Manila, Philippines – When former Philippines President Rodrigo Duterte was arrested by the International Criminal Court (ICC) in March, Sheerah Escuerdo spoke to a local television station, welcoming the politician's detention on charges of murder linked to his war on drugs. Escuerdo, who lost her 18-year-old brother, Ephraim, to Duterte's war, clutched a portrait of her sibling during the interview with News 5 Everywhere as she demanded justice for his killing. Days later, she was shocked to find an AI-generated video of her slain brother circulating on Facebook, in which he said he was alive and accused his sister of lying. Are they paying you to do this?" the computer-generated image of Ephraim said. The video, posted online by a pro-Duterte influencer with 11,000 followers, immediately drew thousands of views on Facebook. One of the comments read, "Fake drug war victims". It was Escudero and her brother's image from her News 5 Everywhere interview that the influencer had used to ...

Arizona Attorney General Kris Mayes explains how drones are frequently used at the southern border to transport drugs, raising concerns from both sides of the aisle. As reported crossings have dropped dramatically at the border, there is still work to be done on matters of stopping drugs from making their way into the United States, especially in the border state of Arizona, a top state official says. One of the ways that cartels transport drugs is by using drones, a tactic that gained attention after bipartisan legislation signed in the Grand Canyon State gave law enforcement the power to shoot down the small aircraft. "I think what has changed is that we have gotten more control over people crossing over the border, but unfortunately what has not changed is we still have a huge amount of fentanyl that is coming across our border here in Arizona, and that is being flown over the by the Mexican drug cartels with drones," Democratic Arizona Attorney General Kris Mayes said. Fentanyl is being delivered across the border by cartels on drones.

The chatbot embedded in Elon Musk's X that referred to itself as "MechaHitler" and made antisemitic comments last week could be considered terrorism or violent extremism content, an Australian tribunal has heard. But an expert witness for X has argued a large language model cannot be ascribed intent, only the user. The outburst came into focus at an administrative review tribunal hearing on Tuesday where X is challenging a notice issued by the eSafety commissioner, Julie Inman Grant, in March last year asking the platform to explain how it is taking action against terrorism and violent extremism (TVE) material. X's expert witness, RMIT economics professor Chris Berg, provided evidence to the case that it was an error to assume a large language model can produce such content, because it is the intent of the user prompting the large language model that is critical in defining what can be considered terrorism and violent extremism content. One of eSafety's expert witnesses, Queensland University of Technology law professor Nicolas Suzor, disagreed with Berg, stating it was "absolutely possible for chatbots, generative AI and other tools to have some role in producing so-called synthetic TVE".

As archives turn to artificial intelligence to manage growing volumes of digital records, privacy risks inherent in current AI data practices raise critical concerns about data sovereignty and ethical accountability. This paper explores how privacy-enhancing technologies (PETs) and Web3 architectures can support archives to preserve control over sensitive content while still being able to make it available for access by researchers. We present Clio-X, a decentralized, privacy-first Web3 digital solution designed to embed PETs into archival workflows and support AI-enabled reference and access. Drawing on a user evaluation of a medium-fidelity prototype, the study reveals both interest in the potential of the solution and significant barriers to adoption related to trust, system opacity, economic concerns, and governance. Using Rogers' Diffusion of Innovation theory, we analyze the sociotechnical dimensions of these barriers and propose a path forward centered on participatory design and decentralized governance through a Clio-X Decentralized Autonomous Organization. By integrating technical safeguards with community-based oversight, Clio-X offers a novel model to ethically deploy AI in cultural heritage contexts.

We introduce an algorithm for identifying interpretable subgroups with elevated treatment effects, given an estimate of individual or conditional average treatment effects (CATE). Subgroups are characterized by "rule sets"--easy-to-understand statements of the form (Condition A AND Condition B) OR (Condition C) --which can capture high-order interactions while retaining interpretability. Our method complements existing approaches for estimating the CATE, which often produce high dimensional and uninterpretable results, by summarizing and extracting critical information from fitted models to aid decision making, policy implementation, and scientific understanding. We propose an objective function that trades-off subgroup size and effect size, and varying the hyperparameter that controls this trade-off results in a "frontier" of Pareto optimal rule sets, none of which dominates the others across all criteria. Valid inference is achievable through sample splitting. We demonstrate the utility and limitations of our method using simulated and empirical examples. In causal inference, average treatment effects (ATE) and average treatment effects on the treated (ATT) are the estimands that garner the most interest. Even if the effect of a treatment is known to be positive on average, it can vary greatly across individuals; some individuals will benefit, but some may experience no effect, and others may even be hurt.

Undesirable biases encoded in the data are key drivers of algorithmic discrimination. Their importance is widely recognized in the algorithmic fairness literature, as well as legislation and standards on anti-discrimination in AI. Despite this recognition, data biases remain understudied, hindering the development of computational best practices for their detection and mitigation. In this work, we present three common data biases and study their individual and joint effect on algorithmic discrimination across a variety of datasets, models, and fairness measures. We find that underrepresentation of vulnerable populations in training sets is less conducive to discrimination than conventionally affirmed, while combinations of proxies and label bias can be far more critical. Consequently, we develop dedicated mechanisms to detect specific types of bias, and combine them into a preliminary construct we refer to as the Data Bias Profile (DBP). This initial formulation serves as a proof of concept for how different bias signals can be systematically documented. Through a case study with popular fairness datasets, we demonstrate the effectiveness of the DBP in predicting the risk of discriminatory outcomes and the utility of fairness-enhancing interventions. Overall, this article bridges algorithmic fairness research and anti-discrimination policy through a data-centric lens.

Although Large Language Models (LLMs) have demonstrated significant advancements in natural language processing tasks, their effectiveness in the classification and transformation of abusive text into non-abusive versions remains an area for exploration. In this study, we aim to use LLMs to transform abusive text (tweets and reviews) featuring hate speech and swear words into non-abusive text, while retaining the intent of the text. We evaluate the performance of two state-of-the-art LLMs, such as Gemini, GPT-4o, DeekSeek and Groq, on their ability to identify abusive text. We them to transform and obtain a text that is clean from abusive and inappropriate content but maintains a similar level of sentiment and semantics, i.e. the transformed text needs to maintain its message. Afterwards, we evaluate the raw and transformed datasets with sentiment analysis and semantic analysis. Our results show Groq provides vastly different results when compared with other LLMs. We have identified similarities between GPT-4o and DeepSeek-V3.

As a promising privacy-aware collaborative model training paradigm, Federated Learning (FL) is becoming popular in the design of distributed recommender systems. However, Federated Recommender Systems (FedRecs) greatly suffer from two major problems: i) extremely high communication overhead due to massive item embeddings involved in recommendation systems, and ii) intolerably low training efficiency caused by the entanglement of both heterogeneous network environments and client devices. Although existing methods attempt to employ various compression techniques to reduce communication overhead, due to the parameter errors introduced by model compression, they inevitably suffer from model performance degradation. To simultaneously address the above problems, this paper presents a communication-efficient FedRec framework named FedRAS, which adopts an action-sharing strategy to cluster the gradients of item embedding into a specific number of model updating actions for communication rather than directly compressing the item embeddings. In this way, the cloud server can use the limited actions from clients to update all the items. Since gradient values are significantly smaller than item embeddings, constraining the directions of gradients (i.e., the action space) introduces smaller errors compared to compressing the entire item embedding matrix into a reduced space. To accommodate heterogeneous devices and network environments, FedRAS incorporates an adaptive clustering mechanism that dynamically adjusts the number of actions. Comprehensive experiments on well-known datasets demonstrate that FedRAS can reduce the size of communication payloads by up to 96.88%, while not sacrificing recommendation performance within various heterogeneous scenarios. We have open-sourced FedRAS at https://github.com/mastlab-T3S/FedRAS.

While the Internet's core infrastructure was designed to be open and universal, today's application layer is dominated by closed, proprietary platforms. Open and interoperable APIs require significant investment, and market leaders have little incentive to enable data exchange that could erode their user lock-in. We argue that LLM-based agents fundamentally disrupt this status quo. Agents can automatically translate between data formats and interact with interfaces designed for humans: this makes interoperability dramatically cheaper and effectively unavoidable. We name this shift universal interoperability: the ability for any two digital services to exchange data seamlessly using AI-mediated adapters. Universal interoperability undermines monopolistic behaviours and promotes data portability. However, it can also lead to new security risks and technical debt. Our position is that the ML community should embrace this development while building the appropriate frameworks to mitigate the downsides. By acting now, we can harness AI to restore user freedom and competitive markets without sacrificing security.

Language models trained with reinforcement learning (RL) can engage in reward hacking--the exploitation of unintended strategies for high reward--without revealing this behavior in their chain-of-thought reasoning. This makes the detection of reward hacking difficult, posing risks for high-stakes applications. We propose verbalization fine-tuning (VFT), a pre-RL fine-tuning intervention that trains models to explicitly acknowledge when they are influenced by prompt cues--hints which point to incorrect answers (e.g., "a Stanford professor thinks the answer is A"). To evaluate VFT, we subsequently train models with RL on environments where held-out prompt cues signal which incorrect answers will receive high reward, incentivizing models to exploit these cues instead of reasoning correctly. We measure how often models exploit these cues without verbalizing it. After RL, only 6% of the VFT-trained model's responses consist of undetected reward hacks. In comparison, when we perform RL without VFT, the rate of undetected reward hacks goes up to 88%; with a debiasing baseline intervention, this increases further to 99%. VFT achieves this by substantially increasing how often models verbalize the influence of cues, from 8% to 43% after VFT, and up to 94% after RL. Baselines remain low even after RL (11% and 1%). Our results show that teaching models to explicitly verbalize reward hacking behavior before RL significantly improves their detection, offering a practical path toward more transparent and safe AI systems.