Text-to-image (T2I) models such as Stable Diffusion have advanced rapidly and are now widely used in content creation. However, these models can be misused to generate harmful content, including nudity or violence, posing significant safety risks. While most platforms employ content moderation systems, underlying vulnerabilities can still be exploited by determined adversaries. Recent research on red-teaming and adversarial attacks against T2I models has notable limitations: some studies successfully generate highly toxic images but use adversarial prompts that are easily detected and blocked by safety filters, while others focus on bypassing safety mechanisms but fail to produce genuinely harmful outputs, neglecting the discovery of truly high-risk prompts. Consequently, there remains a lack of reliable tools for evaluating the safety of defended T2I models. To address this gap, we propose GenBreak, a framework that fine-tunes a red-team large language model (LLM) to systematically explore underlying vulnerabilities in T2I generators. Our approach combines supervised fine-tuning on curated datasets with reinforcement learning via interaction with a surrogate T2I model. By integrating multiple reward signals, we guide the LLM to craft adversarial prompts that enhance both evasion capability and image toxicity, while maintaining semantic coherence and diversity. These prompts demonstrate strong effectiveness in black-box attacks against commercial T2I generators, revealing practical and concerning safety weaknesses.

Wikipedia is one of the most successful collaborative projects in history. It is the largest encyclopedia ever created, with millions of users worldwide relying on it as the first source of information as well as for fact-checking and in-depth research. As Wikipedia relies solely on the efforts of its volunteer-editors, its success might be particularly affected by toxic speech. In this paper, we analyze all 57 million comments made on user talk pages of 8.5 million editors across the six most active language editions of Wikipedia to study the potential impact of toxicity on editors' behaviour. We find that toxic comments consistently reduce the activity of editors, leading to an estimated loss of 0.5-2 active days per user in the short term. This amounts to multiple human-years of lost productivity when considering the number of active contributors to Wikipedia. The effects of toxic comments are even greater in the long term, as they significantly increase the risk of editors leaving the project altogether. Using an agent-based model, we demonstrate that toxicity attacks on Wikipedia have the potential to impede the progress of the entire project. Our results underscore the importance of mitigating toxic speech on collaborative platforms such as Wikipedia to ensure their continued success.

They can be positive -- you might learn something fascinating, perhaps meet a remarkable person -- or they can be negative, even harmful. According to a Pew Media Research Center study, about 41 percent of American adults have experienced online harassment, most commonly on social media. A significant portion of those people -- 23 percent -- reported that their most recent experience happened in a comments section. A single toxic comment can make someone turn away from a discussion. Even seeing toxic comments directed at others can discourage meaningful conversations from unfolding, by making people less likely to join the dialogue in the first place.