Blockchain technologies have experienced rapid adoption across various sectors, including supply chain management, decentralized finance and cross-border payments. With this growth, however, the complexity and security risks of maintaining blockchain integrity and functionality have increased. Addressing these challenges requires a systematic and rigorous organization of knowledge in blockchain security. This paper presents a Systematization of Knowledge (SoK) study based on a structured survey of academic literature, industry reports and real-world case studies. The authors classify vulnerabilities into three layers: system-level, smart contract-level and application-level, analyzing their root causes, real-world prevalence and mitigation tradeoffs. The taxonomy encompasses blockchain-specific threats (e.g. gas-based DoS attacks, MEV) as well as vulnerabilities inherited from distributed systems and software (e.g. Sybil attacks, access control failures). The authors critically evaluate detection and mitigation techniques, including static and dynamic analysis, fuzzing, symbolic execution and formal verification, assessing their precision, recall, scalability and inherent limitations. The authors further review state-of-the-art auditing tools in terms of methodology, adoption and shortcomings. Finally, the authors discuss advanced approaches such as hybrid frameworks that combine AI with program analysis, SMT solvers, and zero-knowledge proofs, outlining how these can address current gaps in scalability, interpretability and runtime verification. Overall, this study systematizes the security landscape of blockchain technologies, synthesizes the limitations of current approaches, and identifies technically actionable future research directions toward building more robust and resilient blockchain systems.
The notion of Zero Trust Architecture (ZTA) has been introduced as a fine-grained defense approach. It assumes that no entities outside and inside the protected system can be trusted and, therefore, requires articulated and high-coverage deployment of security controls. However, ZTA is a complex notion that does not have a single design solution; rather, it consists of numerous interconnected concepts and processes that need to be assessed prior to deciding on a solution. In this monograph, we cover the principles and architectural foundations of ZTA, basically following the guidelines by NIST, and provide a detailed analysis of ZT architectures proposed by research and industry. The monograph also describes an approach for the automatic generation of ZT policies based on application communication requirements, network topology, and organizational information. This approach was designed to meet a critical need of ZTA, that is, the generation and implementation of a large number of fine-grained policies. Finally, the monograph discusses several research directions, including the incorporation of threat intelligence into ZT networks and the use of large language models (LLMs).
Blockchains have become an integrated part of our finance infrastructures. Being monetary yet fully automated, blockchains and their applications are unanimously deemed impracticable before undergoing necessary verification. This monograph reviews the previous attempts at verifying two fundamental properties of blockchains: correctness (where flaws lead to unintentional damages) and security (where vulnerabilities incur attacks and losses). First, it summarizes and categorizes the correctness and security flaws encountered by real-world blockchains. Second, it systematizes the development of formal verification to address the flaws in blockchains, covering the aspects of models, specifications, and techniques. Third, it unveils the progress of security analysis for mitigating the flaws, unveiling the analysis principles being followed, the flaw oracles being devised, and the detection methods being used. Finally, it summarizes the challenges remaining to be addressed, followed by our vision of the trend in the near future. Throughout this monograph, we anticipate shedding light on future blockchain verification advances, especially in expanding its applicability, making specification generation easier, and discovering previously unknown vulnerabilities. By identifying gaps such as missing tools for infrastructure-level components and the difficulty of writing formal specifications, this work aims to motivate the development of more automated, intelligent, and practical verification frameworks.
The success of machine learning algorithms relies not only on achieving good performance but also on ensuring trustworthiness across diverse applications and scenarios. Trustworthy machine learning seeks to handle critical problems in addressing the issues of robustness, privacy, security, reliability, and other desirable properties. The broad research area has achieved remarkable advancement and brings various emerging topics along with the progress. We present this survey to provide a systematic overview of the research problems under trustworthy machine learning covering the perspectives from data to model. Starting with fundamental data-centric learning, the survey reviews learning with noisy data, long-tailed distribution, out-of-distribution data, and adversarial examples to achieve robustness. Delving into private and secured learning, the survey elaborates on core methodologies differential privacy, different attacking threats, and learning paradigms, to realize privacy protection and enhance security. Finally, it introduces several trendy issues related to the foundation models, including jailbreak prompts, watermarking, and hallucination, as well as causal learning and reasoning. The survey integrates commonly isolated research problems in a unified manner, which provides general problem setups, detailed sub-directions, and further discussion on its challenges or future developments. We hope the comprehensive investigation presented in this survey can serve as a clear introduction for the problemevolution from data to models and also bring new insight for developing trustworthy machine learning.
In recent years, the integration of Large Language Models (LLMs) and Recommender Systems (RS) has revolutionized the way personalized and intelligent user experiences are delivered. This survey provides an extensive review of critical challenges, current landscape, and future directions in the collaboration between LLM-based AI agents (LLM Agent) and recommender systems. We begin with an introduction to the foundational knowledge, exploring the components of LLM agents and the applications of LLMs in recommender systems. The survey then delves into the symbiotic relationship between LLM agents and recommender systems, illustrating how LLM agents enhance recommender systems and how recommender systems support better LLM agents. Specifically, we discuss the overall architectures for designing LLM agents for recommendation, encompassing profile, memory, planning, and action components, along with multi-agent collaboration. Conversely, we investigate how recommender systems contribute to LLM agents, focusing on areas such as memory recommendation, plan recommendation, tool recommendation, agent recommendation, and personalized LLMs and LLM agents. Furthermore, a critical evaluation of trustworthy AI agents and recommender systems follows, addressing key issues of safety, explainability, fairness, and privacy. Finally, we propose potential future research directions, highlighting emerging trends and opportunities in the intersection of AI agents and recommender systems. This survey concludes by summarizing the key insights of current research and outlining promising avenues for future exploration in this rapidly evolving field. A curated collection of relevant papers for this survey is available in the GitHub repository: https://github.com/agiresearch/AgentRecSys.
The rapid advancement of large models, driven by their exceptional abilities in learning and generalization through large-scale pre-training, has reshaped the landscape of Artificial Intelligence (AI). These models are now foundational to a wide range of applications, including conversational AI, recommendation systems, autonomous driving, content generation, medical diagnostics, and scientific discovery. However, their widespread deployment also exposes them to significant safety risks, raising concerns about robustness, reliability, and ethical implications. This survey provides a systematic review of current safety research on large models, covering Vision Foundation Models (VFMs), Large Language Models (LLMs), Vision-Language Pre-training (VLP) models, Vision-Language Models (VLMs), Diffusion Models (DMs), and large-model-powered Agents. Our contributions are summarized as follows: (1) We present a comprehensive taxonomy of safety threats to these models, including adversarial attacks, data poisoning, backdoor attacks, jailbreak and prompt injection attacks, energy-latency attacks, data and model extraction attacks, and emerging agent-specific threats. (2) We review defense strategies proposed for each type of attacks if available and summarize the commonly used datasets and benchmarks for safety research. (3) Building on this, we identify and discuss the open challenges in large model safety, emphasizing the need for comprehensive safety evaluations, scalable and effective defense mechanisms, and sustainable data practices. More importantly, we highlight the necessity of collective efforts from the research community and international collaboration. Our work can serve as a useful reference for researchers and practitioners, fostering the ongoing development of comprehensive defense systems and platforms to safeguard AI models.
Smart Grid is a power grid system that uses digital communication technologies. By deploying intelligent devices throughout the power grid infrastructure,from power generation to consumption, and enabling communication among them, it revolutionizes the modern power grid industry with increased efficiency, reliability, and availability. However, reliance on information and communication technologies has also made the smart grids exposed to new vulnerabilities and complications that may negatively impact the availability and stability of electricity services, which are vital for people's daily lives. The purpose of this monograph is to provide an up-to-date and comprehensive survey and tutorial on the cybersecurity aspect of smart grids. The book focuses on the sources of the cybersecurity issues, the taxonomy of threats, and the survey of various approaches to overcome or mitigate such threats. It covers the state-of-the-art research results in recent years, along with remaining open challenges. We hope that this monograph can be used both as learning materials for beginners who are embarking on research in this area and as a useful reference for established researchers in this field.
Financial markets are undergoing an unprecedented transformation. Technological advances have brought major improvements to the operations of financial services. While these advances promote improved accessibility and convenience, traditional finance shortcomings like lack of transparency and moral hazard frictions continue to plague centralized platforms, imposing societal costs. In this paper, we argue how these shortcomings and frictions are being mitigated by the decentralized finance (DeFi) ecosystem. We delve into the workings of smart contracts, the backbone of DeFi transactions, with an emphasis on those underpinning token exchange and lending services. We highlight the pros and cons of the novel form of decentralized governance introduced via the ownership of governance tokens. Despite its potential, the current DeFi infrastructure introduces operational risks to users, which we segment into five primary categories: consensus mechanisms, protocol, oracle, frontrunning, and systemic risks. We conclude by emphasizing the need for future research to focus on the scalability of existing blockchains, the improved design and interoperability of DeFi protocols, and the rigorous auditing of smart contracts.
Every major technical invention resurfaces the dual-use dilemma -- the new technology has the potential to be used for good as well as for harm. Generative AI (GenAI) techniques, such as large language models (LLMs) and diffusion models, have shown remarkable capabilities (e.g., in-context learning, code-completion, and text-to-image generation and editing). However, GenAI can be used just as well by attackers to generate new attacks and increase the velocity and efficacy of existing attacks. This paper reports the findings of a workshop held at Google (co-organized by Stanford University and the University of Wisconsin-Madison) on the dual-use dilemma posed by GenAI. This paper is not meant to be comprehensive, but is rather an attempt to synthesize some of the interesting findings from the workshop. We discuss short-term and long-term goals for the community on this topic. We hope this paper provides both a launching point for a discussion on this important topic as well as interesting problems that the research community can work to address.
Cybersecurity and Privacy (S&P) unlock the full potential of computing. Use of encryption, authentication, and access control, for example, allows employees to correspond with professional colleagues via email with reduced fear of leaking confidential data to competitors or cybercriminals. It also allows, for example, parents to share photos of children with remote loved ones over the Internet with reduced fear of this data reaching the hands of unknown strangers, and anonymous whistleblowers to share information about problematic practices in the workplace with reduced fear of being outed. Conversely, failure to employ appropriate S&P measures can leave people and organizations vulnerable to a broad range of threats. In short, the security and privacy decisions we make on a day-to-day basis determine whether the data we share, manipulate, and store online is protected from theft, surveillance, and exploitation. How can end-users be encouraged to accept recommended S&P behavior from experts? In this monograph, prior art in human-centered S&P is reviewed, and three barriers to end-user acceptance of expert recommendations have been identified. These three barriers make up what we call the “Security & Privacy Acceptance Framework” (SPAF). The barriers are: (1) awareness: i.e., people may not know of relevant security threats and appropriate mitigation measures; (2) motivation: i.e., people may be unwilling to enact S&P behaviors because, e.g., the perceived costs are too high; (3) and, ability: i.e., people may not know when, why, and how to effectively implement S&P behaviors. This monograph also reviews and critically analyzes prior work that has explored mitigating one or more of the barriers that make up the SPAF. Finally, using the SPAF as a lens, discussed is how the human-centered S&P community might re-orient to encourage widespread end-user acceptance of pro-S&P behaviors by employing integrative approaches that address each one of the awareness, motivation, and ability barriers.
This monograph is about verifiable computing (VC). VC refers to cryptographic protocols called interactive proofs (IPs) and arguments that enable a prover to provide a guarantee to a verifier that the prover performed a requested computation correctly. This monograph covers different notions of mathematical proofs and their applications in computer science and cryptography. Informally, what we mean by a proof is anything that convinces someone that a statement is true, and a “proof system” is any procedure that decides what is and is not a convincing proof. Introduced in the 1980s, IPs and arguments represented a major conceptual expansion of what constitutes a “proof” that a statement is true. Traditionally, a proof is a static object that can be easily checked step-by-step for correctness. In contrast, IPs allow for interaction between prover and verifier, as well as a tiny but nonzero probability that an invalid proof passes verification. Arguments (but not IPs) even permit there to be “proofs” of false statements, so long as those “proofs” require exorbitant computational power to find. To an extent, these notions mimic in-person interactions that mathematicians use to convince each other that a claim is true, without going through the painstaking process of writing out and checking a traditional static proof. Celebrated theoretical results from the 1980s and 1990s, such as IP = PSPACE and MIP = NEXP showed that, in principle, surprisingly complicated statements can be verified efficiently. What is more, any argument can in principle be transformed into one that is zero-knowledge, which means that proofs reveal no information other than their own validity. Zero-knowledge arguments have a myriad of applications in cryptography. Within the last decade, general-purpose zero-knowledge arguments have made the jump from theory to practice. This has opened new doors in the design of cryptographic systems, and generated additional insights into the power of IPs and arguments (zero-knowledge or otherwise). There are now no fewer than five promising approaches to designing efficient, general-purpose zero-knowledge arguments. This monograph covers these approaches in a unified manner, emphasizing commonalities between them.
Autonomous systems will soon be ubiquitous in our society, saving us time, performing tasks we do not want to do, caring for us and keeping us safe. Autonomous robots in homes and businesses are already cleaning floors, mowing lawns, delivering meals and packages, and the technology is now driving cars and trucks. Though they will soon be common occurrences in everyday life, assuring their safety, privacy and security is still a huge challenge. A number of autonomous car accidents have occurred after millions of miles of testing, and injuries regularly occur from other types of autonomous systems. Assuring the proper behavior and safety of autonomous systems is an important endeavor to reduce risks in using them. This monograph discusses assurance for autonomous systems, the different approaches to assuring autonomy, formal analysis, cybersecurity, certification and research challenges. The monograph starts with a brief introduction to assured autonomy, providing definitions and key terms. Thereafter, an overview of assured autonomy and different aspects of system and software assurances are provided, and Section 3 discusses governance, trust, ethics and privacy of autonomous systems. Section 4 covers assuring the correct operation of autonomous systems, which can be done through techniques such as formal verification, testing and monitoring. The monograph then describes certification of current systems and proposals for certifying autonomous systems, providing an example of the certification of aircraft software and multiple proposals for how autonomous systems could be certified. Lastly, areas of research in assuring autonomous systems are covered.
Personal mobile devices like smartphones and tablets are ubiquitous. People use mobile devices for fun, for work, and for organizing and managing their lives, including their finances. This has become possible because over the past two decades, mobile phones evolved from closed platforms intended for voice calls and messaging to open platforms whose functionality can be extended in myriad ways by third party developers. Such wide-ranging scope of use also means widely different security and privacy requirements for those uses. As mobile platforms gradually opened, platform security mechanisms were incorporated into their architectures so that the security and privacy requirements of all stakeholders could be met. The time is therefore right to take a new look at mobile platform security, which is the intent of this monograph. The monograph is divided into four parts: firstly, the authors look at the how and why of mobile platform security, and this is followed by a discussion on vulnerabilities and attacks. The monograph concludes by looking forward and discussing emerging research that explores ways of dealing with hardware compromise, and building blocks for the next generation of hardware platform security. The authors have intended to provide a broad overview of the current state of practice and a glimpse of possible research directions that can be of use to practitioners, decision makers, and researchers. The focus of this monograph is on hardware platform security in mobile devices. Other forms of Security, such as OS Security, are briefly covered, but from the perspective of motivating hardware platform security. Also, specific high-level attacks such as jail-breaking or rooting are not covered, though the basic attacks described in Part III can, and often are, used as stepping stones for these high-level attacks.
Cloud services have revolutionized computing in the modern world. In an increasingly networked ecosystem, it is commonplace for enterprises and private parties alike to leverage cloud services for storage and compute. The most obvious benefits include scalability, increased availability, and the potential for reduced costs when compared to lower-scale on premise infrastructures. In addition, cloud-hosted data (and compute) is accessible across platforms and is not limited by geographical constraints making collaboration attractively viable. However, the benefits of outsourcing data and computation come with security and privacy concerns. This monograph explores the advances in cloud security research across both industry and academia, with a special focus on secure infrastructure, services and storage. Besides overviewing the state of the art, the monograph highlights open problems, and possible future research directions. Cloud security is a broad topic encompassing concepts from a large cross section of domains. To make this monograph concise and meaningful, several topics and challenges that are almost entirely specific to clouds are covered. For this reason, general computing security topics such as intrusion detection, software protection, phishing etc. are excluded. While these are important building blocks that need to be considered in an end-to-end cloud-centric design, they have been extensively addressed elsewhere. The publication is divided into three parts based on a broad clustering into hardware, computation, and storage. The monograph should appeal to researchers, students and professionals who work on Cloud Computing in general, and Cloud Security specifically.
With information comes responsibility: a responsibility to use information according to appropriate restrictions. Forced by regulations and public sentiment, technology companies are increasing the transparency of how personal data is used, allowing users to make more fine-grained decisions on how and where their information should flow. Work over the last four decades has led to the term Information flow properties being introduced. These can express complex restrictions on data usage by specifying how sensitive data may flow throughout computation. In this monograph the authors match the demand of the digital society for expressing complex data-usage restrictions with the supply of information flow properties proposed in the literature. For the first time ever, the authors perform a large-scale systematization of such information flow properties. In doing so, they survey the wide variety of information flow properties that have been formulated within the last four decades, compare their expressive power, and suggest research directions for a faster convergence between future technological demand and literature supply. This concise overview of such a diverse topic provides the reader with an invaluable reference when implementing security technologies into all types of information systems. It is particularly useful for students, researchers and practitioners working on modern day information security problems.
Modern day security technologies, such as passwords, authentication protocols, firewalls, and access-control Mechanisms, are preventive in nature. That is, they stop unauthorized parties before they are able to access data, information and services or violate system policies. However, the dramatically increased scale and complexity of Internet commerce, social networking, remote work, distance learning, and myriad other forms of social, economic, and intellectual engagement online with both strangers and friends has increased the awareness that these preventive mechanisms are inadequate in certain circumstances. The result is a growing interest in accountability mechanisms to complement preventive measures. In this survey of the concept of accountability in information systems, the authors focus on systems in which policy violations are punished; that is, the actors are held accountable for their actions. As there is no accepted definition of the precise meaning of accountability in terms of such systems, the authors provide the reader with a broad overview of the concept. In doing so, they introduce the topic and place it in context of the social and systematic factors which help to define the term. They proceed to discuss in depth the mechanisms and domains across numerous disciplines before describing the available tools and proofs for implementing accountability in systems. Finally, they summarize the ideas, key published papers and ideas for future work. This monograph provides the reader with a thorough overview of the concept of accountability in modern day computing systems. In enables the reader to quickly understand the concept and the progress that has been to date in implementing the tools for the next generation of online security systems.
Since its introduction by Andrew Yao in the 1980s, multi-party computation has developed from a theoretical curiosity to an important tool for building large-scale privacy-preserving applications. Secure multi-party computation (MPC) enables a group to jointly perform a computation without disclosing any participant’s private inputs. The participants agree on a function to compute, and then can use an MPC protocol to jointly compute the output of that function on their secret inputs without revealing them. This monograph provides an introduction to multi-party computation for practitioners interested in building privacy-preserving applications and researchers who want to work in the area. The authors introduce the foundations of MPC and describe the current state of the art. The goal is to enable readers to understand what is possible today, and what may be possible in the future. It provides a starting point for building applications using MPC and for developing MPC protocols, implementations, tools, and applications. Those seeking a concise, accessible introduction to the topic which quickly enables them to build practical systems or conduct further research will find this essential reading.
