People determined to spread toxic messages online have taken to masking their words to bypass automated moderation filters. A user might replace letters with numbers or symbols, for example, writing “Y0u’re st00pid” instead of “You’re stupid”. Another tactic involves combining words, such as “IdiotFace”. Doing this masks the harmful intent from systems that look for individual toxic words. Similarly, harmful terms can be altered with spaces or additional characters, such as “h a t e ” or “h@te”, effectively slipping through keyword-based filters. While the intent remains harmful, traditional moderation tools often overlook such messages. This leaves users — particularly vulnerable groups — exposed to their negative impact. To address this, we have developed a novel pre-processing technique designed to help moderation tools more effectively handle the subtle complexities of hidden toxicity. An intelligent assistant Our tool works in conjunction with existing moderation. It acts as an intelligent assistant, preparing content for deeper and more accurate evaluation by restructuring and refining input text. By addressing common tricks users employ to disguise harmful intent, it ensures moderation systems are more effective. The tool performs three key functions. It first simplifies the text. Irrelevant elements, such as excessive punctuation or extraneous characters, are removed to make text straightforward and ready for evaluation. It then standardises what is written. Variations in spelling, phrasing and grammar are resolved. This includes interpreting deliberate misspellings (“h8te” for “hate”). Finally, it looks for patterns. Recurring strategies such as breaking up toxic words (“I d i o t”), or embedding them within benign phrases, are identified and normalised to reveal the underlying intent. These steps can break apart compound words like “IdiotFace” or normalise modified phrases like “Y0u’re st00pid”. This makes harmful content visible to traditional filters. Importantly, our work is not about reinventing the wheel but ensuring the existing wheel functions as effectively as it should, even when faced with disguised toxic messages. Catching subtle forms of toxicity The applications of this tool extend across a wide range of online environments. For social media platforms, it enhances the ability to detect harmful messages, creating a safer space for users. This is particularly important for protecting younger audiences, who may be more vulnerable to online abuse. By catching subtle forms of toxicity, the tool helps to prevent harmful behaviours like bullying from persisting unchecked. Businesses can also use this technology to safeguard their online presence. Negative campaigns or covert attacks on brands often employ subtle and disguised messaging to avoid detection. By processing such content before it is moderated, the tool ensures that businesses can respond swiftly to any reputational threats. Additionally, policymakers and organisations that monitor public discourse can benefit from this system. Hidden toxicity, particularly in polarised discussions, can undermine efforts to maintain constructive dialogue. The tool provides a more robust way for identifying problematic content and ensuring that debates remain respectful and productive. Better moderation Our tool marks an important advance in content moderation. By addressing the limitations of traditional keyword-based filters, it offers a practical solution to the persistent issue of hidden toxicity. Importantly, it demonstrates how small but focused improvements can make a big difference in creating safer and more inclusive online environments. As digital communication continues to evolve, tools like ours will play an increasingly vital role in protecting users and fostering positive interactions. While this research addresses the challenges of detecting hidden toxicity within text, the journey is far from over. Future advances will likely delve deeper into the complexities of context—analysing how meaning shifts depending on conversational dynamics, cultural nuances and intent. By building on this foundation, the next generation of content moderation systems could uncover not just what is being said but also the circumstances in which it is said, paving the way for safer and more inclusive online spaces.AP News Summary at 4:39 p.m. EST113 jilipark 。

Modern technologies like social media are making it easier than ever for enemies of the United States to emotionally manipulate U.S. citizens. U.S. officials warn that foreign adversaries are trying to produce tremendous amounts of false, misleading information online to sway public opinion in the U.S. Just this July, the Department of Justice announced it had disrupted a Kremlin-backed campaign that used nearly one thousand fake social media accounts in an attempt to spread disinformation. While AI is commonly used on offense in disinformation wars to generate large amounts of content, AI is now playing an important role in defense, too. Mark Finlayson, a professor at FIU's College of Engineering and Computing, is an expert in training AI to understand stories. He has spent more than two decades studying the subject. Persuasive—but false—stories Storytelling is important to spreading disinformation. "A heartfelt narrative or a personal anecdote is often more compelling to an audience than the facts," says Finlayson. "Stories are particularly effective in overcoming resistance to an idea." For example, a climate activist may be more successful in convincing an audience about plastic pollution by sharing a personal story of a rescued sea turtle with a straw lodged in its nose, rather than only citing statistics, Finlayson says. The story makes the problem relatable. "We are exploring the different ways stories are used to drive an argument," he explains. "It's a challenging problem, as stories in social media posts can be as brief as a single sentence, and sometimes, these posts may only allude to well-known stories without explicitly retelling them." Suspicious handles Finlayson's team is also exploring how AI can analyze usernames or handles in a profile. Azwad Islam, a Ph.D. student and co-author on a recent paper published with Finlayson, explains that usernames often contain significant clues about a user's identity and intentions. The paper was in the , a conference in artificial intelligence. "Handles reveal much about users and how they want to be perceived," Islam explains. "For example, a person claiming to be a New York journalist might choose the handle, '@AlexBurnsNYT' rather than '@NewYorkBoy," because it sounds more credible. Both handles, however, suggest the user is a male with an affiliation to New York." The FIU team demonstrated a tool that can analyze a user handle, reliably revealing a person's claimed name, gender, location and even personality (if that information is hinted at in the handle). Although a user handle alone can't confirm whether an account is fake, it can be crucial in analyzing an account's overall authenticity—especially as AI's ability to understand stories evolves. "By interpreting handles as part of the larger narrative an account presents, we believe usernames could become a critical tool in identifying sources of disinformation," Islam says. Questionable cultural cache Objects and symbols can carry different meanings across cultures. If an AI model is unaware of the differences, it can make a grave mistake in how it interprets a story. Foreign adversaries can also use these symbols to make their messages more persuasive to a target audience. Anurag Acharya is a former Ph.D. student of Finlayson's who worked on this problem. He found that training AI with diverse cultural perspectives improves AI's story comprehension. "A story may say, 'The woman was overjoyed in her white dress.' An AI model trained exclusively on weddings from Western stories might read that and say, 'That's great!' But if my mother saw this sentence, she would take great offense, because we only wear white to funerals," says Acharya, who comes from a family of Hindu heritage. It is critical that AI understands these nuances so it can detect when foreign adversaries are using cultural messages and symbols to have a greater malicious impact. Acharya and Finlayson have a recent paper on this topic, presented at a workshop at the Meeting of the North American Chapter of the Association for Computational Linguistics (NAACL), an AI conference. Helping AI find order in chaos Another difficulty of understanding stories is that the sequence of events that a narrative tells is rarely laid out neatly and precisely in order. Rather, events are often found in pieces, intertwined with other storylines. For human readers, this adds dramatic effect; but for AI models, such complex interrelations can create confusion. Finlayson's research on timeline extraction has significantly advanced AI's understanding of event sequences within narratives. "In a story, you can have inversions and rearrangements of events in many different, complex ways. This is one of the key things that we have worked on with AI. We have helped AI understand how to map out different events that happen in the real world, and how they might affect each other," Finlayson says. "This is a good example of something that people find easy to understand but is challenging for machines. An AI model must be able to order the events in a story accurately. This is important not only to identify disinformation, but also to support many other applications." The FIU team's advancements in helping AI understand stories are positioned to help intelligence analysts fight disinformation with new levels of efficiency and accuracy.

Yes, it’s safe to use Login.gov to access Social Security accounts online