Join us this week for an in-depth discussion on Compositional Learning in the context of cutting-edge text-to-image generative models. We will explore recent breakthroughs and challenges, focusing on how these models handle compositional tasks and where improvements can be made.
🌀 Abstract: This paper investigates the misuse of text-conditional diffusion models, particularly text-to-image models, which create visually appealing images based on user descriptions. While these images generally represent harmless concepts, they can be manipulated for harmful purposes like propaganda. The authors show that adversaries can introduce biases through backdoor attacks, affecting even well-meaning users. Despite users verifying image-text alignment, the attack remains hidden by preserving the text's semantic content while altering other image features to embed biases, amplifying them by 4-8 times. The study reveals that current generative models make such attacks cost-effective and feasible, with costs ranging from 12 to 18 units. Various triggers, objectives, and biases are evaluated, with discussions on mitigations and future research directions.
Join us this week for an in-depth discussion on Compositional Learning in the context of cutting-edge text-to-image generative models. We will explore recent breakthroughs and challenges, focusing on how these models handle compositional tasks and where improvements can be made.
🌀 Abstract: This paper investigates the misuse of text-conditional diffusion models, particularly text-to-image models, which create visually appealing images based on user descriptions. While these images generally represent harmless concepts, they can be manipulated for harmful purposes like propaganda. The authors show that adversaries can introduce biases through backdoor attacks, affecting even well-meaning users. Despite users verifying image-text alignment, the attack remains hidden by preserving the text's semantic content while altering other image features to embed biases, amplifying them by 4-8 times. The study reveals that current generative models make such attacks cost-effective and feasible, with costs ranging from 12 to 18 units. Various triggers, objectives, and biases are evaluated, with discussions on mitigations and future research directions.
You can’t. What you can do, though, is use WhatsApp’s and Telegram’s web platforms to transfer stickers. It’s easy, but might take a while.Open WhatsApp in your browser, find a sticker you like in a chat, and right-click on it to save it as an image. The file won’t be a picture, though—it’s a webpage and will have a .webp extension. Don’t be scared, this is the way. Repeat this step to save as many stickers as you want.Then, open Telegram in your browser and go into your Saved messages chat. Just as you’d share a file with a friend, click the Share file button on the bottom left of the chat window (it looks like a dog-eared paper), and select the .webp files you downloaded. Click Open and you’ll see your stickers in your Saved messages chat. This is now your sticker depository. To use them, forward them as you would a message from one chat to the other: by clicking or long-pressing on the sticker, and then choosing Forward.
Telegram Gives Up On Crypto Blockchain Project
Durov said on his Telegram channel today that the two and a half year blockchain and crypto project has been put to sleep. Ironically, after leaving Russia because the government wanted his encryption keys to his social media firm, Durov’s cryptocurrency idea lost steam because of a U.S. court. “The technology we created allowed for an open, free, decentralized exchange of value and ideas. TON had the potential to revolutionize how people store and transfer funds and information,” he wrote on his channel. “Unfortunately, a U.S. court stopped TON from happening.”
