Search

The advent of Large Language Models (LLMs) has enabled the development of LLM agents capable of autonomously achieving under-specified goals and continuously evolving through post-deployment improvement, sometimes without requiring code or model updates. Conventional approaches, such as pre-defined test cases and code/model redevelopment pipelines, are inadequate for addressing the unique challenges of LLM agent development, particularly in terms of quality and risk control. This paper introduces an evaluation-driven design approach, inspired by test-driven development, to address these challenges. Through a multivocal literature review (MLR), we synthesize existing LLM evaluation methods and propose a novel process model and reference architecture specifically designed for LLM agents. The proposed approach integrates online and offline evaluations to support adaptive runtime adjustments and systematic offline redevelopment, improving runtime pipelines, artifacts, system architecture, and LLMs by continuously incorporating evaluation results, including fine-grained feedback from human and AI evaluators.

Utilising quantum computing technology to enhance artificial intelligence systems is expected to improve training and inference times, increase robustness against noise and adversarial attacks, and reduce the number of parameters without compromising accuracy. However, moving beyond proof-of-concept or simulations to develop practical applications of these systems while ensuring high software quality faces significant challenges due to the limitations of quantum hardware and the underdeveloped knowledge base in software engineering for such systems. In this work, we have conducted a systematic mapping study to identify the challenges and solutions associated with the software architecture of quantum-enhanced artificial intelligence systems. Our review uncovered several architectural patterns that describe how quantum components can be integrated into inference engines, as well as middleware patterns that facilitate communication between classical and quantum components. These insights have been compiled into a catalog of architectural patterns. Each pattern realises a trade-off between efficiency, scalability, trainability, simplicity, portability and deployability, and other software quality attributes.

The ever-improving quality of LLMs has fueled the growth of a diverse range of downstream tasks, leading to an increased demand for AI automation and a burgeoning interest in developing foundation model (FM)-based autonomous agents. As AI agent systems tackle more complex tasks and evolve, they involve a wider range of stakeholders, including agent users, agentic system developers and deployers, and AI model developers. These systems also integrate multiple components such as AI agent workflows, RAG pipelines, prompt management, agent capabilities, and observability features. In this case, obtaining reliable outputs and answers from these agents remains challenging, necessitating a dependable execution process and end-to-end observability solutions. To build reliable AI agents and LLM applications, it is essential to shift towards designing AgentOps platforms that ensure observability and traceability across the entire development-to-production life-cycle. To this end, we conducted a rapid review and identified relevant AgentOps tools from the agentic ecosystem. Based on this review, we provide an overview of the essential features of AgentOps and propose a comprehensive overview of observability data/traceable artifacts across the agent production life-cycle. Our findings provide a systematic overview of the current AgentOps landscape, emphasizing the critical role of observability/traceability in enhancing the reliability of autonomous agent systems., Comment: 19 pages, 9 figures

The rise of Large Language Models (LLMs) has streamlined frontend interface creation through tools like Vercel's V0, yet surfaced challenges in design quality (e.g., accessibility, and usability). Current solutions, often limited by their focus, generalisability, or data dependency, fall short in addressing these complexities. Moreover, none of them examine the quality of LLM-generated UI design. In this work, we introduce DesignRepair, a novel dual-stream design guideline-aware system to examine and repair the UI design quality issues from both code aspect and rendered page aspect. We utilised the mature and popular Material Design as our knowledge base to guide this process. Specifically, we first constructed a comprehensive knowledge base encoding Google's Material Design principles into low-level component knowledge base and high-level system design knowledge base. After that, DesignRepair employs a LLM for the extraction of key components and utilizes the Playwright tool for precise page analysis, aligning these with the established knowledge bases. Finally, we integrate Retrieval-Augmented Generation with state-of-the-art LLMs like GPT-4 to holistically refine and repair frontend code through a strategic divide and conquer approach. Our extensive evaluations validated the efficacy and utility of our approach, demonstrating significant enhancements in adherence to design guidelines, accessibility, and user experience metrics., Comment: Accepted to 47nd International Conference on Software Engineering

As Artificial Intelligence (AI) becomes integral to business operations, integrating Responsible AI (RAI) within Environmental, Social, and Governance (ESG) frameworks is essential for ethical and sustainable AI deployment. This study examines how leading companies align RAI with their ESG goals. Through interviews with 28 industry leaders, we identified a strong link between RAI and ESG practices. However, a significant gap exists between internal RAI policies and public disclosures, highlighting the need for greater board-level expertise, robust governance, and employee engagement. We provide key recommendations to strengthen RAI strategies, focusing on transparency, cross-functional collaboration, and seamless integration into existing ESG frameworks., Comment: 10 pages, 1 table, 1 figure

The rapid advancement of AI technology has led to widespread applications of agent systems across various domains. However, the need for detailed architecture design poses significant challenges in designing and operating these systems. This paper introduces a taxonomy focused on the architectures of foundation-model-based agents, addressing critical aspects such as functional capabilities and non-functional qualities. We also discuss the operations involved in both design-time and run-time phases, providing a comprehensive view of architectural design and operational characteristics. By unifying and detailing these classifications, our taxonomy aims to improve the design of foundation-model-based agents. Additionally, the paper establishes a decision model that guides critical design and runtime decisions, offering a structured approach to enhance the development of foundation-model-based agents. Our contributions include providing a structured architecture design option and guiding the development process of foundation-model-based agents, thereby addressing current fragmentation in the field., Comment: Under review

Foundation Model (FM)-based agents are revolutionizing application development across various domains. However, their rapidly growing capabilities and autonomy have raised significant concerns about AI safety. Researchers are exploring better ways to design guardrails to ensure that the runtime behavior of FM-based agents remains within specific boundaries. Nevertheless, designing effective runtime guardrails is challenging due to the agents' autonomous and non-deterministic behavior. The involvement of multiple pipeline stages and agent artifacts, such as goals, plans, tools, at runtime further complicates these issues. Addressing these challenges at runtime requires multi-layered guardrails that operate effectively at various levels of the agent architecture. Thus, in this paper, we present a comprehensive taxonomy of runtime guardrails for FM-based agents to identify the key quality attributes for guardrails and design dimensions based on the results of a systematic literature review. Inspired by the Swiss Cheese Model, we also propose a reference architecture for designing multi-layered runtime guardrails for FM-based agents, which includes three dimensions: quality attributes, pipelines, and artifacts. The proposed taxonomy and reference architecture provide concrete and robust guidance for researchers and practitioners to build AI-safety-by-design from a software architecture perspective., Comment: 17 Pages

The rapid growth of Artificial Intelligence (AI) has underscored the urgent need for responsible AI practices. Despite increasing interest, a comprehensive AI risk assessment toolkit remains lacking. This study introduces our Responsible AI (RAI) Question Bank, a comprehensive framework and tool designed to support diverse AI initiatives. By integrating AI ethics principles such as fairness, transparency, and accountability into a structured question format, the RAI Question Bank aids in identifying potential risks, aligning with emerging regulations like the EU AI Act, and enhancing overall AI governance. A key benefit of the RAI Question Bank is its systematic approach to linking lower-level risk questions to higher-level ones and related themes, preventing siloed assessments and ensuring a cohesive evaluation process. Case studies illustrate the practical application of the RAI Question Bank in assessing AI projects, from evaluating risk factors to informing decision-making processes. The study also demonstrates how the RAI Question Bank can be used to ensure compliance with standards, mitigate risks, and promote the development of trustworthy AI systems. This work advances RAI by providing organizations with a valuable tool to navigate the complexities of ethical AI development and deployment while ensuring comprehensive risk management., Comment: 30 pages, 6 tables, 14 figures

Artificial Intelligence (AI) is a widely developed and adopted technology across entire industry sectors. Integrating environmental, social, and governance (ESG) considerations with AI investments is crucial for ensuring ethical and sustainable technological advancement. Particularly from an investor perspective, this integration not only mitigates risks but also enhances long-term value creation by aligning AI initiatives with broader societal goals. Yet, this area has been less explored in both academia and industry. To bridge the gap, we introduce a novel ESG-AI framework, which is developed based on insights from engagements with 28 companies and comprises three key components. The framework provides a structured approach to this integration, developed in collaboration with industry practitioners. The ESG-AI framework provides an overview of the environmental and social impacts of AI applications, helping users such as investors assess the materiality of AI use. Moreover, it enables investors to evaluate a company's commitment to responsible AI through structured engagements and thorough assessment of specific risk areas. We have publicly released the framework and toolkit in April 2024, which has received significant attention and positive feedback from the investment community. This paper details each component of the framework, demonstrating its applicability in real-world contexts and its potential to guide ethical AI investments., Comment: 23 pages, 8 tables, 10 figures

Workloads in data processing clusters are often represented in the form of DAG (Directed Acyclic Graph) jobs. Scheduling DAG jobs is challenging. Simple heuristic scheduling algorithms are often adopted in practice in production data centres. There is much room for scheduling performance optimisation for cost saving. Recently, reinforcement learning approaches (like decima) have been attempted to optimise DAG job scheduling and demonstrate clear performance gain in comparison to traditional algorithms. However, reinforcement learning (RL) approaches face their own problems in real-world deployment. In particular, their black-box decision making processes and generalizability in unseen workloads may add a non-trivial burden to the cluster administrators. Moreover, adapting RL models on unseen workloads often requires significant amount of training data, which leaves edge cases run in a sub-optimal mode. To fill the gap, we propose a new method to distill a simple scheduling policy based on observations of the behaviours of a complex deep learning model. The simple model not only provides interpretability of scheduling decisions, but also adaptive to edge cases easily through tuning. We show that our method achieves high fidelity to the decisions made by deep learning models and outperforms these models when additional heuristics are taken into account., Comment: 20 pages, 18 figures

Recent studies indicate that large multimodal models (LMMs) potentially act as general-purpose assistants and are highly robust against different distributions. Despite this, domain-specific adaptation is still necessary particularly in specialized areas like healthcare. Due to the impracticality of fine-tuning LMMs given their vast parameter space, this work investigates in-context learning (ICL) as an effective alternative for enhancing LMMs' adaptability. Our study addresses this by evaluating an unsupervised ICL method which selects in-context examples through a nearest example search based on feature similarity. We uncover that its effectiveness is limited by the deficiencies of pre-trained vision encoders under distribution shift scenarios. To address these challenges, we propose InvariantSelectPR, a novel method leveraging Class-conditioned Contrastive Invariance (CCI) for more robust demonstration selection. Specifically, CCI enhances pre-trained vision encoders by improving their discriminative capabilities across different classes and ensuring invariance to domain-specific variations. This enhancement allows the encoders to effectively identify and retrieve the most informative examples, which are then used to guide LMMs in adapting to new query samples under varying distributions. Our experiments show that InvariantSelectPR substantially improves the adaptability of LMMs, achieving significant performance gains on benchmark datasets, with a 34.2%$\uparrow$ accuracy increase in 7-shot on Camelyon17 and 16.9%$\uparrow$ increase in 7-shot on HAM10000 compared to the baseline zero-shot performance., Comment: 10 pages, 9 figures, 7 tables

Foundation model-enabled generative artificial intelligence facilitates the development and implementation of agents, which can leverage distinguished reasoning and language processing capabilities to takes a proactive, autonomous role to pursue users' goals. Nevertheless, there is a lack of systematic knowledge to guide practitioners in designing the agents considering challenges of goal-seeking (including generating instrumental goals and plans), such as hallucinations inherent in foundation models, explainability of reasoning process, complex accountability, etc. To address this issue, we have performed a systematic literature review to understand the state-of-the-art foundation model-based agents and the broader ecosystem. In this paper, we present a pattern catalogue consisting of 18 architectural patterns with analyses of the context, forces, and trade-offs as the outcomes from the previous literature review. We propose a decision model for selecting the patterns. The proposed catalogue can provide holistic guidance for the effective use of patterns, and support the architecture design of foundation model-based agents by facilitating goal-seeking and plan generation.

The exploitation of publicly accessible data has led to escalating concerns regarding data privacy and intellectual property (IP) breaches in the age of artificial intelligence. To safeguard both data privacy and IP-related domain knowledge, efforts have been undertaken to render shared data unlearnable for unauthorized models in the wild. Existing methods apply empirically optimized perturbations to the data in the hope of disrupting the correlation between the inputs and the corresponding labels such that the data samples are converted into Unlearnable Examples (UEs). Nevertheless, the absence of mechanisms to verify the robustness of UEs against uncertainty in unauthorized models and their training procedures engenders several under-explored challenges. First, it is hard to quantify the unlearnability of UEs against unauthorized adversaries from different runs of training, leaving the soundness of the defense in obscurity. Particularly, as a prevailing evaluation metric, empirical test accuracy faces generalization errors and may not plausibly represent the quality of UEs. This also leaves room for attackers, as there is no rigid guarantee of the maximal test accuracy achievable by attackers. Furthermore, we find that a simple recovery attack can restore the clean-task performance of the classifiers trained on UEs by slightly perturbing the learned weights. To mitigate the aforementioned problems, in this paper, we propose a mechanism for certifying the so-called $(q, \eta)$-Learnability of an unlearnable dataset via parametric smoothing. A lower certified $(q, \eta)$-Learnability indicates a more robust and effective protection over the dataset. Concretely, we 1) improve the tightness of certified $(q, \eta)$-Learnability and 2) design Provably Unlearnable Examples (PUEs) which have reduced $(q, \eta)$-Learnability., Comment: Accepted to Network and Distributed System Security (NDSS) Symposium 2025, San Diego, CA, USA. Source code is available at https://github.com/NeuralSec/certified-data-learnability

The advent of advanced AI underscores the urgent need for comprehensive safety evaluations, necessitating collaboration across communities (i.e., AI, software engineering, and governance). However, divergent practices and terminologies across these communities, combined with the complexity of AI systems-of which models are only a part-and environmental affordances (e.g., access to tools), obstruct effective communication and comprehensive evaluation. This paper proposes a framework for AI system evaluation comprising three components: 1) harmonised terminology to facilitate communication across communities involved in AI safety evaluation; 2) a taxonomy identifying essential elements for AI system evaluation; 3) a mapping between AI lifecycle, stakeholders, and requisite evaluations for accountable AI supply chain. This framework catalyses a deeper discourse on AI system evaluation beyond model-centric approaches., Comment: 1st ACM International Conference on AI-powered Software (AIware)

The diversity of web configuration interfaces for IoT devices has exacerbated issues such as inadequate permission controls and insecure interfaces, resulting in various vulnerabilities. Owing to the varying interface configurations across various devices, the existing methods are inadequate for identifying these vulnerabilities precisely and comprehensively. This study addresses these issues by introducing an automated vulnerability detection system, called LuaTaint. It is designed for the commonly used web configuration interface of IoT devices. LuaTaint combines static taint analysis with a large language model (LLM) to achieve widespread and high-precision detection. The extensive traversal of the static analysis ensures the comprehensiveness of the detection. The system also incorporates rules related to page handler control logic within the taint detection process to enhance its precision and extensibility. Moreover, we leverage the prodigious abilities of LLM for code analysis tasks. By utilizing LLM in the process of pruning false alarms, the precision of LuaTaint is enhanced while significantly reducing its dependence on manual analysis. We develop a prototype of LuaTaint and evaluate it using 2,447 IoT firmware samples from 11 renowned vendors. LuaTaint has discovered 111 vulnerabilities. Moreover, LuaTaint exhibits a vulnerability detection precision rate of up to 89.29%.

Recent studies have shown that recommender systems (RSs) are highly vulnerable to data poisoning attacks. Understanding attack tactics helps improve the robustness of RSs. We intend to develop efficient attack methods that use limited resources to generate high-quality fake user profiles to achieve 1) transferability among black-box RSs 2) and imperceptibility among detectors. In order to achieve these goals, we introduce textual reviews of products to enhance the generation quality of the profiles. Specifically, we propose a novel attack framework named R-Trojan, which formulates the attack objectives as an optimization problem and adopts a tailored transformer-based generative adversarial network (GAN) to solve it so that high-quality attack profiles can be produced. Comprehensive experiments on real-world datasets demonstrate that R-Trojan greatly outperforms state-of-the-art attack methods on various victim RSs under black-box settings and show its good imperceptibility., Comment: Accepted by ICDM 2023

The robustness of large language models (LLMs) becomes increasingly important as their use rapidly grows in a wide range of domains. Retrieval-Augmented Generation (RAG) is considered as a means to improve the trustworthiness of text generation from LLMs. However, how the outputs from RAG-based LLMs are affected by slightly different inputs is not well studied. In this work, we find that the insertion of even a short prefix to the prompt leads to the generation of outputs far away from factually correct answers. We systematically evaluate the effect of such prefixes on RAG by introducing a novel optimization technique called Gradient Guided Prompt Perturbation (GGPP). GGPP achieves a high success rate in steering outputs of RAG-based LLMs to targeted wrong answers. It can also cope with instructions in the prompts requesting to ignore irrelevant context. We also exploit LLMs' neuron activation difference between prompts with and without GGPP perturbations to give a method that improves the robustness of RAG-based LLMs through a highly effective detector trained on neuron activation triggered by GGPP generated prompts. Our evaluation on open-sourced LLMs demonstrates the effectiveness of our methods., Comment: 12 pages, 9 figures

The advent of Generative AI has marked a significant milestone in artificial intelligence, demonstrating remarkable capabilities in generating realistic images, texts, and data patterns. However, these advancements come with heightened concerns over data privacy and copyright infringement, primarily due to the reliance on vast datasets for model training. Traditional approaches like differential privacy, machine unlearning, and data poisoning only offer fragmented solutions to these complex issues. Our paper delves into the multifaceted challenges of privacy and copyright protection within the data lifecycle. We advocate for integrated approaches that combines technical innovation with ethical foresight, holistically addressing these concerns by investigating and devising solutions that are informed by the lifecycle perspective. This work aims to catalyze a broader discussion and inspire concerted efforts towards data privacy and copyright integrity in Generative AI., Comment: Accepted by 2024 IEEE/ACM 3rd International Conference on AI Engineering - Software Engineering for AI (CAIN)

Artificial Intelligence (AI), particularly through the advent of large-scale generative AI (GenAI) models such as Large Language Models (LLMs), has become a transformative element in contemporary technology. While these models have unlocked new possibilities, they simultaneously present significant challenges, such as concerns over data privacy and the propensity to generate misleading or fabricated content. Current frameworks for Responsible AI (RAI) often fall short in providing the granular guidance necessary for tangible application, especially for Accountability-a principle that is pivotal for ensuring transparent and auditable decision-making, bolstering public trust, and meeting increasing regulatory expectations. This study bridges the accountability gap by introducing our effort towards a comprehensive metrics catalogue, formulated through a systematic multivocal literature review (MLR) that integrates findings from both academic and grey literature. Our catalogue delineates process metrics that underpin procedural integrity, resource metrics that provide necessary tools and frameworks, and product metrics that reflect the outputs of AI systems. This tripartite framework is designed to operationalize Accountability in AI, with a special emphasis on addressing the intricacies of GenAI.

Foundation models, such as large language models (LLMs), have been widely recognised as transformative AI technologies due to their capabilities to understand and generate content, including plans with reasoning capabilities. Foundation model based agents derive their autonomy from the capabilities of foundation models, which enable them to autonomously break down a given goal into a set of manageable tasks and orchestrate task execution to meet the goal. Despite the huge efforts put into building foundation model based agents, the architecture design of the agents has not yet been systematically explored. Also, while there are significant benefits of using agents for planning and execution, there are serious considerations regarding responsible AI related software quality attributes, such as security and accountability. Therefore, this paper presents a pattern-oriented reference architecture that serves as guidance when designing foundation model based agents. We evaluate the completeness and utility of the proposed reference architecture by mapping it to the architecture of two real-world agents.

Energy disaggregation techniques, which use smart meter data to infer appliance energy usage, can provide consumers and energy companies valuable insights into energy management. However, these techniques also present privacy risks, such as the potential for behavioral profiling. Local differential privacy (LDP) methods provide strong privacy guarantees with high efficiency in addressing privacy concerns. However, existing LDP methods focus on protecting aggregated energy consumption data rather than individual appliances. Furthermore, these methods do not consider the fact that smart meter data are a form of streaming data, and its processing methods should account for time windows. In this paper, we propose a novel LDP approach (named LDP-SmartEnergy) that utilizes randomized response techniques with sliding windows to facilitate the sharing of appliance-level energy consumption data over time while not revealing individual users' appliance usage patterns. Our evaluations show that LDP-SmartEnergy runs efficiently compared to baseline methods. The results also demonstrate that our solution strikes a balance between protecting privacy and maintaining the utility of data for effective analysis., Comment: 18 pages, 9 figures

The World Wide Web, a ubiquitous source of information, serves as a primary resource for countless individuals, amassing a vast amount of data from global internet users. However, this online data, when scraped, indexed, and utilized for activities like web crawling, search engine indexing, and, notably, AI model training, often diverges from the original intent of its contributors. The ascent of Generative AI has accentuated concerns surrounding data privacy and copyright infringement. Regrettably, the web's current framework falls short in facilitating pivotal actions like consent withdrawal or data copyright claims. While some companies offer voluntary measures, such as crawler access restrictions, these often remain inaccessible to individual users. To empower online users to exercise their rights and enable companies to adhere to regulations, this paper introduces a user-controlled consent tagging framework for online data. It leverages the extensibility of HTTP and HTML in conjunction with the decentralized nature of distributed ledger technology. With this framework, users have the ability to tag their online data at the time of transmission, and subsequently, they can track and request the withdrawal of consent for their data from the data holders. A proof-of-concept system is implemented, demonstrating the feasibility of the framework. This work holds significant potential for contributing to the reinforcement of user consent, privacy, and copyright on the modern internet and lays the groundwork for future insights into creating a more responsible and user-centric web ecosystem., Comment: added some information on how to deal with CDN in the design section; minor fixes on writing

Recent breakthroughs in pre-trained code models, such as CodeBERT and Codex, have shown their superior performance in various downstream tasks. The correctness and unambiguity of API usage among these code models are crucial for achieving desirable program functionalities, requiring them to learn various API fully qualified names structurally and semantically. Recent studies reveal that even state-of-the-art pre-trained code models struggle with suggesting the correct APIs during code generation. However, the reasons for such poor API usage performance are barely investigated. To address this challenge, we propose using knowledge probing as a means of interpreting code models, which uses cloze-style tests to measure the knowledge stored in models. Our comprehensive study examines a code model's capability of understanding API fully qualified names from two different perspectives: API call and API import. Specifically, we reveal that current code models struggle with understanding API names, with pre-training strategies significantly affecting the quality of API name learning. We demonstrate that natural language context can assist code models in locating Python API names and generalize Python API name knowledge to unseen data. Our findings provide insights into the limitations and capabilities of current pre-trained code models, and suggest that incorporating API structure into the pre-training process can improve automated API usage and code representations. This work provides significance for advancing code intelligence practices and direction for future studies. All experiment results, data and source code used in this work are available at \url{https://doi.org/10.5281/zenodo.7902072}.

Foundation models including large language models (LLMs) are increasingly attracting interest worldwide for their distinguished capabilities and potential to perform a wide variety of tasks. Nevertheless, people are concerned about whether foundation model based AI systems are properly governed to ensure the trustworthiness and to prevent misuse that could harm humans, society and the environment. In this paper, we identify eight governance challenges of foundation model based AI systems regarding the three fundamental dimensions of governance: decision rights, incentives, and accountability. Furthermore, we explore the potential of blockchain as an architectural solution to address the challenges by providing a distributed ledger to facilitate decentralised governance. We present an architecture that demonstrates how blockchain can be leveraged to realise governance in foundation model based AI systems.

Quantum computing systems depend on the principles of quantum mechanics to perform multiple challenging tasks more efficiently than their classical counterparts. In classical software engineering, the software life cycle is used to document and structure the processes of design, implementation, and maintenance of software applications. It helps stakeholders understand how to build an application. In this paper, we summarize a set of software analytics topics and techniques in the development life cycle that can be leveraged and integrated into quantum software application development. The results of this work can assist researchers and practitioners in better understanding the quantum-specific emerging development activities, challenges, and opportunities in the next generation of quantum software.

The robustness of critical infrastructure systems is contingent upon the integrity and transparency of their software supply chains. A Software Bill of Materials (SBOM) is pivotal in this regard, offering an exhaustive inventory of components and dependencies crucial to software development. However, prevalent challenges in SBOM sharing, such as data tampering risks and vendors' reluctance to fully disclose sensitive information, significantly hinder its effective implementation. These challenges pose a notable threat to the security of critical infrastructure and systems where transparency and trust are paramount, underscoring the need for a more secure and flexible mechanism for SBOM sharing. To bridge the gap, this study introduces a blockchain-empowered architecture for SBOM sharing, leveraging verifiable credentials to allow for selective disclosure. This strategy not only heightens security but also offers flexibility. Furthermore, this paper broadens the remit of SBOM to encompass AI systems, thereby coining the term AI Bill of Materials (AIBOM). The advent of AI and its application in critical infrastructure necessitates a nuanced understanding of AI software components, including their origins and interdependencies. The evaluation of our solution indicates the feasibility and flexibility of the proposed SBOM sharing mechanism, positing a solution for safeguarding (AI) software supply chains, which is essential for the resilience and reliability of modern critical infrastructure systems., Comment: Accepted by The Joint International Workshop on Engineering and Security of Critical Systems and Software Vulnerability Management (EnCyCriS/SVM 2024), Co-located with ICSE 2024

Foundation models, such as GPT-4, DALL-E have brought unprecedented AI "operating system" effect and new forms of human-AI interaction, sparking a wave of innovation in AI-native services, where natural language prompts serve as executable "code" directly (prompt as executable code), eliminating the need for programming language as an intermediary and opening up the door to personal AI. Prompt Sapper has emerged in response, committed to support the development of AI-native services by AI chain engineering. It creates a large language model (LLM) empowered software engineering infrastructure for authoring AI chains through human-AI collaborative intelligence, unleashing the AI innovation potential of every individual, and forging a future where everyone can be a master of AI innovation. This article will introduce the R\&D motivation behind Prompt Sapper, along with its corresponding AI chain engineering methodology and technical practices.

Distributed trust is a nebulous concept that has evolved from different perspectives in recent years. While one can attribute its current prominence to blockchain and cryptocurrency, the distributed trust concept has been cultivating progress in federated learning, trustworthy and responsible AI in an ecosystem setting, data sharing, privacy issues across organizational boundaries, and zero trust cybersecurity. This paper will survey the concept of distributed trust in multiple disciplines. It will take a system/software architecture point of view to look at trust redistribution/shift and the associated tradeoffs in systems and applications enabled by distributed trust technologies.

The rapid advancement of Artificial Intelligence (AI), represented by ChatGPT, has raised concerns about responsible AI development and utilization. Existing frameworks lack a comprehensive synthesis of AI risk assessment questions. To address this, we introduce QB4AIRA, a novel question bank developed by refining questions from five globally recognized AI risk frameworks, categorized according to Australia's AI ethics principles. QB4AIRA comprises 293 prioritized questions covering a wide range of AI risk areas, facilitating effective risk assessment. It serves as a valuable resource for stakeholders in assessing and managing AI risks, while paving the way for new risk frameworks and guidelines. By promoting responsible AI practices, QB4AIRA contributes to responsible AI deployment, mitigating potential risks and harms.

The recent release of large language model (LLM) based chatbots, such as ChatGPT, has attracted huge interest in foundation models. It is widely believed that foundation models will serve as the fundamental building blocks for future AI systems. As foundation models are in their early stages, the design of foundation model based systems has not yet been systematically explored. There is limited understanding about the impact of introducing foundation models in software architecture. Therefore, in this paper, we propose a taxonomy of foundation model based systems, which classifies and compares the characteristics of foundation models and design options of foundation model based systems. Our taxonomy comprises three categories: the pretraining and adaptation of foundation models, the architecture design of foundation model based systems, and responsible-AI-by-design. This taxonomy can serve as concrete guidance for making major architectural design decisions when designing foundation model based systems and highlights trade-offs arising from design decisions.

Programming screencasts (e.g., video tutorials on Youtube or live coding stream on Twitch) are important knowledge source for developers to learn programming knowledge, especially the workflow of completing a programming task. Nonetheless, the image nature of programming screencasts limits the accessibility of screencast content and the workflow embedded in it, resulting in a gap to access and interact with the content and workflow in programming screencasts. Existing non-intrusive methods are limited to extract either primitive human-computer interaction (HCI) actions or coarse-grained video fragments.In this work, we leverage Computer Vision (CV) techniques to build a programming screencast analysis tool which can automatically extract code-line editing steps (enter text, delete text, edit text and select text) from screencasts.Given a programming screencast, our approach outputs a sequence of coding steps and code snippets involved in each step, which we refer to as programming workflow. The proposed method is evaluated on 41 hours of tutorial videos and live coding screencasts with diverse programming environments.The results demonstrate our tool can extract code-line editing steps accurately and the extracted workflow steps can be intuitively understood by developers., Comment: Accepted by IEEE/ACM International Conference on Software Engineering 2023 (ICSE 2023)

The Software Bill of Materials (SBOM) has emerged as a promising solution, providing a machine-readable inventory of software components used, thus bolstering supply chain security. This paper presents an extensive study concerning the practical aspects of SBOM practice. Leveraging an analysis of 4,786 GitHub discussions from 510 SBOM-related projects, our research delineates key topics, challenges, and solutions intrinsic to the effective utilization of SBOMs. Furthermore, we shed light on commonly used tools and frameworks for generating SBOMs, exploring their respective strengths and limitations. Our findings underscore the pivotal role SBOMs play in ensuring resilient software development practices and underscore the imperative of their widespread integration to bolster supply chain security. The insights accrued from our study hold significance as valuable input for prospective research and development in this crucial domain.

The release of ChatGPT, Gemini, and other large language model has drawn huge interests on foundations models. There is a broad consensus that foundations models will be the fundamental building blocks for future AI systems. However, there is a lack of systematic guidance on the architecture design. Particularly, the the rapidly growing capabilities of foundations models can eventually absorb other components of AI systems, posing challenges of moving boundary and interface evolution in architecture design. Furthermore, incorporating foundations models into AI systems raises significant concerns about responsible and safe AI due to their opaque nature and rapidly advancing intelligence. To address these challenges, the paper first presents an architecture evolution of AI systems in the era of foundation models, transitioning from "foundation-model-as-a-connector" to "foundation-model-as-a-monolithic architecture". The paper then identifies key design decisions and proposes a pattern-oriented reference architecture for designing responsible foundation-model-based systems. The patterns can enable the potential of foundation models while ensuring associated risks.

Various data-sharing platforms have emerged with the growing public demand for open data and legislation mandating certain data to remain open. Most of these platforms remain opaque, leading to many questions about data accuracy, provenance and lineage, privacy implications, consent management, and the lack of fair incentives for data providers. With their transparency, immutability, non-repudiation, and decentralization properties, blockchains could not be more apt to answer these questions and enhance trust in a data-sharing platform. However, blockchains are not good at handling the four Vs of big data (i.e., volume, variety, velocity, and veracity) due to their limited performance, scalability, and high cost. Given many related works proposes blockchain-based trustworthy data-sharing solutions, there is increasing confusion and difficulties in understanding and selecting these technologies and platforms in terms of their sharing mechanisms, sharing services, quality of services, and applications. In this paper, we conduct a comprehensive survey on blockchain-based data-sharing architectures and applications to fill the gap. First, we present the foundations of blockchains and discuss the challenges of current data-sharing techniques. Second, we focus on the convergence of blockchain and data sharing to give a clear picture of this landscape and propose a reference architecture for blockchain-based data sharing. Third, we discuss the industrial applications of blockchain-based data sharing, ranging from healthcare and smart grid to transportation and decarbonization. For each application, we provide lessons learned for the deployment of Blockchain-based data sharing. Finally, we discuss research challenges and open research directions., Comment: 40 pages, 15 figures, and 8 tables

Due to convenience, open-source software is widely used. For beneficial reasons, open-source maintainers often fix the vulnerabilities silently, exposing their users unaware of the updates to threats. Previous works all focus on black-box binary detection of the silent dependency alerts that suffer from high false-positive rates. Open-source software users need to analyze and explain AI prediction themselves. Explainable AI becomes remarkable as a complementary of black-box AI models, providing details in various forms to explain AI decisions. Noticing there is still no technique that can discover silent dependency alert on time, in this work, we propose a framework using an encoder-decoder model with a binary detector to provide explainable silent dependency alert prediction. Our model generates 4 types of vulnerability key aspects including vulnerability type, root cause, attack vector, and impact to enhance the trustworthiness and users' acceptance to alert prediction. By experiments with several models and inputs, we confirm CodeBERT with both commit messages and code changes achieves the best results. Our user study shows that explainable alert predictions can help users find silent dependency alert more easily than black-box predictions. To the best of our knowledge, this is the first research work on the application of Explainable AI in silent dependency alert prediction, which opens the door of the related domains.

The right to be forgotten (RTBF) is motivated by the desire of people not to be perpetually disadvantaged by their past deeds. For this, data deletion needs to be deep and permanent, and should be removed from machine learning models. Researchers have proposed machine unlearning algorithms which aim to erase specific data from trained models more efficiently. However, these methods modify how data is fed into the model and how training is done, which may subsequently compromise AI ethics from the fairness perspective. To help software engineers make responsible decisions when adopting these unlearning methods, we present the first study on machine unlearning methods to reveal their fairness implications. We designed and conducted experiments on two typical machine unlearning methods (SISA and AmnesiacML) along with a retraining method (ORTR) as baseline using three fairness datasets under three different deletion strategies. Experimental results show that under non-uniform data deletion, SISA leads to better fairness compared with ORTR and AmnesiacML, while initial training and uniform data deletion do not necessarily affect the fairness of all three methods. These findings have exposed an important research problem in software engineering, and can help practitioners better understand the potential trade-offs on fairness when considering solutions for RTBF., Comment: Accepted by AAAI Spring Symposium on AI Trustworthiness Assessment 2023. Published in AI and Ethics Journal https://link.springer.com/article/10.1007/s43681-023-00398-y

The usage of Python idioms is popular among Python developers in a formative study of 101 performance-related questions of Python idioms on Stack Overflow, we find that developers often get confused about the performance impact of Python idioms and use anecdotal toy code or rely on personal project experience which is often contradictory in performance outcomes. There has been no large-scale, systematic empirical evidence to reconcile these performance debates. In the paper, we create a large synthetic dataset with 24,126 pairs of non-idiomatic and functionally-equivalent idiomatic code for the nine unique Python idioms identified in Zhang et al., and reuse a large real-project dataset of 54,879 such code pairs provided by Zhang et al. We develop a reliable performance measurement method to compare the speedup or slowdown by idiomatic code against non-idiomatic counterpart, and analyze the performance discrepancies between the synthetic and real-project code, the relationships between code features and performance changes, and the root causes of performance changes at the bytecode level. We summarize our findings as some actionable suggestions for using Python idioms., Comment: 12 pages, accepted to ICSE'2023

In the field of artificial intelligence (AI), the quest to understand and model data-generating processes (DGPs) is of paramount importance. Deep generative models (DGMs) have proven adept in capturing complex data distributions but often fall short in generalization and interpretability. On the other hand, causality offers a structured lens to comprehend the mechanisms driving data generation and highlights the causal-effect dynamics inherent in these processes. While causality excels in interpretability and the ability to extrapolate, it grapples with intricacies of high-dimensional spaces. Recognizing the synergistic potential, we delve into the confluence of causality and DGMs. We elucidate the integration of causal principles within DGMs, investigate causal identification using DGMs, and navigate an emerging research frontier of causality in large-scale generative models, particularly generative large language models (LLMs). We offer insights into methodologies, highlight open challenges, and suggest future directions, positioning our comprehensive review as an essential guide in this swiftly emerging and evolving area.

The rapid development of artificial intelligence (AI) has led to increasing concerns about the capability of AI systems to make decisions and behave responsibly. Responsible AI (RAI) refers to the development and use of AI systems that benefit humans, society, and the environment while minimising the risk of negative consequences. To ensure responsible AI, the risks associated with AI systems' development and use must be identified, assessed and mitigated. Various AI risk assessment frameworks have been released recently by governments, organisations, and companies. However, it can be challenging for AI stakeholders to have a clear picture of the available frameworks and determine the most suitable ones for a specific context. Additionally, there is a need to identify areas that require further research or development of new frameworks, as well as updating and maintaining existing ones. To fill the gap, we present a mapping study of 16 existing AI risk assessment frameworks from the industry, governments, and non-government organizations (NGOs). We identify key characteristics of each framework and analyse them in terms of RAI principles, stakeholders, system lifecycle stages, geographical locations, targeted domains, and assessment methods. Our study provides a comprehensive analysis of the current state of the frameworks and highlights areas of convergence and divergence among them. We also identify the deficiencies in existing frameworks and outlines the essential characteristics of a concrete and connected framework AI risk assessment (C$^2$AIRA) framework. Our findings and insights can help relevant stakeholders choose suitable AI risk assessment frameworks and guide the design of future frameworks towards concreteness and connectedness., Comment: [Camera-ready] Accepted by 2nd International Conference on AI Engineering - Software Engineering for AI (CAIN 2023)

The rapid growth of software supply chain attacks has attracted considerable attention to software bill of materials (SBOM). SBOMs are a crucial building block to ensure the transparency of software supply chains that helps improve software supply chain security. Although there are significant efforts from academia and industry to facilitate SBOM development, it is still unclear how practitioners perceive SBOMs and what are the challenges of adopting SBOMs in practice. Furthermore, existing SBOM-related studies tend to be ad-hoc and lack software engineering focuses. To bridge this gap, we conducted the first empirical study to interview and survey SBOM practitioners. We applied a mixed qualitative and quantitative method for gathering data from 17 interviewees and 65 survey respondents from 15 countries across five continents to understand how practitioners perceive the SBOM field. We summarized 26 statements and grouped them into three topics on SBOM's states of practice. Based on the study results, we derived a goal model and highlighted future directions where practitioners can put in their effort., Comment: Accepted to ICSE 2023; Camera-ready version

The recent release of ChatGPT has gained huge attention and discussion worldwide, with responsible AI being a key topic of discussion. How can we ensure that AI systems, including ChatGPT, are developed and adopted in a responsible way? To tackle the responsible AI challenges, various ethical principles have been released by governments, organisations, and companies. However, those principles are very abstract and not practical enough. Further, significant efforts have been put on algorithm-level solutions that only address a narrow set of principles, such as fairness and privacy. To fill the gap, we adopt a pattern-oriented responsible AI engineering approach and build a Responsible AI Pattern Catalogue to operationalise responsible AI from a system perspective. In this article, we first summarise the major challenges in operationalising responsible AI at scale and introduce how we use the Responsible AI Pattern Catalogue to address those challenges. We then examine the risks at each stage of the chatbot development process and recommend pattern-driven mitigations to evaluate the the usefulness of the Responsible AI Pattern Catalogue in a real-world setting.

Blockchain technology has been integrated into diverse software applications by enabling a decentralised architecture design. However, the defects of on-chain algorithmic mechanisms, and tedious disputes and debates in off-chain communities may affect the operation of blockchain systems. Accordingly, blockchain governance has received great interest for supporting the design, use, and maintenance of blockchain systems, hence improving the overall trustworthiness. Although much effort has been put into this research topic, there is a distinct lack of consideration for blockchain governance from the perspective of software architecture design. In this study, we propose a pattern-oriented reference architecture for governance-driven blockchain systems, which can provide guidance for future blockchain architecture design. We design the reference architecture based on an extensive review of architecture patterns for blockchain governance in academic literature and industry implementation. The reference architecture consists of four layers. We demonstrate the components in each layer, annotating with the identified patterns. A qualitative analysis of mapping two concrete blockchain architectures, Polkadot and Quorum, on the reference architecture is conducted, to evaluate the correctness and utility of proposed reference architecture.

Responsible AI is widely considered as one of the greatest scientific challenges of our time and is key to increase the adoption of AI. Recently, a number of AI ethics principles frameworks have been published. However, without further guidance on best practices, practitioners are left with nothing much beyond truisms. Also, significant efforts have been placed at algorithm-level rather than system-level, mainly focusing on a subset of mathematics-amenable ethical principles, such as fairness. Nevertheless, ethical issues can arise at any step of the development lifecycle, cutting across many AI and non-AI components of systems beyond AI algorithms and models. To operationalize responsible AI from a system perspective, in this paper, we present a Responsible AI Pattern Catalogue based on the results of a Multivocal Literature Review (MLR). Rather than staying at the principle or algorithm level, we focus on patterns that AI system stakeholders can undertake in practice to ensure that the developed AI systems are responsible throughout the entire governance and engineering lifecycle. The Responsible AI Pattern Catalogue classifies the patterns into three groups: multi-level governance patterns, trustworthy process patterns, and responsible-AI-by-design product patterns. These patterns provide systematic and actionable guidance for stakeholders to implement responsible AI.

We regularly consider answering counterfactual questions in practice, such as "Would people with diabetes take a turn for the better had they choose another medication?". Observational studies are growing in significance in answering such questions due to their widespread accumulation and comparatively easier acquisition than Randomized Control Trials (RCTs). Recently, some works have introduced representation learning and domain adaptation into counterfactual inference. However, most current works focus on the setting of binary treatments. None of them considers that different treatments' sample sizes are imbalanced, especially data examples in some treatment groups are relatively limited due to inherent user preference. In this paper, we design a new algorithmic framework for counterfactual inference, which brings an idea from Meta-learning for Estimating Individual Treatment Effects (MetaITE) to fill the above research gaps, especially considering multiple imbalanced treatments. Specifically, we regard data episodes among treatment groups in counterfactual inference as meta-learning tasks. We train a meta-learner from a set of source treatment groups with sufficient samples and update the model by gradient descent with limited samples in target treatment. Moreover, we introduce two complementary losses. One is the supervised loss on multiple source treatments. The other loss which aligns latent distributions among various treatment groups is proposed to reduce the discrepancy. We perform experiments on two real-world datasets to evaluate inference accuracy and generalization ability. Experimental results demonstrate that the model MetaITE matches/outperforms state-of-the-art methods., Comment: 11 pages