AI systems can take harmful actions and are highly vulnerable to adversarial attacks.

AI systems can take harmful actions and are highly vulnerable to adversarial attacks. We present an approach, inspired by recent advances in representation engineering, that interrupts the models as they respond with harmful outputs with circuit breakers. Existing techniques aimed at improving alignment, such as refusal training, are often bypassed. Techniques such as adversarial training try to plug these holes by countering specific attacks. As an alternative to refusal training and adversarial training, circuit-breaking directly controls the representations that are responsible for harmful outputs in the first place. Our technique can be applied to both text-only and multimodal language models to prevent the generation of harmful outputs without sacrificing utility -- even in the presence of powerful unseen attacks. Notably, while adversarial robustness in standalone image recognition remains an open challenge, circuit breakers allow the larger multimodal system to reliably withstand image hijacks that aim to produce harmful content. Finally, we extend our approach to AI agents, demonstrating considerable reductions in the rate of harmful actions when they are under attack. Our approach represents a significant step forward in the development of reliable safeguards to harmful behavior and adversarial attacks.

AI systems can take harmful actions and are highly vulnerable to adversarial attacks.

Commercial high-voltage circuit breaker (CB) condition monitoring systems rely on directly observable physical parameters such as gas filling pressure with pre-defined thresholds. While these parameters are crucial, they only cover a small subset of malfunctioning mechanisms and usually can be monitored only if the CB is disconnected from the grid. To facilitate online condition monitoring while CBs remain connected, non-intrusive measurement techniques such as vibration or acoustic signals are necessary. Currently, CB condition monitoring studies using these signals typically utilize supervised methods for fault diagnostics, where ground-truth fault types are known due to artificially introduced faults in laboratory settings. This supervised approach is however not feasible in real-world applications, where fault labels are unavailable. In this work, we propose a novel unsupervised fault detection and segmentation framework for CBs based on vibration and acoustic signals. This framework can detect deviations from the healthy state. The explainable artificial intelligence (XAI) approach is applied to the detected faults for fault diagnostics. The specific contributions are: (1) we propose an integrated unsupervised fault detection and segmentation framework that is capable of detecting faults and clustering different faults with only healthy data required during training (2) we provide an unsupervised explainability-guided fault diagnostics approach using XAI to offer domain experts potential indications of the aged or faulty components, achieving fault diagnostics without the prerequisite of ground-truth fault labels. These contributions are validated using an experimental dataset from a high-voltage CB under healthy and artificially introduced fault conditions, contributing to more reliable CB system operation.

AI systems can take harmful actions and are highly vulnerable to adversarial attacks. We present an approach, inspired by recent advances in representation engineering, that interrupts the models as they respond with harmful outputs with "circuit breakers." Existing techniques aimed at improving alignment, such as refusal training, are often bypassed. Techniques such as adversarial training try to plug these holes by countering specific attacks. As an alternative to refusal training and adversarial training, circuit-breaking directly controls the representations that are responsible for harmful outputs in the first place.

Integrating Retrieval Augmented Generation (RAG) with Large Language Models (LLMs) has shown the potential to provide precise, contextually relevant responses in knowledge intensive domains. This study investigates th e ap - plication of RAG for ABB circuit breakers, focusing on accuracy, reliability, and contextual relevance in high - stakes engineering environments. By leveraging tailored datasets, advanced embedding models, and optimized chunking strategies, the research addresses challenges in data retrieval and contextual alignment unique to engineering documentation. Key contributions include the development of a domain - specific dataset for ABB circuit breakers and the evaluation of three RAG pipelines: OpenAI GPT4o, C ohere, and Anthropic Claude. Advanced chunking methods, such as paragraph - based and title - aware segmentation, are assessed for their impact on retrieval accuracy and response generation. Results demonstrate that while certain configurations achieve high pr ecision and relevancy, limitations persist in ensuring factual faithfulness and completeness, critical in engineering contexts. This work underscores the need for iterative improvements in RAG systems to meet the stringent demands of electrical engineering tasks, including design, troubleshooting, and operational decision - making. The findings in this paper help advance research of AI in highly technical domains such as electrical engineering. Electrical engineering is a cornerstone of modern infrastructure, underpin n ing systems that power cities, enable communication, and drive technological innovation. From power generation and distribution to the design of advanced electronic systems, electrical engineering plays a vital role in ensuring the reliability, efficiency, and safety of critical infrastructure [1]. Mistakes or inaccuracies in the design, operation, or maintenance of e lectrical systems can have far - reaching consequences, including equipment failure, financial losses, and risks to public safety. In such high - stakes environments, precision and reliability in accessing accurate technical information are paramount [2]. Sim ilarly, in medicine, iterative retrieval methods have been proposed to enhance the accuracy of RAG systems. Xiong et al. [3] introduced the i - MedRAG system, which dynamically generates follow - up queries to refine responses. This approach improved retrieval accuracy and generalizability, although it incurred higher computational costs.

AI systems can take harmful actions and are highly vulnerable to adversarial attacks. We present an approach, inspired by recent advances in representation engineering, that interrupts the models as they respond with harmful outputs with "circuit breakers." Existing techniques aimed at improving alignment, such as refusal training, are often bypassed. Techniques such as adversarial training try to plug these holes by countering specific attacks. As an alternative to refusal training and adversarial training, circuit-breaking directly controls the representations that are responsible for harmful outputs in the first place. Our technique can be applied to both text-only and multimodal language models to prevent the generation of harmful outputs without sacrificing utility -- even in the presence of powerful unseen attacks. Notably, while adversarial robustness in standalone image recognition remains an open challenge, circuit breakers allow the larger multimodal system to reliably withstand image "hijacks" that aim to produce harmful content. Finally, we extend our approach to AI agents, demonstrating considerable reductions in the rate of harmful actions when they are under attack. Our approach represents a significant step forward in the development of reliable safeguards to harmful behavior and adversarial attacks.

The pre-insertion resistors (PIR) within high-voltage circuit breakers are critical components and warm up by generating Joule heat when an electric current flows through them. Elevated temperature can lead to temporary closure failure and, in severe cases, the rupture of PIR. To accurately predict the temperature of PIR, this study combines finite element simulation techniques with Support Vector Regression (SVR) optimized by an Improved Whale Optimization Algorithm (IWOA) approach. The IWOA includes Tent mapping, a convergence factor based on the sigmoid function, and the Ornstein-Uhlenbeck variation strategy. The IWOA-SVR model is compared with the SSA-SVR and WOA-SVR. The results reveal that the prediction accuracies of the IWOA-SVR model were 90.2% and 81.5% (above 100$^\circ$C) in the 3$^\circ$C temperature deviation range and 96.3% and 93.4% (above 100$^\circ$C) in the 4$^\circ$C temperature deviation range, surpassing the performance of the comparative models. This research demonstrates the method proposed can realize the online monitoring of the temperature of the PIR, which can effectively prevent thermal faults PIR and provide a basis for the opening and closing of the circuit breaker within a short period.

API economy is driving the digital transformation of business applications across the hybrid Cloud and edge environments. For such transformations to succeed, end-to-end testing of the application API composition is required. Testing of API compositions, even in centralized Cloud environments, is challenging as it requires coverage of functional as well as reliability requirements. The combinatorial space of scenarios is huge, e.g., API input parameters, order of API execution, and network faults. Hybrid Cloud and edge environments exacerbate the challenge of API testing due to the need to coordinate test execution across dynamic wide-area networks, possibly across network boundaries. To handle this challenge, we envision a test framework named Distributed Software Test Kit (DSTK). The DSTK leverages Combinatorial Test Design (CTD) to cover the functional requirements and then automatically covers the reliability requirements via under-the-hood closed loop between test execution feedback and AI based search algorithms. In each iteration of the closed loop, the search algorithms generate more reliability test scenarios to be executed next. Specifically, five kinds of reliability tests are envisioned: out-of-order execution of APIs, network delays and faults, API performance and throughput, changes in API call graph patterns, and changes in application topology.

At the start of the Circuit Breaker, NParks enforced safe distancing measures at all its parks, gardens and nature reserves, including Park Connectors, Pulau Ubin and parks managed by town councils. This includes crowd estimation and park patrols at these green spaces, which can be laborious and tedious, especially for large public spaces. And this work is very much limited by manpower constraints. To address this problem, NParks rapidly developed a Safe Distance @ Parks website within a short span of 3.5 days for the public to access the park visitorship status. Further to that, the team partnered with GovTech's Data Science and AI Division (DSAID) which set up a squad of 1 AI Engineer, 1 DevOps Engineer and 1 Engagement manager to work out a solution to extract the visitor count from CCTV snapshots and automatically update the Safe Distance @ Parks portal in less than two weeks.