Large-language models are capable of completing a variety of tasks, but remain unpredictable and intractable. Representation engineering seeks to resolve this problem through a new approach utilizing samples of contrasting inputs to detect and edit high-level representations of concepts such as honesty, harmfulness or power-seeking. We formalize the goals and methods of representation engineering to present a cohesive picture of work in this emerging discipline. We compare it with alternative approaches, such as mechanistic interpretability, prompt-engineering and fine-tuning. We outline risks such as performance decrease, compute time increases and steerability issues. We present a clear agenda for future research to build predictable, dynamic, safe and personalizable LLMs.

This report presents a comprehensive response to the United Nation's Interim Report on Governing Artificial Intelligence (AI) for Humanity. It emphasizes the transformative potential of AI in achieving the Sustainable Development Goals (SDGs) while acknowledging the need for robust governance to mitigate associated risks. The response highlights opportunities for promoting equitable, secure, and inclusive AI ecosystems, which should be supported by investments in infrastructure and multi-stakeholder collaborations across jurisdictions. It also underscores challenges, including societal inequalities exacerbated by AI, ethical concerns, and environmental impacts. Recommendations advocate for legally binding norms, transparency, and multi-layered data governance models, alongside fostering AI literacy and capacity-building initiatives. Internationally, the report calls for harmonising AI governance frameworks with established laws, human rights standards, and regulatory approaches. The report concludes with actionable principles for fostering responsible AI governance through collaboration among governments, industry, academia, and civil society, ensuring the development of AI aligns with universal human values and the public good.

Modern applications in data analysis and machine learning work with highdimensional data to support inferences and provide recommendations [1, 2]. Increasingly, the data to support these tasks comes from individuals who hold their data on personal devices such as smartphones and wearables. In the federated model of computation [3, 4], this data remains on the users' devices, which collaborate and cooperate to build accurate models by performing computations and aggregations on their locally held information (e.g., training and fine-tuning small-scale models). A key primitive needed is the ability to compare the distribution of data held by these clients with a reference distribution. For instance, a platform or a service provider would like to know whether the overall behavior of the data is consistent over time for deploying the best fitting and most relevant model. In cases where the data distribution has changed, it may be necessary to trigger model rebuilding or fine-tuning, whereas if there is no change the current model can continue to be used.

Statistical heterogeneity is a measure of how skewed the samples of a dataset are. It is a common problem in the study of differential privacy that the usage of a statistically heterogeneous dataset results in a significant loss of accuracy. In federated scenarios, statistical heterogeneity is more likely to happen, and so the above problem is even more pressing. We explore the three most promising ways to measure statistical heterogeneity and give formulae for their accuracy, while simultaneously incorporating differential privacy. We find the optimum privacy parameters via an analytic mechanism, which incorporates root finding methods. We validate the main theorems and related hypotheses experimentally, and test the robustness of the analytic mechanism to different heterogeneity levels. The analytic mechanism in a distributed setting delivers superior accuracy to all combinations involving the classic mechanism and/or the centralized setting. All measures of statistical heterogeneity do not lose significant accuracy when a heterogeneous sample is used.

However, this extensive integration of IoT devices has also introduced significant cybersecurity risks. The Internet of Things (IoT) has attracted the attention of cybersecurity professionals after cyber-attackers started using IoT devices as botnets (Palekar and Radhika 2022). IoT devices are often vulnerable to various cyber threats, including distributed denial-of-service (DDoS) attacks, botnet exploitation, and data breaches, all of which can compromise critical systems' integrity, confidentiality, and availability. Understanding and mitigating the risks associated with IoT deployments is crucial in this evolving landscape, especially given the interdependencies between IoT components and systems.

Since its implementation in May 2018, the General Data Protection Regulation (GDPR) has prompted businesses to revisit and revise their data handling practices to ensure compliance. The privacy policy, which serves as the primary means of informing users about their privacy rights and the data practices of companies, has been significantly updated by numerous businesses post-GDPR implementation. However, many privacy policies remain packed with technical jargon, lengthy explanations, and vague descriptions of data practices and user rights. This makes it a challenging task for users and regulatory authorities to manually verify the GDPR compliance of these privacy policies. In this study, we aim to address the challenge of compliance analysis between GDPR (Article 13) and privacy policies for 5G networks. We manually collected privacy policies from almost 70 different 5G MNOs, and we utilized an automated BERT-based model for classification. We show that an encouraging 51$\%$ of companies demonstrate a strong adherence to GDPR. In addition, we present the first study that provides current empirical evidence on the readability of privacy policies for 5G network. we adopted readability analysis toolset that incorporates various established readability metrics. The findings empirically show that the readability of the majority of current privacy policies remains a significant challenge. Hence, 5G providers need to invest considerable effort into revising these documents to enhance both their utility and the overall user experience.

Releasing open-source large language models (LLMs) presents a dual-use risk since bad actors can easily fine-tune these models for harmful purposes. Even without the open release of weights, weight stealing and fine-tuning APIs make closed models vulnerable to harmful fine-tuning attacks (HFAs). While safety measures like preventing jailbreaks and improving safety guardrails are important, such measures can easily be reversed through fine-tuning. In this work, we propose Representation Noising (RepNoise), a defence mechanism that is effective even when attackers have access to the weights and the defender no longer has any control. RepNoise works by removing information about harmful representations such that it is difficult to recover them during fine-tuning. Importantly, our defence is also able to generalize across different subsets of harm that have not been seen during the defence process. Our method does not degrade the general capability of LLMs and retains the ability to train the model on harmless tasks. We provide empirical evidence that the effectiveness of our defence lies in its "depth": the degree to which information about harmful representations is removed across all layers of the LLM.

This report examines Artificial Intelligence (AI) in the financial sector, outlining its potential to revolutionise the industry and identify its challenges. It underscores the criticality of a well-rounded understanding of AI, its capabilities, and its implications to effectively leverage its potential while mitigating associated risks. The potential of AI potential extends from augmenting existing operations to paving the way for novel applications in the finance sector. The application of AI in the financial sector is transforming the industry. Its use spans areas from customer service enhancements, fraud detection, and risk management to credit assessments and high-frequency trading. However, along with these benefits, AI also presents several challenges. These include issues related to transparency, interpretability, fairness, accountability, and trustworthiness. The use of AI in the financial sector further raises critical questions about data privacy and security. A further issue identified in this report is the systemic risk that AI can introduce to the financial sector. Being prone to errors, AI can exacerbate existing systemic risks, potentially leading to financial crises. Regulation is crucial to harnessing the benefits of AI while mitigating its potential risks. Despite the global recognition of this need, there remains a lack of clear guidelines or legislation for AI use in finance. This report discusses key principles that could guide the formation of effective AI regulation in the financial sector, including the need for a risk-based approach, the inclusion of ethical considerations, and the importance of maintaining a balance between innovation and consumer protection. The report provides recommendations for academia, the finance industry, and regulators.

Over recent years, denoising diffusion generative models have come to be considered as state-of-the-art methods for synthetic data generation, especially in the case of generating images. These approaches have also proved successful in other applications such as tabular and graph data generation. However, due to computational complexity, to this date, the application of these techniques to graph data has been restricted to small graphs, such as those used in molecular modeling. In this paper, we propose SaGess, a discrete denoising diffusion approach, which is able to generate large real-world networks by augmenting a diffusion model (DiGress) with a generalized divide-and-conquer framework. The algorithm is capable of generating larger graphs by sampling a covering of subgraphs of the initial graph in order to train DiGress. SaGess then constructs a synthetic graph using the subgraphs that have been generated by DiGress. We evaluate the quality of the synthetic data sets against several competitor methods by comparing graph statistics between the original and synthetic samples, as well as evaluating the utility of the synthetic data set produced by using it to train a task-driven model, namely link prediction. In our experiments, SaGess, outperforms most of the one-shot state-of-the-art graph generating methods by a significant factor, both on the graph metrics and on the link prediction task.

The federated learning (FL) technique was developed to mitigate data privacy issues in the traditional machine learning paradigm. While FL ensures that a user's data always remain with the user, the gradients are shared with the centralized server to build the global model. This results in privacy leakage, where the server can infer private information from the shared gradients. To mitigate this flaw, the next-generation FL architectures proposed encryption and anonymization techniques to protect the model updates from the server. However, this approach creates other challenges, such as malicious users sharing false gradients. Since the gradients are encrypted, the server is unable to identify rogue users. To mitigate both attacks, this paper proposes a novel FL algorithm based on a fully homomorphic encryption (FHE) scheme. We develop a distributed multi-key additive homomorphic encryption scheme that supports model aggregation in FL. We also develop a novel aggregation scheme within the encrypted domain, utilizing users' non-poisoning rates, to effectively address data poisoning attacks while ensuring privacy is preserved by the proposed encryption scheme. Rigorous security, privacy, convergence, and experimental analyses have been provided to show that FheFL is novel, secure, and private, and achieves comparable accuracy at reasonable computational cost.