Search

Symmetry is crucial for gaining insights into the fundamental properties of physical systems, bringing possibilities in studying exotic phenomena such as quantum phase transitions and ground state entanglement. Here, we experimentally simulate a highly controllable extended quantum Rabi model, capable of tuning into the ultra-strong or deep coupling regime, in a spin-motion-coupled trapped ion. We observe that the phonon driven by such a model with parity symmetry preserved (broken) would experience double (single) excitation in the ultra-strong coupling regime. Quantum phenomena such as strong ground state entanglement and quantum superposition in systems occur with parity symmetry, and these phenomena disappear following the symmetry breaking. We also find sensitive responses for the two-level system entropy and phonon Wigner function in the deep coupling regime, depending on the parameter across the symmetry transition point. This work offers the prospect of exploring symmetry-controlled quantum phenomena and their applications in high-precision quantum technologies., Comment: 11 pages, 6 figures

Plastic scintillators are widely used for the detection of elementary particles, and 3D reconstruction of particle tracks is achieved by segmenting the detector into 3D granular structures. In this study, we present a novel prototype fabricated by additive manufacturing, consisting of a 5 x 5 x 5 array of 1 cm3 plastic scintillator cubes, each optically isolated. This innovative approach eliminates the need to construct complex monolithic geometries in a single operation and gets rid of the traditional time-consuming manufacturing and assembling processes. The prototype underwent performance characterization during a beam test at CERN's Proton-Synchrotron facility. Light yield, optical crosstalk, and light response uniformity, were evaluated. The prototype demonstrated a consistent light yield of approximately 27 photoelectrons (p.e.) per channel, similar to traditional cast scintillator detectors. Crosstalk between adjacent cubes averaged 4-5%, and light yield uniformity within individual cubes exhibited about 7% variation, indicating stability and reproducibility. These results underscore the potential of the novel additive manufacturing technique, for efficient and reliable production of high-granularity scintillator detectors.

The nontrivial degeneracies in non-Hermitian systems, exceptional points (EPs), have attracted extensive attention due to intriguing phenomena. Compared with commonly observed second-order EPs, high-order EPs show rich physics due to their extended dimension and parameter space, ranging from the coalescence of EPs into higher order to potential applications in topological properties. However, these features also pose challenges in controlling multiple coherent and dissipative elements in a scaled system. Here we experimentally demonstrate a native programmable control to simulate a high-order non-Hermitian Hamiltonian in a multi-dimensional trapped ion system. We simulate a series of non-Hermitian systems with varied parameters and observe the coalescence of second-order EPs into a fourth-order EP. Our results pave the way for scalable quantum simulation of high-dimensional dissipative systems and can be beneficial for the application of high-order EPs in quantum sensing and quantum control., Comment: 7 pages, 8 figures

The rapid advancement of generative models in creating highly realistic images poses substantial risks for misinformation dissemination. For instance, a synthetic image, when shared on social media, can mislead extensive audiences and erode trust in digital content, resulting in severe repercussions. Despite some progress, academia has not yet created a large and diversified deepfake detection dataset for social media, nor has it devised an effective solution to address this issue. In this paper, we introduce the Social media Image Detection dataSet (SID-Set), which offers three key advantages: (1) extensive volume, featuring 300K AI-generated/tampered and authentic images with comprehensive annotations, (2) broad diversity, encompassing fully synthetic and tampered images across various classes, and (3) elevated realism, with images that are predominantly indistinguishable from genuine ones through mere visual inspection. Furthermore, leveraging the exceptional capabilities of large multimodal models, we propose a new image deepfake detection, localization, and explanation framework, named SIDA (Social media Image Detection, localization, and explanation Assistant). SIDA not only discerns the authenticity of images, but also delineates tampered regions through mask prediction and provides textual explanations of the model's judgment criteria. Compared with state-of-the-art deepfake detection models on SID-Set and other benchmarks, extensive experiments demonstrate that SIDA achieves superior performance among diversified settings. The code, model, and dataset will be released.

The integration of Large Language Models (LLMs) into autonomous driving systems demonstrates strong common sense and reasoning abilities, effectively addressing the pitfalls of purely data-driven methods. Current LLM-based agents require lengthy inference times and face challenges in interacting with real-time autonomous driving environments. A key open question is whether we can effectively leverage the knowledge from LLMs to train an efficient and robust Reinforcement Learning (RL) agent. This paper introduces RAPID, a novel \underline{\textbf{R}}obust \underline{\textbf{A}}daptive \underline{\textbf{P}}olicy \underline{\textbf{I}}nfusion and \underline{\textbf{D}}istillation framework, which trains specialized mix-of-policy RL agents using data synthesized by an LLM-based driving agent and online adaptation. RAPID features three key designs: 1) utilization of offline data collected from an LLM agent to distil expert knowledge into RL policies for faster real-time inference; 2) introduction of robust distillation in RL to inherit both performance and robustness from LLM-based teacher; and 3) employment of a mix-of-policy approach for joint decision decoding with a policy adapter. Through fine-tuning via online environment interaction, RAPID reduces the forgetting of LLM knowledge while maintaining adaptability to different tasks. Extensive experiments demonstrate RAPID's capability to effectively integrate LLM knowledge into scaled-down RL policies in an efficient, adaptable, and robust way. Code and checkpoints will be made publicly available upon acceptance.

Text-to-Image (T2I) Diffusion Models (DMs) have garnered widespread attention for their impressive advancements in image generation. However, their growing popularity has raised ethical and social concerns related to key non-functional properties of trustworthiness, such as robustness, fairness, security, privacy, factuality, and explainability, similar to those in traditional deep learning (DL) tasks. Conventional approaches for studying trustworthiness in DL tasks often fall short due to the unique characteristics of T2I DMs, e.g., the multi-modal nature. Given the challenge, recent efforts have been made to develop new methods for investigating trustworthiness in T2I DMs via various means, including falsification, enhancement, verification \& validation and assessment. However, there is a notable lack of in-depth analysis concerning those non-functional properties and means. In this survey, we provide a timely and focused review of the literature on trustworthy T2I DMs, covering a concise-structured taxonomy from the perspectives of property, means, benchmarks and applications. Our review begins with an introduction to essential preliminaries of T2I DMs, and then we summarise key definitions/metrics specific to T2I tasks and analyses the means proposed in recent literature based on these definitions/metrics. Additionally, we review benchmarks and domain applications of T2I DMs. Finally, we highlight the gaps in current research, discuss the limitations of existing methods, and propose future research directions to advance the development of trustworthy T2I DMs. Furthermore, we keep up-to-date updates in this field to track the latest developments and maintain our GitHub repository at: https://github.com/wellzline/Trustworthy_T2I_DMs, Comment: under review

The vulnerability of machine learning models to Membership Inference Attacks (MIAs) has garnered considerable attention in recent years. These attacks determine whether a data sample belongs to the model's training set or not. Recent research has focused on reference-based attacks, which leverage difficulty calibration with independently trained reference models. While empirical studies have demonstrated its effectiveness, there is a notable gap in our understanding of the circumstances under which it succeeds or fails. In this paper, we take a further step towards a deeper understanding of the role of difficulty calibration. Our observations reveal inherent limitations in calibration methods, leading to the misclassification of non-members and suboptimal performance, particularly on high-loss samples. We further identify that these errors stem from an imperfect sampling of the potential distribution and a strong dependence of membership scores on the model parameters. By shedding light on these issues, we propose RAPID: a query-efficient and computation-efficient MIA that directly \textbf{R}e-lever\textbf{A}ges the original membershi\textbf{P} scores to m\textbf{I}tigate the errors in \textbf{D}ifficulty calibration. Our experimental results, spanning 9 datasets and 5 model architectures, demonstrate that RAPID outperforms previous state-of-the-art attacks (e.g., LiRA and Canary offline) across different metrics while remaining computationally efficient. Our observations and analysis challenge the current de facto paradigm of difficulty calibration in high-precision inference, encouraging greater attention to the persistent risks posed by MIAs in more practical scenarios., Comment: Accepted by ACM CCS 2024

Data efficiency of learning, which plays a key role in the Reinforcement Learning (RL) training process, becomes even more important in continual RL with sequential environments. In continual RL, the learner interacts with non-stationary, sequential tasks and is required to learn new tasks without forgetting previous knowledge. However, there is little work on implementing data augmentation for continual RL. In this paper, we investigate the efficacy of data augmentation for continual RL. Specifically, we provide benchmarking data augmentations for continual RL, by (1) summarising existing data augmentation methods and (2) including a new augmentation method for continual RL: Adversarial Augmentation with Gradient Episodic Memory (Adv-GEM). Extensive experiments show that data augmentations, such as random amplitude scaling, state-switch, mixup, adversarial augmentation, and Adv-GEM, can improve existing continual RL algorithms in terms of their average performance, catastrophic forgetting, and forward transfer, on robot control tasks. All data augmentation methods are implemented as plug-in modules for trivial integration into continual RL methods.

The deployment of generative AI (GenAI) models raises significant fairness concerns, addressed in this paper through novel characterization and enforcement techniques specific to GenAI. Unlike standard AI performing specific tasks, GenAI's broad functionality requires "conditional fairness" tailored to the context being generated, such as demographic fairness in generating images of poor people versus successful business leaders. We define two fairness levels: the first evaluates fairness in generated outputs, independent of prompts and models; the second assesses inherent fairness with neutral prompts. Given the complexity of GenAI and challenges in fairness specifications, we focus on bounding the worst case, considering a GenAI system unfair if the distance between appearances of a specific group exceeds preset thresholds. We also explore combinatorial testing for accessing relative completeness in intersectional fairness. By bounding the worst case, we develop a prompt injection scheme within an agent-based framework to enforce conditional fairness with minimal intervention, validated on state-of-the-art GenAI systems.

Quantum friction, a quantum analog of classical friction, reduces the performance of quantum machines, such as heat engines, and makes them less energy efficient. We here report the experimental realization of an energy efficient quantum engine coupled to a quantum battery that stores the produced work, using a single ion in a linear Paul trap. We first establish the quantum nature of the device by observing nonclassical work oscillations with the number of cycles as verified by energy measurements of the battery. We moreover successfully apply shortcut-to-adiabaticity techniques to suppress quantum friction and improve work production. While the average energy cost of the shortcut protocol is only about $3\%$, the work output is enhanced by up to approximately 33$\%$, making the machine significantly more energy efficient. In addition, we show that the quantum engine consistently outperforms its classical counterpart in this regime. Our results pave the way for energy efficient machines with quantum-enhanced performance.

Text-to-Image (T2I) Diffusion Models (DMs) have shown impressive abilities in generating high-quality images based on simple text descriptions. However, as is common with many Deep Learning (DL) models, DMs are subject to a lack of robustness. While there are attempts to evaluate the robustness of T2I DMs as a binary or worst-case problem, they cannot answer how robust in general the model is whenever an adversarial example (AE) can be found. In this study, we first introduce a probabilistic notion of T2I DMs' robustness; and then establish an efficient framework, ProTIP, to evaluate it with statistical guarantees. The main challenges stem from: i) the high computational cost of the generation process; and ii) determining if a perturbed input is an AE involves comparing two output distributions, which is fundamentally harder compared to other DL tasks like classification where an AE is identified upon misprediction of labels. To tackle the challenges, we employ sequential analysis with efficacy and futility early stopping rules in the statistical testing for identifying AEs, and adaptive concentration inequalities to dynamically determine the "just-right" number of stochastic perturbations whenever the verification target is met. Empirical experiments validate the effectiveness and efficiency of ProTIP over common T2I DMs. Finally, we demonstrate an application of ProTIP to rank commonly used defence methods., Comment: Accepted by ECCV24

Modeling and calibrating the fidelity of synthetic data is paramount in shaping the future of safe and reliable self-driving technology by offering a cost-effective and scalable alternative to real-world data collection. We focus on its role in safety-critical applications, introducing four types of instance-level fidelity that go beyond mere visual input characteristics. The aim is to ensure that applying testing on synthetic data can reveal real-world safety issues, and the absence of safety-critical issues when testing under synthetic data can provide a strong safety guarantee in real-world behavior. We suggest an optimization method to refine the synthetic data generator, reducing fidelity gaps identified by deep learning components. Experiments show this tuning enhances the correlation between safety-critical errors in synthetic and real data.

As Large Language Models (LLMs) become more integrated into our daily lives, it is crucial to identify and mitigate their risks, especially when the risks can have profound impacts on human users and societies. Guardrails, which filter the inputs or outputs of LLMs, have emerged as a core safeguarding technology. This position paper takes a deep look at current open-source solutions (Llama Guard, Nvidia NeMo, Guardrails AI), and discusses the challenges and the road towards building more complete solutions. Drawing on robust evidence from previous research, we advocate for a systematic approach to construct guardrails for LLMs, based on comprehensive consideration of diverse contexts across various LLMs applications. We propose employing socio-technical methods through collaboration with a multi-disciplinary team to pinpoint precise technical requirements, exploring advanced neural-symbolic implementations to embrace the complexity of the requirements, and developing verification and testing to ensure the utmost quality of the final product., Comment: Proceedings of the 41st International Conference on Machine Learning, Vienna, Austria. PMLR 235, 2024

Squeezing a quantum state along a specific direction has long been recognized as a crucial technique for enhancing the precision of quantum metrology by reducing parameter uncertainty. However, practical quantum metrology often involves the simultaneous estimation of multiple parameters, necessitating the use of high-quality squeezed states along multiple orthogonal axes to surpass the standard quantum limit for all relevant parameters. In addition, a temporally stabilized squeezed state can provide an event-ready probe for parameters, regardless of the initial state, and robust to the timing of the state preparation process once stabilized. In this work, we generate and stabilize a two-mode squeezed state along two secular motional modes in a vibrating trapped ion with reservoir engineering, despite starting from a thermal state of the motion. Leveraging this resource, we demonstrate an estimation of two simultaneous collective displacements along the squeezed axes, achieving improvements surpassing the classical limit by up to 6.9(3) and 7.0(3) decibels (dB), respectively. Our demonstration can be readily scaled to squeezed states with even more modes. The practical implications of our findings span a wide range of applications, including quantum sensing, quantum imaging, and various fields that demand precise measurements of multiple parameters.

While Goal-Conditioned Reinforcement Learning (GCRL) has gained attention, its algorithmic robustness against adversarial perturbations remains unexplored. The attacks and robust representation training methods that are designed for traditional RL become less effective when applied to GCRL. To address this challenge, we first propose the Semi-Contrastive Representation attack, a novel approach inspired by the adversarial contrastive attack. Unlike existing attacks in RL, it only necessitates information from the policy function and can be seamlessly implemented during deployment. Then, to mitigate the vulnerability of existing GCRL algorithms, we introduce Adversarial Representation Tactics, which combines Semi-Contrastive Adversarial Augmentation with Sensitivity-Aware Regularizer to improve the adversarial robustness of the underlying RL agent against various types of perturbations. Extensive experiments validate the superior performance of our attack and defence methods across multiple state-of-the-art GCRL algorithms. Our tool ReRoGCRL is available at https://github.com/TrustAI/ReRoGCRL., Comment: This paper has been accepted in AAAI24 (https://aaai.org/aaai-conference/)

Semantic segmentation of remote sensing imagery plays a pivotal role in extracting precise information for diverse down-stream applications. Recent development of the Segment Anything Model (SAM), an advanced general-purpose segmentation model, has revolutionized this field, presenting new avenues for accurate and efficient segmentation. However, SAM is limited to generating segmentation results without class information. Consequently, the utilization of such a powerful general vision model for semantic segmentation in remote sensing images has become a focal point of research. In this paper, we present a streamlined framework aimed at leveraging the raw output of SAM by exploiting two novel concepts called SAM-Generated Object (SGO) and SAM-Generated Boundary (SGB). More specifically, we propose a novel object loss and further introduce a boundary loss as augmentative components to aid in model optimization in a general semantic segmentation framework. Taking into account the content characteristics of SGO, we introduce the concept of object consistency to leverage segmented regions lacking semantic information. By imposing constraints on the consistency of predicted values within objects, the object loss aims to enhance semantic segmentation performance. Furthermore, the boundary loss capitalizes on the distinctive features of SGB by directing the model's attention to the boundary information of the object. Experimental results on two well-known datasets, namely ISPRS Vaihingen and LoveDA Urban, demonstrate the effectiveness of our proposed method. The source code for this work will be accessible at https://github.com/sstary/SSRS., Comment: 10 pages, 4 figures

Multi-label classification (MLC) refers to the problem of tagging a given instance with a set of relevant labels. Most existing MLC methods are based on the assumption that the correlation of two labels in each label pair is symmetric, which is violated in many real-world scenarios. Moreover, most existing methods design learning processes associated with the number of labels, which makes their computational complexity a bottleneck when scaling up to large-scale output space. To tackle these issues, we propose a novel method named Scalable Label Distribution Learning (SLDL) for multi-label classification which can describe different labels as distributions in a latent space, where the label correlation is asymmetric and the dimension is independent of the number of labels. Specifically, SLDL first converts labels into continuous distributions within a low-dimensional latent space and leverages the asymmetric metric to establish the correlation between different labels. Then, it learns the mapping from the feature space to the latent space, resulting in the computational complexity is no longer related to the number of labels. Finally, SLDL leverages a nearest-neighbor-based strategy to decode the latent representations and obtain the final predictions. Extensive experiments illustrate that SLDL achieves very competitive classification performances with little computational consumption.

Prior to the COVID-19 pandemic, the adoption of live polling and real-time feedback tools gained traction in higher education to enhance student engagement and learning outcomes. Integrating live polling activities has been shown to boost attention, participation, and understanding of course materials. However, recent changes in learning behaviours due to the pandemic necessitate a reevaluation of these active learning technologies. In this context, our study focuses on the Computer Science (CS) domain, investigating the impact of Live Polling Quizzes (LPQs) in undergraduate CS lectures. These quizzes comprise fact-based, formally defined questions with clear answers, aiming to enhance engagement, learning outcomes, and overall perceptions of the course module. A survey was conducted among 70 undergraduate CS students, attending CS modules with and without LPQs. The results revealed that while LPQs contributed to higher attendance, other factors likely influenced attendance rates more significantly. LPQs were generally viewed positively, aiding comprehension and maintaining student attention and motivation. However, careful management of LPQ frequency is crucial to prevent overuse for some students and potential reduced motivation. Clear instructions for using the polling software were also highlighted as essential., Comment: Submitted

Machine learning has made remarkable advancements, but confidently utilising learning-enabled components in safety-critical domains still poses challenges. Among the challenges, it is known that a rigorous, yet practical, way of achieving safety guarantees is one of the most prominent. In this paper, we first discuss the engineering and research challenges associated with the design and verification of such systems. Then, based on the observation that existing works cannot actually achieve provable guarantees, we promote a two-step verification method for the ultimate achievement of provable statistical guarantees.

Most image retrieval research prioritizes improving predictive performance, often overlooking situations where the reliability of predictions is equally important. The gap between model performance and reliability requirements highlights the need for a systematic approach to analyze and address the risks associated with image retrieval. Uncertainty quantification technique can be applied to mitigate this issue by assessing uncertainty for retrieval sets, but it provides only a heuristic estimate of uncertainty rather than a guarantee. To address these limitations, we present Risk Controlled Image Retrieval (RCIR), which generates retrieval sets with coverage guarantee, i.e., retrieval sets that are guaranteed to contain the true nearest neighbors with a predefined probability. RCIR can be easily integrated with existing uncertainty-aware image retrieval systems, agnostic to data distribution and model selection. To the best of our knowledge, this is the first work that provides coverage guarantees to image retrieval. The validity and efficiency of RCIR are demonstrated on four real-world datasets: CAR-196, CUB-200, Pittsburgh, and ChestX-Det.

Large Language Models (LLMs) have exploded a new heatwave of AI for their ability to engage end-users in human-level conversations with detailed and articulate answers across many knowledge domains. In response to their fast adoption in many industrial applications, this survey concerns their safety and trustworthiness. First, we review known vulnerabilities and limitations of the LLMs, categorising them into inherent issues, attacks, and unintended bugs. Then, we consider if and how the Verification and Validation (V&V) techniques, which have been widely developed for traditional software and deep learning models such as convolutional neural networks as independent processes to check the alignment of their implementations against the specifications, can be integrated and further extended throughout the lifecycle of the LLMs to provide rigorous analysis to the safety and trustworthiness of LLMs and their applications. Specifically, we consider four complementary techniques: falsification and evaluation, verification, runtime monitoring, and regulations and ethical use. In total, 370+ references are considered to support the quick understanding of the safety and trustworthiness issues from the perspective of V&V. While intensive research has been conducted to identify the safety and trustworthiness issues, rigorous yet practical methods are called for to ensure the alignment of LLMs with safety and trustworthiness requirements.

Can safety analysis make use of Large Language Models (LLMs)? A case study explores Systems Theoretic Process Analysis (STPA) applied to Automatic Emergency Brake (AEB) and Electricity Demand Side Management (DSM) systems using ChatGPT. We investigate how collaboration schemes, input semantic complexity, and prompt guidelines influence STPA results. Comparative results show that using ChatGPT without human intervention may be inadequate due to reliability related issues, but with careful design, it may outperform human experts. No statistically significant differences are found when varying the input semantic complexity or using common prompt guidelines, which suggests the necessity for developing domain-specific prompt engineering. We also highlight future challenges, including concerns about LLM trustworthiness and the necessity for standardisation and regulation in this domain., Comment: Under Review

Autonomous robots used in infrastructure inspection, space exploration and other critical missions operate in highly dynamic environments. As such, they must continually verify their ability to complete the tasks associated with these missions safely and effectively. Here we present a Bayesian learning framework that enables this runtime verification of autonomous robots. The framework uses prior knowledge and observations of the verified robot to learn expected ranges for the occurrence rates of regular and singular (e.g., catastrophic failure) events. Interval continuous-time Markov models defined using these ranges are then analysed to obtain expected intervals of variation for system properties such as mission duration and success probability. We apply the framework to an autonomous robotic mission for underwater infrastructure inspection and repair. The formal proofs and experiments presented in the paper show that our framework produces results that reflect the uncertainty intrinsic to many real-world systems, enabling the robust verification of their quantitative properties under parametric uncertainty., Comment: Accepted by Communications Engineering

Systems Theoretic Process Analysis (STPA) is a systematic approach for hazard analysis that has been used across many industrial sectors including transportation, energy, and defense. The unstoppable trend of using Machine Learning (ML) in safety-critical systems has led to the pressing need of extending STPA to Learning-Enabled Systems (LESs). Although works have been carried out on various example LESs, without a systematic review, it is unclear how effective and generalisable the extended STPA methods are, and whether further improvements can be made. To this end, we present a systematic survey of 31 papers, summarising them from five perspectives (attributes of concern, objects under study, modifications, derivatives and processes being modelled). Furthermore, we identify room for improvement and accordingly introduce DeepSTPA, which enhances STPA from two aspects that are missing from the state-of-the-practice: (i) Control loop structures are explicitly extended to identify hazards from the data-driven development process spanning the ML lifecycle; (ii) Fine-grained functionalities are modelled at the layer-wise levels of ML models to detect root causes. We demonstrate and compare DeepSTPA and STPA through a case study on an autonomous emergency braking system., Comment: Accepted by the 26th IEEE Int. Conf. on Intelligent Transportation Systems (ITSC'23), 8 pages

Multi-robot cooperative control has gained extensive research interest due to its wide applications in civil, security, and military domains. This paper proposes a cooperative control algorithm for multi-robot systems with general linear dynamics. The algorithm is based on distributed cooperative optimisation and output regulation, and it achieves global optimum by utilising only information shared among neighbouring robots. Technically, a high-level distributed optimisation algorithm for multi-robot systems is presented, which will serve as an optimal reference generator for each individual agent. Then, based on the distributed optimisation algorithm, an output regulation method is utilised to solve the optimal coordination problem for general linear dynamic systems. The convergence of the proposed algorithm is theoretically proved. Both numerical simulations and real-time physical robot experiments are conducted to validate the effectiveness of the proposed cooperative control algorithms., Comment: Accepted by AAMAS'23

Automatic intracranial hemorrhage segmentation in 3D non-contrast head CT (NCCT) scans is significant in clinical practice. Existing hemorrhage segmentation methods usually ignores the anisotropic nature of the NCCT, and are evaluated on different in-house datasets with distinct metrics, making it highly challenging to improve segmentation performance and perform objective comparisons among different methods. The INSTANCE 2022 was a grand challenge held in conjunction with the 2022 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI). It is intended to resolve the above-mentioned problems and promote the development of both intracranial hemorrhage segmentation and anisotropic data processing. The INSTANCE released a training set of 100 cases with ground-truth and a validation set with 30 cases without ground-truth labels that were available to the participants. A held-out testing set with 70 cases is utilized for the final evaluation and ranking. The methods from different participants are ranked based on four metrics, including Dice Similarity Coefficient (DSC), Hausdorff Distance (HD), Relative Volume Difference (RVD) and Normalized Surface Dice (NSD). A total of 13 teams submitted distinct solutions to resolve the challenges, making several baseline models, pre-processing strategies and anisotropic data processing techniques available to future researchers. The winner method achieved an average DSC of 0.6925, demonstrating a significant growth over our proposed baseline method. To the best of our knowledge, the proposed INSTANCE challenge releases the first intracranial hemorrhage segmentation benchmark, and is also the first challenge that intended to resolve the anisotropic problem in 3D medical image segmentation, which provides new alternatives in these research fields., Comment: Summarized paper for the MICCAI INSTANCE 2022 Challenge

In this article, we use artificial intelligence algorithms to show how to enhance the resolution of the elementary particle track fitting in inhomogeneous dense detectors, such as plastic scintillators. We use deep learning to replace more traditional Bayesian filtering methods, drastically improving the reconstruction of the interacting particle kinematics. We show that a specific form of neural network, inherited from the field of natural language processing, is very close to the concept of a Bayesian filter that adopts a hyper-informative prior. Such a paradigm change can influence the design of future particle physics experiments and their data exploitation.

Deep Reinforcement Learning (DRL) has achieved impressive performance in robotics and autonomous systems (RAS). A key challenge to its deployment in real-life operations is the presence of spuriously unsafe DRL policies. Unexplored states may lead the agent to make wrong decisions that could result in hazards, especially in applications where DRL-trained end-to-end controllers govern the behaviour of RAS. This paper proposes a novel quantitative reliability assessment framework for DRL-controlled RAS, leveraging verification evidence generated from formal reliability analysis of neural networks. A two-level verification framework is introduced to check the safety property with respect to inaccurate observations that are due to, e.g., environmental noise and state changes. Reachability verification tools are leveraged locally to generate safety evidence of trajectories. In contrast, at the global level, we quantify the overall reliability as an aggregated metric of local safety evidence, corresponding to a set of distinct tasks and their occurrence probabilities. The effectiveness of the proposed verification framework is demonstrated and validated via experiments on real RAS.

Interpretability of Deep Learning (DL) is a barrier to trustworthy AI. Despite great efforts made by the Explainable AI (XAI) community, explanations lack robustness -- indistinguishable input perturbations may lead to different XAI results. Thus, it is vital to assess how robust DL interpretability is, given an XAI method. In this paper, we identify several challenges that the state-of-the-art is unable to cope with collectively: i) existing metrics are not comprehensive; ii) XAI techniques are highly heterogeneous; iii) misinterpretations are normally rare events. To tackle these challenges, we introduce two black-box evaluation methods, concerning the worst-case interpretation discrepancy and a probabilistic notion of how robust in general, respectively. Genetic Algorithm (GA) with bespoke fitness function is used to solve constrained optimisation for efficient worst-case evaluation. Subset Simulation (SS), dedicated to estimate rare event probabilities, is used for evaluating overall robustness. Experiments show that the accuracy, sensitivity, and efficiency of our methods outperform the state-of-the-arts. Finally, we demonstrate two applications of our methods: ranking robust XAI methods and selecting training schemes to improve both classification and interpretation robustness., Comment: Accepted by the IEEE/CVF International Conference on Computer Vision 2023 (ICCV'23)

This paper presents Bayesian techniques for conservative claims about software reliability, particularly when evidence suggests the software's executions are not statistically independent. We formalise informal notions of "doubting" that the executions are independent, and incorporate such doubts into reliability assessments. We develop techniques that reveal the extent to which independence assumptions can undermine conservatism in assessments, and identify conditions under which this impact is not significant. These techniques - novel extensions of conservative Bayesian inference (CBI) approaches - give conservative confidence bounds on the software's failure probability per execution. With illustrations in two application areas - nuclear power-plant safety and autonomous vehicle (AV) safety - our analyses reveals: 1) the confidence an assessor should possess before subjecting a system to operational testing. Otherwise, such testing is futile - favourable operational testing evidence will eventually decrease one's confidence in the system being sufficiently reliable; 2) the independence assumption supports conservative claims sometimes; 3) in some scenarios, observing a system operate without failure gives less confidence in the system than if some failures had been observed; 4) building confidence in a system is very sensitive to failures - each additional failure means significantly more operational testing is required, in order to support a reliability claim., Comment: Accepted by Quality and Reliability Engineering International

With the employment of smart meters, massive data on consumer behaviour can be collected by retailers. From the collected data, the retailers may obtain the household profile information and implement demand response. While retailers prefer to acquire a model as accurate as possible among different customers, there are two major challenges. First, different retailers in the retail market do not share their consumer's electricity consumption data as these data are regarded as their assets, which has led to the problem of data island. Second, the electricity load data are highly heterogeneous since different retailers may serve various consumers. To this end, a fully distributed short-term load forecasting framework based on a consensus algorithm and Long Short-Term Memory (LSTM) is proposed, which may protect the customer's privacy and satisfy the accurate load forecasting requirement. Specifically, a fully distributed learning framework is exploited for distributed training, and a consensus technique is applied to meet confidential privacy. Case studies show that the proposed method has comparable performance with centralised methods regarding the accuracy, but the proposed method shows advantages in training speed and data privacy., Comment: 5 pages, 4 figures, 2023 ISGT-NA

When assessing a software-based system, the results of Bayesian statistical inference on operational testing data can provide strong support for software reliability claims. For inference, this data (i.e. software successes and failures) is often assumed to arise in an independent, identically distributed (i.i.d.) manner. In this paper we show how conservative Bayesian approaches make this assumption unnecessary, by incorporating one's doubts about the assumption into the assessment. We derive conservative confidence bounds on a system's probability of failure on demand (pfd), when operational testing reveals no failures. The generality and utility of the confidence bounds are illustrated in the assessment of a nuclear power-plant safety-protection system, under varying levels of skepticism about the i.i.d. assumption. The analysis suggests that the i.i.d. assumption can make Bayesian reliability assessments extremely optimistic - such assessments do not explicitly account for how software can be very likely to exhibit no failures during extensive operational testing despite the software's pfd being undesirably large., Comment: Accepted by IEEE Transactions on Software Engineering

Hazard and Operability Analysis (HAZOP) is a powerful safety analysis technique with a long history in industrial process control domain. With the increasing use of Machine Learning (ML) components in cyber physical systems--so called Learning-Enabled Systems (LESs), there is a recent trend of applying HAZOP-like analysis to LESs. While it shows a great potential to reserve the capability of doing sufficient and systematic safety analysis, there are new technical challenges raised by the novel characteristics of ML that require retrofit of the conventional HAZOP technique. In this regard, we present a new Hierarchical HAZOP-Like method for LESs (HILLS). To deal with the complexity of LESs, HILLS first does "divide and conquer" by stratifying the whole system into three levels, and then proceeds HAZOP on each level to identify (latent-)hazards, causes, security threats and mitigation (with new nodes and guide words). Finally, HILLS attempts at linking and propagating the causal relationship among those identified elements within and across the three levels via both qualitative and quantitative methods. We examine and illustrate the utility of HILLS by a case study on Autonomous Underwater Vehicles, with discussions on assumptions and extensions to real-world applications. HILLS, as a first HAZOP-like attempt on LESs that explicitly considers ML internal behaviours and its interactions with other components, not only uncovers the inherent difficulties of doing safety analysis for LESs, but also demonstrates a good potential to tackle them., Comment: Accepted by the AISafety2022 Workshop at IJCAI2022. To appear in a volume of CEUR Workshop Proceedings

Deep Learning (DL) is increasingly used in safety-critical applications, raising concerns about its reliability. DL suffers from a well-known problem of lacking robustness, especially when faced with adversarial perturbations known as Adversarial Examples (AEs). Despite recent efforts to detect AEs using advanced attack and testing methods, these approaches often overlook the input distribution and perceptual quality of the perturbations. As a result, the detected AEs may not be relevant in practical applications or may appear unrealistic to human observers. This can waste testing resources on rare AEs that seldom occur during real-world use, limiting improvements in DL model dependability. In this paper, we propose a new robustness testing approach for detecting AEs that considers both the feature level distribution and the pixel level distribution, capturing the perceptual quality of adversarial perturbations. The two considerations are encoded by a novel hierarchical mechanism. First, we select test seeds based on the density of feature level distribution and the vulnerability of adversarial robustness. The vulnerability of test seeds are indicated by the auxiliary information, that are highly correlated with local robustness. Given a test seed, we then develop a novel genetic algorithm based local test case generation method, in which two fitness functions work alternatively to control the perceptual quality of detected AEs. Finally, extensive experiments confirm that our holistic approach considering hierarchical distributions is superior to the state-of-the-arts that either disregard any input distribution or only consider a single (non-hierarchical) distribution, in terms of not only detecting imperceptible AEs but also improving the overall robustness of the DL model under testing., Comment: Accepted by ACM Transactions on Software Engineering and Methodology (TOSEM)