undeniably caused some to wonder if Apple is also in the process of securing the same deal. However, SamMobile says it's still unclear if Apple would be offered the same thing so that its iPhone X's Animoji feature could also have access to the same Disney emojis that are coming to Samsung's AR Emoji. It's also still unknown if the Disney emojis are exclusive to Samsung at this point.

Disney says its parks are "Where Dreams Come True," but that statement was never so literal as it was for two foster kids during a recent visit to the park. Janielle and Elijah Gilmour, ages 12 and 10, got the surprise of a lifetime in April, when foster parents Courtney and Tom Gilmour announced news of their official adoption date during a visit to Walt Disney World. "We planned it as soon as we got the [official] date, which was the Friday before our trip," Courtney tells Fox News. What Courtney didn't plan on, however, was that Disney would catch wind of the duo's plans and offer to lend a mouse-like, white-gloved hand. After arriving at the park from Portland, Penn., Courtney tweeted out a photo of the family's Walt Disney World celebration buttons, and the park got in touch to offer a private meet-and-greet with Mickey Mouse himself.

Walt Disney World in Florida appears poised to launch the highest-profile commercial deployment of driverless passenger vehicles to date, testing a fleet of driverless shuttles that could cart passengers through car parks and around its theme parks. According to sources with direct knowledge of Disney's plans, Walt Disney is in late-stage negotiations with at least two manufacturers of autonomous shuttles. The sources, who asked not be identified to avoid offending Disney, said the company plans a pilot program this year to transport employees in the electric-drive robot vehicles. If that goes well, they said, the shuttles would begin transporting park visitors sometime next year. There are no plans for driverless shuttles at Disneyland in Anaheim, according to the sources.