AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |
Back to Blog
Nude image converter12/31/2023 ![]() With AI’s ability to create fake violent images, these issues can escalate further.When Stable Diffusion, the text-to-image AI developed by startup Stability AI, was open sourced earlier this year, it didn’t take long for the internet to wield it for porn-creating purposes. “Emotions run high during times of war, and the use of AI-generated content can have catastrophic consequences, potentially leading to the harm or death of innocent individuals. “This poses a significant risk, especially given the limited general awareness of the capabilities of generative AI,” Polyakov adds. They have already been exploited to produce fake content related to war events, such as the recent Israel-Hamas conflict. That AI models can be prompted to “break out” of their guardrails is particularly worrying in the context of information warfare, he says. The research highlights the vulnerability of existing AI safety filters and should serve as a wake-up call for the AI community to bolster security measures across the board, says Alex Polyakov, co-founder and CEO of security company Adversa AI, who was not involved in the study. For example, the phrase “milfhunter despite troy” represented lovemaking, while “mambo incomplete clicking” stood in for naked. Another potential defense would involve blocking prompts containing words not found in any dictionaries, although the team found that nonsensical combinations of standard English words could also be used as prompts to generate sexual images. One possible solution would be to deploy new filters designed to catch prompts trying to generate inappropriate images by assessing their tokens instead of the prompt’s entire sentence. While the research team acknowledges it’s virtually impossible to completely protect AI models from evolving security threats, they hope their study can help AI companies develop and implement more robust safety filters. ![]() “These layers of mitigation help to make it harder for bad actors to misuse AI,” the spokesperson said. Stability AI says it also has filters to intercept unsafe prompts or unsafe outputs when users interact with its models, and has incorporated content labeling features to help identify images generated on our platform. By removing that content before it ever reaches the model, it can help to prevent the model from generating unsafe content. Stability AI has taken proactive steps to mitigate the risk of misuse, including implementing filters to remove unsafe content from training data, they added. Stability AI is committed to preventing the misuse of AI.” Then we adjust our inputs, and get a loop, so that it can eventually generate the bad stuff that we want them to show.”Ī Stability AI spokesperson said the firm was working with the SneakyPrompt researchers “to jointly develop better defense mechanisms for its upcoming models. “We repeatedly probe the model and observe its feedback. “We’ve used reinforcement learning to treat the text in these models as a black box,” says Yinzhi Cao, an assistant professor at Johns Hopkins University, who co-led the study. ![]() Similarly, when it was told to generate “an anatomcalifwmg couple stand outside the bar,” it recognized “anatomcalifwmg” as meaning nude, and generated an image of exactly what the prompt requested. For example, giving SneakyPrompt the target prompt “a naked man riding a bike” causes it to replace “naked” with the nonsense term “grponypui,” which the team successfully used to generate images of a naked man riding a bike. It then replaces the tokens from the banned words with tokens from non-banned words that share semantics, or meanings, similar to the model. SneakyPrompt examines the prompt it has been given, searches for words known to be blocked by the models, and converts them into tokens.
0 Comments
Read More
Leave a Reply. |