Synthetic realities are digital creations or augmentations that are contextually generated through the use of Artificial Intelligence (AI) methods, leveraging extensive amounts of data to construct new narratives or realities, regardless of the intent to deceive. In this paper, we delve into the concept of synthetic realities and their implications for Digital Forensics and society at large within the rapidly advancing field of AI. We highlight the crucial need for the development of forensic techniques capable of identifying harmful synthetic creations and distinguishing them from reality. This is especially important in scenarios involving the creation and dissemination of fake news, disinformation, and misinformation. Our focus extends to various forms of media, such as images, videos, audio, and text, as we examine how synthetic realities are crafted and explore approaches to detecting these malicious creations. Additionally, we shed light on the key research challenges that lie ahead in this area. This study is of paramount importance due to the rapid progress of AI generative techniques and their impact on the fundamental principles of Forensic Science.

Large and complex datasets are often collected from several, possibly heterogeneous sources. Collaborative learning methods improve efficiency by leveraging commonalities across datasets while accounting for possible differences among them. Here we study collaborative linear regression and contextual bandits, where each instance's associated parameters are equal to a global parameter plus a sparse instance-specific term. We propose a novel two-stage estimator called MOLAR that leverages this structure by first constructing an entry-wise median of the instances' linear regression estimates, and then shrinking the instance-specific estimates towards the median. MOLAR improves the dependence of the estimation error on the data dimension, compared to independent least squares estimates. We then apply MOLAR to develop methods for sparsely heterogeneous collaborative contextual bandits, which lead to improved regret guarantees compared to independent bandit methods. We further show that our methods are minimax optimal by providing a number of lower bounds. Finally, we support the efficiency of our methods by performing experiments on both synthetic data and the PISA dataset on student educational outcomes from heterogeneous countries.

The In-Network Computing (COIN) paradigm is a promising solution that leverages unused network resources to perform some tasks to meet up with computation-demanding applications, such as metaverse. In this vein, we consider the metaverse partial computation offloading problem for multiple subtasks in a COIN environment to minimise energy consumption and delay while dynamically adjusting the offloading policy based on the changing computation resources status. We prove that the problem is NP and thus transformed it into two subproblems: task splitting problem (TSP) on the user side and task offloading problem (TOP) on the COIN side. We modelled the TSP as an ordinal potential game (OPG) and proposed a decentralised algorithm to obtain its Nash Equilibrium (NE). Then, we model the TOP as Markov Decision Process (MDP) proposed double deep Q-network (DDQN) to solve for the optimal offloading policy. Unlike the conventional DDQN algorithm, where intelligent agents sample offloading decisions randomly within a certain probability, our COIN agent explores the NE of the TSP and the deep neural network. Finally, simulation results show that our proposed model approach allows the COIN agent to update its policies and make more informed decisions, leading to improved performance over time compared to the traditional baseline.

The usability of Reinforcement Learning is restricted by the large computation times it requires. Curriculum Reinforcement Learning speeds up learning by defining a helpful order in which an agent encounters tasks, i.e. from simple to hard. Curricula based on Absolute Learning Progress (ALP) have proven successful in different environments, but waste computation on repeating already learned behaviour in new tasks. We solve this problem by introducing a new regularization method based on Self-Paced (Deep) Learning, called Self-Paced Absolute Learning Progress (SPALP). We evaluate our method in three different environments. Our method achieves performance comparable to original ALP in all cases, and reaches it quicker than ALP in two of them. We illustrate possibilities to further improve the efficiency and performance of SPALP.

Background and Context: Over the past year, large language models (LLMs) have taken the world by storm. In computing education, like in other walks of life, many opportunities and threats have emerged as a consequence. Objectives: In this article, we explore such opportunities and threats in a specific area: responding to student programmers' help requests. More specifically, we assess how good LLMs are at identifying issues in problematic code that students request help on. Method: We collected a sample of help requests and code from an online programming course. We then prompted two different LLMs (OpenAI Codex and GPT-3.5) to identify and explain the issues in the students' code and assessed the LLM-generated answers both quantitatively and qualitatively. Findings: GPT-3.5 outperforms Codex in most respects. Both LLMs frequently find at least one actual issue in each student program (GPT-3.5 in 90% of the cases). Neither LLM excels at finding all the issues (GPT-3.5 finding them 57% of the time). False positives are common (40% chance for GPT-3.5). The advice that the LLMs provide on the issues is often sensible. The LLMs perform better on issues involving program logic rather than on output formatting. Model solutions are frequently provided even when the LLM is prompted not to. LLM responses to prompts in a non-English language are only slightly worse than responses to English prompts. Implications: Our results continue to highlight the utility of LLMs in programming education. At the same time, the results highlight the unreliability of LLMs: LLMs make some of the same mistakes that students do, perhaps especially when formatting output as required by automated assessment systems. Our study informs teachers interested in using LLMs as well as future efforts to customize LLMs for the needs of programming education.

Federated learning (FL) is a distributed paradigm that coordinates massive local clients to collaboratively train a global model via stage-wise local training processes on the heterogeneous dataset. Previous works have implicitly studied that FL suffers from the ``client-drift'' problem, which is caused by the inconsistent optimum across local clients. However, till now it still lacks solid theoretical analysis to explain the impact of this local inconsistency. To alleviate the negative impact of the ``client drift'' and explore its substance in FL, in this paper, we first design an efficient FL algorithm \textit{FedInit}, which allows employing the personalized relaxed initialization state at the beginning of each local training stage. Specifically, \textit{FedInit} initializes the local state by moving away from the current global state towards the reverse direction of the latest local state. This relaxed initialization helps to revise the local divergence and enhance the local consistency level. Moreover, to further understand how inconsistency disrupts performance in FL, we introduce the excess risk analysis and study the divergence term to investigate the test error of the proposed \textit{FedInit} method. Our studies show that optimization error is not sensitive to this local inconsistency, while it mainly affects the generalization error bound in \textit{FedInit}. Extensive experiments are conducted to validate this conclusion. Our proposed \textit{FedInit} could achieve state-of-the-art~(SOTA) results compared to several advanced benchmarks without any additional costs. Meanwhile, stage-wise relaxed initialization could also be incorporated into the current advanced algorithms to achieve higher performance in the FL paradigm.

Simultaneously, the use of AI in academic writing has generated significant interest in AI related plagiarism. This has led to the emergence of a new term that warrants our attention: AI-giarism, a term that combines'AI' and'plagiarism', and has yet to be widely researched and defined within academic literature. For the study of AI in education in relation to academic misconduct, I, propose the following definition: AI-giarism refers to the unethical practice of using artificial intelligence technology, particularly generative language models, to generate content that is plagiarised either from original human-authored work or directly from AIgenerated content, without appropriate acknowledgement of the original sources or AI's contribution. This can happen when people use AI tools or language models to create written or multimedia content, such as articles, blog posts, images or videos, without properly attributing the original sources or modifying the content sufficiently to make it original (Salvagno et al, 2023). Some AI tools are designed to generate content by automatically combining or predicting from different sources, such as articles or websites, and paraphrasing them to create new content.

This study focuses on the topic of offline preference-based reinforcement learning (PbRL), a variant of conventional reinforcement learning that dispenses with the need for online interaction or specification of reward functions. Instead, the agent is provided with fixed offline trajectories and human preferences between pairs of trajectories to extract the dynamics and task information, respectively. Since the dynamics and task information are orthogonal, a naive approach would involve using preference-based reward learning followed by an off-the-shelf offline RL algorithm. However, this requires the separate learning of a scalar reward function, which is assumed to be an information bottleneck of the learning process. To address this issue, we propose the offline preference-guided policy optimization (OPPO) paradigm, which models offline trajectories and preferences in a one-step process, eliminating the need for separately learning a reward function. OPPO achieves this by introducing an offline hindsight information matching objective for optimizing a contextual policy and a preference modeling objective for finding the optimal context. OPPO further integrates a well-performing decision policy by optimizing the two objectives iteratively. Our empirical results demonstrate that OPPO effectively models offline preferences and outperforms prior competing baselines, including offline RL algorithms performed over either true or pseudo reward function specifications. Our code is available on the project website: https://sites.google.com/view/oppo-icml-2023 .

Federated Learning (FL) aims to train machine learning models for multiple clients without sharing their own private data. Due to the heterogeneity of clients' local data distribution, recent studies explore the personalized FL that learns and deploys distinct local models with the help of auxiliary global models. However, the clients can be heterogeneous in terms of not only local data distribution, but also their computation and communication resources. The capacity and efficiency of personalized models are restricted by the lowest-resource clients, leading to sub-optimal performance and limited practicality of personalized FL. To overcome these challenges, we propose a novel approach named pFedGate for efficient personalized FL by adaptively and efficiently learning sparse local models. With a lightweight trainable gating layer, pFedGate enables clients to reach their full potential in model capacity by generating different sparse models accounting for both the heterogeneous data distributions and resource constraints. Meanwhile, the computation and communication efficiency are both improved thanks to the adaptability between the model sparsity and clients' resources. Further, we theoretically show that the proposed pFedGate has superior complexity with guaranteed convergence and generalization error. Extensive experiments show that pFedGate achieves superior global accuracy, individual accuracy and efficiency simultaneously over state-of-the-art methods. We also demonstrate that pFedGate performs better than competitors in the novel clients participation and partial clients participation scenarios, and can learn meaningful sparse local models adapted to different data distributions.

Accurate, self-consistent bathymetric maps are needed to monitor changes in subsea environments and infrastructure. These maps are increasingly collected by underwater vehicles, and mapping requires an accurate vehicle navigation solution. Commercial off-the-shelf (COTS) navigation solutions for underwater vehicles often rely on external acoustic sensors for localization, however survey-grade acoustic sensors are expensive to deploy and limit the range of the vehicle. Techniques from the field of simultaneous localization and mapping, particularly loop closures, can improve the quality of the navigation solution over dead-reckoning, but are difficult to integrate into COTS navigation systems. This work presents a method to improve the self-consistency of bathymetric maps by smoothly integrating loop-closure measurements into the state estimate produced by a commercial subsea navigation system. Integration is done using a white-noise-on-acceleration motion prior, without access to raw sensor measurements or proprietary models. Improvements in map self-consistency are shown for both simulated and experimental datasets, including a 3D scan of an underwater shipwreck in Wiarton, Ontario, Canada.