Recently, text-to-image models have been thriving. Despite their powerful generative capacity, our research has uncovered a lack of robustness in this generation process. Specifically, the introduction of small perturbations to the text prompts can result in the blending of primary subjects with other categories or their complete disappearance in the generated images. In this paper, we propose Auto-attack on Text-to-image Models (ATM), a gradient-based approach, to effectively and efficiently generate such perturbations. By learning a Gumbel Softmax distribution, we can make the discrete process of word replacement or extension continuous, thus ensuring the differentiability of the perturbation generation.

This research explores whether the interaction between adversarial robots and creative practitioners can push artists to rethink their initial ideas. It also explores how working with these robots may influence artists' views of machines designed for creative tasks or collaboration. Many existing robots developed for creativity and the arts focus on complementing creative practices, but what if robots challenged ideas instead? To begin investigating this, I designed UnsTable, a robot drawing desk that moves the paper while participants (N=19) draw to interfere with the process. This inquiry invites further research into adversarial robots designed to challenge creative practitioners.

Henry Kissinger must be watching the latest season of "Westworld." The former U.S. secretary of state is warning against the threat of "unstable" artificial intelligence in a new essay in The Atlantic -- fearing the rapid rise of machines could lead to questions humanity is not ready to tackle. "What will become of human consciousness if its own explanatory power is surpassed by AI, and societies are no longer able to interpret the world they inhabit in terms that are meaningful to them?" asked Kissinger in the piece. Also Read: 'Silicon Valley' Fact Check: That'Digital Overlord' Thought Experiment Is Real and Horrifying Up to this point, humans are reported to have only reached "limited" AI, where machines have mastered chess and other complex games. The same machines would be useless if used to play Monopoly.