Privacy and security challenges in Machine Learning (ML) have become increasingly severe, along with ML's pervasive development and the recent demonstration of large attack surfaces. As a mature system-oriented approach, Confidential Computing has been utilized in both academia and industry to mitigate privacy and security issues in various ML scenarios. In this paper, the conjunction between ML and Confidential Computing is investigated. We systematize the prior work on Confidential Computing-assisted ML techniques that provide i) confidentiality guarantees and ii) integrity assurances, and discuss their advanced features and drawbacks. Key challenges are further identified, and we provide dedicated analyses of the limitations in existing Trusted Execution Environment (TEE) systems for ML use cases. Finally, prospective works are discussed, including grounded privacy definitions for closed-loop protection, partitioned executions of efficient ML, dedicated TEE-assisted designs for ML, TEE-aware ML, and ML full pipeline guarantees. By providing these potential solutions in our systematization of knowledge, we aim to build the bridge to help achieve a much stronger TEE-enabled ML for privacy guarantees without introducing computation and system costs.
相關內容
The rapid progress in the reasoning capability of the Multi-modal Large Language Models (MLLMs) has triggered the development of autonomous agent systems on mobile devices. MLLM-based mobile agent systems consist of perception, reasoning, memory, and multi-agent collaboration modules, enabling automatic analysis of user instructions and the design of task pipelines with only natural language and device screenshots as inputs. Despite the increased human-machine interaction efficiency, the security risks of MLLM-based mobile agent systems have not been systematically studied. Existing security benchmarks for agents mainly focus on Web scenarios, and the attack techniques against MLLMs are also limited in the mobile agent scenario. To close these gaps, this paper proposes a mobile agent security matrix covering 3 functional modules of the agent systems. Based on the security matrix, this paper proposes 4 realistic attack paths and verifies these attack paths through 8 attack methods. By analyzing the attack results, this paper reveals that MLLM-based mobile agent systems are not only vulnerable to multiple traditional attacks, but also raise new security concerns previously unconsidered. This paper highlights the need for security awareness in the design of MLLM-based systems and paves the way for future research on attacks and defense methods.
Collective remote attestation (CRA) is a security service that aims to efficiently identify compromised (often low-powered) devices in a (heterogeneous) network. The last few years have seen an extensive growth in CRA protocol proposals, showing a variety of designs guided by different network topologies, hardware assumptions and other functional requirements. However, they differ in their trust assumptions, adversary models and role descriptions making it difficult to uniformly assess their security guarantees. In this paper we present Catt, a unifying framework for CRA protocols that enables them to be compared systematically, based on a comprehensive study of 40 CRA protocols and their adversary models. Catt characterises the roles that devices can take and based on these we develop a novel set of security properties for CRA protocols. We then classify the security aims of all the studied protocols. We illustrate the applicability of our security properties by encoding them in the tamarin prover and verifying the SIMPLE+ protocol against them.
Retrieval-augmented Generation (RAG) systems have been actively studied and deployed across various industries to query on domain-specific knowledge base. However, evaluating these systems presents unique challenges due to the scarcity of domain-specific queries and corresponding ground truths, as well as a lack of systematic approaches to diagnosing the cause of failure cases -- whether they stem from knowledge deficits or issues related to system robustness. To address these challenges, we introduce GRAMMAR (GRounded And Modular Methodology for Assessment of RAG), an evaluation framework comprising two key elements: 1) a data generation process that leverages relational databases and LLMs to efficiently produce scalable query-answer pairs for evaluation. This method facilitates the separation of query logic from linguistic variations, enabling the testing of hypotheses related to non-robust textual forms; and 2) an evaluation framework that differentiates knowledge gaps from robustness and enables the identification of defective modules. Our empirical results underscore the limitations of current reference-free evaluation approaches and the reliability of GRAMMAR to accurately identify model vulnerabilities. For implementation details, refer to our GitHub repository: //github.com/xinzhel/grammar.
Vulnerabilities in software security can remain undiscovered even after being exploited. Linking attacks to vulnerabilities helps experts identify and respond promptly to the incident. This paper introduces VULDAT, a classification tool using a sentence transformer MPNET to identify system vulnerabilities from attack descriptions. Our model was applied to 100 attack techniques from the ATT&CK repository and 685 issues from the CVE repository. Then, we compare the performance of VULDAT against the other eight state-of-the-art classifiers based on sentence transformers. Our findings indicate that our model achieves the best performance with F1 score of 0.85, Precision of 0.86, and Recall of 0.83. Furthermore, we found 56% of CVE reports vulnerabilities associated with an attack were identified by VULDAT, and 61% of identified vulnerabilities were in the CVE repository.
The emergence of Large Language Models (LLMs) has demonstrated promising progress in solving logical reasoning tasks effectively. Several recent approaches have proposed to change the role of the LLM from the reasoner into a translator between natural language statements and symbolic representations which are then sent to external symbolic solvers to resolve. This paradigm has established the current state-of-the-art result in logical reasoning (i.e., deductive reasoning). However, it remains unclear whether the variance in performance of these approaches stems from the methodologies employed or the specific symbolic solvers utilized. There is a lack of consistent comparison between symbolic solvers and how they influence the overall reported performance. This is important, as each symbolic solver also has its own input symbolic language, presenting varying degrees of challenge in the translation process. To address this gap, we perform experiments on 3 deductive reasoning benchmarks with LLMs augmented with widely used symbolic solvers: Z3, Pyke, and Prover9. The tool-executable rates of symbolic translation generated by different LLMs exhibit a near 50% performance variation. This highlights a significant difference in performance rooted in very basic choices of tools. The almost linear correlation between the executable rate of translations and the accuracy of the outcomes from Prover9 highlight a strong alignment between LLMs ability to translate into Prover9 symbolic language, and the correctness of those translations.
Electronic voting systems are essential for holding virtual elections, and the need for such systems increases due to the COVID-19 pandemic and the social distancing that it mandates. One of the main challenges in e-voting systems is to secure the voting process: namely, to certify that the computed results are consistent with the cast ballots, and that the privacy of the voters is preserved. We propose herein a secure voting protocol for elections that are governed by order-based voting rules. Our protocol offers perfect ballot secrecy, in the sense that it issues only the required output, while no other information on the cast ballots is revealed. Such perfect secrecy, which is achieved by employing secure multiparty computation tools, may increase the voters' confidence and, consequently, encourage them to vote according to their true preferences. Evaluation of the protocol's computational costs establishes that it is lightweight and can be readily implemented in real-life electronic elections.
This paper comprehensively explores the ethical challenges arising from security threats to Large Language Models (LLMs). These intricate digital repositories are increasingly integrated into our daily lives, making them prime targets for attacks that can compromise their training data and the confidentiality of their data sources. The paper delves into the nuanced ethical repercussions of such security threats on society and individual privacy. We scrutinize five major threats--prompt injection, jailbreaking, Personal Identifiable Information (PII) exposure, sexually explicit content, and hate-based content--going beyond mere identification to assess their critical ethical consequences and the urgency they create for robust defensive strategies. The escalating reliance on LLMs underscores the crucial need for ensuring these systems operate within the bounds of ethical norms, particularly as their misuse can lead to significant societal and individual harm. We propose conceptualizing and developing an evaluative tool tailored for LLMs, which would serve a dual purpose: guiding developers and designers in preemptive fortification of backend systems and scrutinizing the ethical dimensions of LLM chatbot responses during the testing phase. By comparing LLM responses with those expected from humans in a moral context, we aim to discern the degree to which AI behaviors align with the ethical values held by a broader society. Ultimately, this paper not only underscores the ethical troubles presented by LLMs; it also highlights a path toward cultivating trust in these systems.
In distributed computing by mobile robots, robots are deployed over a region, continuous or discrete, operating through a sequence of \textit{look-compute-move} cycles. An extensive study has been carried out to understand the computational powers of different robot models. The models vary on the ability to 1)~remember constant size information and 2)~communicate constant size message. Depending on the abilities the different models are 1)~$\mathcal{OBLOT}$ (robots are oblivious and silent), 2)~$\mathcal{FSTA}$ (robots have finite states but silent), 3)~$\mathcal{FCOM}$ (robots are oblivious but can communicate constant size information) and, 4)~$\mathcal{LUMI}$ (robots have finite states and can communicate constant size information). Another factor that affects computational ability is the scheduler that decides the activation time of the robots. The main three schedulers are \textit{fully-synchronous}, \textit{semi-synchronous} and \textit{asynchronous}. Combining the models ($M$) with schedulers ($K$), we have twelve combinations $M^K$. In the euclidean domain, the comparisons between these twelve variants have been done in different works for transparent robots, opaque robots, and robots with limited visibility. There is a vacant space for similar works when robots are operating on discrete regions like networks. It demands separate research attention because there have been a series of works where robots operate on different networks, and there is a fundamental difference when robots are operating on a continuous domain versus a discrete domain in terms of robots' movement. This work contributes to filling the space by giving a full comparison table for all models with two synchronous schedulers: fully-synchronous and semi-synchronous.
Reasoning, a crucial ability for complex problem-solving, plays a pivotal role in various real-world settings such as negotiation, medical diagnosis, and criminal investigation. It serves as a fundamental methodology in the field of Artificial General Intelligence (AGI). With the ongoing development of foundation models, e.g., Large Language Models (LLMs), there is a growing interest in exploring their abilities in reasoning tasks. In this paper, we introduce seminal foundation models proposed or adaptable for reasoning, highlighting the latest advancements in various reasoning tasks, methods, and benchmarks. We then delve into the potential future directions behind the emergence of reasoning abilities within foundation models. We also discuss the relevance of multimodal learning, autonomous agents, and super alignment in the context of reasoning. By discussing these future research directions, we hope to inspire researchers in their exploration of this field, stimulate further advancements in reasoning with foundation models, and contribute to the development of AGI.
The advent of large language models marks a revolutionary breakthrough in artificial intelligence. With the unprecedented scale of training and model parameters, the capability of large language models has been dramatically improved, leading to human-like performances in understanding, language synthesizing, and common-sense reasoning, etc. Such a major leap-forward in general AI capacity will change the pattern of how personalization is conducted. For one thing, it will reform the way of interaction between humans and personalization systems. Instead of being a passive medium of information filtering, large language models present the foundation for active user engagement. On top of such a new foundation, user requests can be proactively explored, and user's required information can be delivered in a natural and explainable way. For another thing, it will also considerably expand the scope of personalization, making it grow from the sole function of collecting personalized information to the compound function of providing personalized services. By leveraging large language models as general-purpose interface, the personalization systems may compile user requests into plans, calls the functions of external tools to execute the plans, and integrate the tools' outputs to complete the end-to-end personalization tasks. Today, large language models are still being developed, whereas the application in personalization is largely unexplored. Therefore, we consider it to be the right time to review the challenges in personalization and the opportunities to address them with LLMs. In particular, we dedicate this perspective paper to the discussion of the following aspects: the development and challenges for the existing personalization system, the newly emerged capabilities of large language models, and the potential ways of making use of large language models for personalization.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191