This paper proposes Meta Parallel Graph Neural Network (MPGNN) to establish a scalable Network Intrusion Detection System (NIDS) for large-scale Internet of Things (IoT) networks. MPGNN leverages a meta-learning framework to optimize the parallelism of GNN-based NIDS. The core of MPGNN is a coalition formation policy that generates meta-knowledge for partitioning a massive graph into multiple coalitions/subgraphs in a way that maximizes the performance and efficiency of parallel coalitional NIDSs. We propose an offline reinforcement learning algorithm, called Graph-Embedded Adversarially Trained Actor-Critic (G-ATAC), to learn a coalition formation policy that jointly optimizes intrusion detection accuracy, communication overheads, and computational complexities of coalitional NIDSs. In particular, G-ATAC learns to capture the temporal dependencies of network states and coalition formation decisions over offline data, eliminating the need for expensive online interactions with large IoT networks. Given generated coalitions, MPGNN employs E-GraphSAGE to establish coalitional NIDSs which then collaborate via ensemble prediction to accomplish intrusion detection for the entire network. We evaluate MPGNN on two real-world datasets. The experimental results demonstrate the superiority of our method with substantial improvements in F1 score, surpassing the state-of-the-art methods by 0.38 and 0.29 for the respective datasets. Compared to the centralized NIDS, MPGNN reduces the training time of NIDS by 41.63% and 22.11%, while maintaining an intrusion detection performance comparable to centralized NIDS.
论文检索
输入标题、作者或关键词，从 432 篇学术成果中精准定位
Serverless computing is supplanting past versions of cloud computing as the easiest way to rapidly prototype and deploy applications. However, the reentrant and ephemeral nature of serverless functions only exacerbates the challenge of correctly specifying security policies. Unfortunately, with role-based access control solutions like Amazon Identity and Access Management (IAM) already suffering from pervasive misconfiguration problems, the likelihood of policy failures in serverless applications is high. In this work, we introduce GRASP, a graph-based analysis framework for modeling serverless access control policies as queryable reachability graphs. GRASP generates reusable models that represent the principals of a serverless application and the interactions between those principals. We implement GRASP for Amazon IAM in Prolog, then deploy it on a corpus of 731 open source Amazon Lambda applications. We find that serverless policies tend to be short and highly permissive, e.g., 92% of surveyed policies are comprised of just 10 statements and 30% exhibit full reachability between all application functions and resources. We then use GRASP to identify potential attack vectors permitted by these policies, including hundreds of sensitive access channels, a dozen publicly-exposed resources, and four channels that may permit an attacker to exfiltrate an application's private resources through one of its public resources. These findings demonstrate GRASP's utility as a means of identifying opportunities for hardening application policies and highlighting potential exfiltration channels.
Permissionless blockchains promise resilience against censorship by a single entity. This suggests that deterministic rules, not third-party actors, decide whether a transaction is appended to the blockchain. In 2022, the U.S. ØFAC sanctioned a Bitcoin mixer and an Ethereum application, challenging the neutrality of permissionless blockchains. In this paper, we formalize, quantify, and analyze the security impact of blockchain censorship. We start by defining censorship, followed by a quantitative assessment of current censorship practices. We find that 46% of Ethereum blocks were made by censoring actors complying with OFAC sanctions, indicating the significant impact of OFAC sanctions on the neutrality of public blockchains. We discover that censorship affects not only neutrality but also security. After Ethereum's transition to ¶oS, censored transactions faced an average delay of 85%, compromising their security and strengthening sandwich adversaries.
We evaluate a bundle of specifications from the Self-Sovereign Identity (SSI) paradigm to construct an authentication protocol for the Web. We demonstrate how relevant standards such as W3C Verifiable Credentials (VC), W3C Decentralised Identifiers (DIDs), and components of the Hyperledger Aries Framework are to be assembled methodologically into a protocol. We make those assumptions from standard trust models explicit that underlie the derived protocol, and verify security and privacy properties, notably secrecy, authentication, and unlinkability. This enables us to formally justify the additional precision that we urge these specifications to consider, to ensure that implementors of SSI-based systems do not neglect security-critical controls.
To detect unknown attack traffic, anomaly-based network intrusion detection systems (NIDSs) are widely used in Internet infrastructure. However, the security communities realize some limitations when they put most existing proposals into practice. The challenges are mainly concerned with (i) fine-grained emerging attack detection and (ii) incremental updates/adaptations. To tackle these problems, we propose to decouple the need for model capabilities by transforming known/new class identification issues into multiple independent one-class learning tasks. Based on the above core ideas, we develop Trident, a universal framework for fine-grained unknown encrypted traffic detection. It consists of three main modules, i.e., tSieve, tScissors, and tMagnifier are used for profiling traffic, determining outlier thresholds, and clustering respectively, each of which supports custom configuration. Using four popular datasets of network traces, we show that Trident significantly outperforms 16 state-of-the-art (SOTA) methods. Furthermore, a series of experiments (concept drift, overhead/parameter evaluation) demonstrate the stability, scalability, and practicality of Trident.
There has been substantial commentary on the role of cyberattacks carried out by low-level cybercrime actors in the Russia-Ukraine conflict. We analyse 358k website defacement attacks, 1.7M UDP amplification DDoS attacks, 1764 posts made by 372 users on Hack Forums mentioning the two countries, and 441 Telegram announcements (with 58k replies) of a volunteer hacking group for two months before and four months after the invasion. We find the conflict briefly but notably caught the attention of low-level cybercrime actors, with significant increases in online discussion and both types of attacks targeting Russia and Ukraine. However, there was little evidence of high-profile actions; the role of these players in the ongoing hybrid warfare is minor, and they should be separated from persistent and motivated 'hacktivists' in state-sponsored operations. Their involvement in the conflict appears to have been short-lived and fleeting, with a clear loss of interest in discussing the situation and carrying out both website defacement and DDoS attacks against either Russia or Ukraine after just a few weeks.
Cryptocurrencies, while revolutionary, have become a magnet for malicious actors. With numerous reports underscoring cyberattacks and scams in this domain, our paper takes the lead in characterizing visual scams associated with cryptocurrency wallets---a fundamental component of Web3. Specifically, scammers capitalize on the omission of vital wallet interface details, such as token symbols, wallet addresses, and smart contract function names, to mislead users, potentially resulting in unintended financial losses. Analyzing Ethereum blockchain transactions from July 2022 to June 2023, we uncovered a total of 24,901,115 visual scam incidents, which include 3,585,493 counterfeit token attacks, 21,281,749 zero-transfer attacks, and 33,873 function name attacks, orchestrated by 6,768 distinct attackers. Shockingly, over 28,414 victims fell prey to these scams, with losses surpassing 27 million USD. This alarming data underscores the pressing need for robust protective measures. By profiling the typical victims and attackers, we are able to propose mitigation strategies informed by our findings.
File upload is a critical feature incorporated by a myriad of web applications in an effort to enable users to share and manage their files conveniently. It has been used in many useful services such as file-sharing and social media. While file upload is an essential component of web applications, the lack of rigorous checks on the file name, type, and content of the uploaded files can result in security issues, often referred to as Unrestricted File Upload (UFU). In this study, we analyze the (in)security of popular file upload libraries and real-world applications in the Node.js ecosystem. To automate our analysis, we propose and implement NodeSEC- a tool designed to analyze file upload insecurities in Node.js applications and libraries. NodeSEC generates unique payloads and thoroughly evaluates the application's file upload security against 13 distinct UFU-type attacks. Utilizing NodeSEC, we analyze the most popular file upload libraries and real-world applications in the Node.js ecosystem. Our analysis results reveal that some real-world web applications are vulnerable to UFU attacks and disclose serious security bugs in file upload libraries. As of this writing, we received 19 CVEs and two US-CERT cases for the security issues that we reported. Our findings provide strong evidence that dynamic features of Node.js applications introduce security shortcomings and that web developers should be cautious when implementing file upload features in their applications. Finally, combining our responsible disclosure experience and root cause analysis, we identified the main causes of significant security weaknesses in file uploads in Node.js.
Private browsing is a common feature of web browsers on desktop platforms. This feature protects the privacy of users browsing the Internet and, therefore, is widely welcomed by users. In recent years, with the popularity of smartphones, the private browsing mode has been introduced into mobile browsers. However, its deployment on mobile platforms has not been well evaluated. To bridge the gap, in this work, we systemically studied the private browsing modes of Android browser apps. Specifically, we proposed six private rules for mobile browsers to follow by combining the mobile browsing features with the previous research on private browsing. Furthermore, we designed an automated analysis framework, BroDroid, to detect whether mobile browsers violate these rules. Also, with BroDroid, we evaluated 49 popular browser apps crawled from Google Play. Finally, BroDroid successfully identified 58 violations, some of which come from the promised capabilities of the browser. We reported our discovered issues to the corresponding developers, and four of them (Yandex Browser, Mint Browser, Web Explorer, and Net Fast Web Browser) have acknowledged our findings. Our observation may be the tip of the iceberg, and more efforts should be put into improving the privacy protections of mobile browsers.
Blockchain and smart contracts are one of the key technologies promoting Web 3.0. However, due to security considerations and consistency requirements, smart contracts currently only support simple and deterministic programs, which significantly hinders their deployment in intelligent Web 3.0 applications. To enhance smart contracts intelligence on the blockchain, we propose SMART, a plug-in smart contract framework that supports efficient AI model inference while being compatible with existing blockchains. To handle the high complexity of model inference, we propose an on-chain and off-chain joint execution model, which separates the SMART contract into two parts: the deterministic code still runs inside an on-chain virtual machine, while the complex model inference is offloaded to off-chain compute nodes. To solve the non-determinism brought by model inference, we leverage Trusted Execution Environments (TEEs) to endorse the integrity and correctness of the off-chain execution. We also design distributed attestation and secret key provisioning schemes to further enhance the system security and model privacy. We implement a SMART prototype and evaluate it on a popular Ethereum Virtual Machine (EVM)-based blockchain. Theoretical analysis and prototype evaluation show that SMART not only achieves the security goals of correctness, liveness, and model privacy, but also has approximately 5 orders of magnitude faster inference efficiency than existing on-chain solutions.
Asking multi-turn clarifying questions has been applied in various conversational search systems to help recommend people, commodities, and images to users. However, its importance is still not emphasized in the Web search. In this paper, we make a step to extend the multi-turn clarification generation to Web search for clarifying users' ambiguous or faceted intents. Compared with other conversational search scenarios, Web search queries are more complicated, so clarification should be generated instead of being selected which is commonly applied in current studies. To this end, we first define the whole process of multi-turn Web search clarification composed of clarification candidate generation, optimal clarification selection, and document retrieval. Due to the lack of multi-turn open-domain clarification data, we first design a simple yet effective rule-based method to fit the above three components. After that, by utilizing the in-context learning and zero-shot instruction ability of large language models (LLMs), we implement clarification generation and selection by prompting LLMs with demonstrations and declarations, further improving the clarification effectiveness. To evaluate our proposed methods, we first measure whether our methods can improve the ability to retrieve documents. We also evaluate the quality of generated candidate facets. Experimental results show that, compared with existing single-turn methods for Web search clarification, our proposed framework is more suitable for open-domain Web search systems in asking multi-turn clarification questions to clarify users' ambiguous or faceted intents.
In the contemporary digital landscape, search engines play an invaluable role in information access, yet they often face challenges in Cross-Lingual Information Retrieval (CLIR). Though attempts are made to improve CLIR, current methods still leave users grappling with issues such as misplaced named entities and lost cultural context when querying in non-native languages. While some advances have been made using Neural Machine Translation models and cross-lingual representation, these are not without limitations. Enter the paradigm shift brought about by Large Language Models (LLMs), which have transformed search engines from simple retrievers to generators of contextually relevant information. This paper introduces the Multilingual Information Model for Intelligent Retrieval (MIMIR). Built on the power of LLMs, MIMIR directly responds in the language of the user's query, reducing the need for post-search translations. Our model's architecture encompasses a dual-module system: a retriever for searching multilingual documents and a responder for crafting answers in the user's desired language. Through a unique unified training framework, with the retriever serving as a reward model supervising the responder, and in turn, the responder producing synthetic data to refine the retriever's proficiency, MIMIR's retriever and responder iteratively enhance each other. Performance evaluations via CLEF and MKQA benchmarks reveal MIMIR's superiority over existing models, effectively addressing traditional CLIR challenges.
This paper introduces a novel information retrieval (IR) task of Conversational Entity Retrieval from a Knowledge Graph (CER-KG), which extends non-conversational entity retrieval from a knowledge graph (KG) to the conversational scenario. The user queries in CER-KG dialog turns may rely on the results of the preceding turns, which are KG entities. Similar to the conversational document IR, CER-KG can be viewed as a sequence of interrelated ranking tasks. To enable future research on CER-KG, we created QBLink-KG, a publicly available benchmark that was adapted from QBLink, a benchmark for text-based conversational reading comprehension of Wikipedia. As an initial approach to CER-KG, we experimented with Transformer- and LSTM-based query encoders in combination with the Neural Architecture for Conversational Entity Retrieval (NACER), our proposed feature-based neural architecture for entity ranking in CER-KG. NACER computes the ranking score of a candidate KG entity by taking into account diverse lexical and semantic matching signals between various KG components in its neighborhood, such as entities, categories, and literals, as well as entities in the results of the preceding turns in dialog history. The reported experimental results reveal the key challenges of CER-KG along with the possible directions for new approaches to this task.
Session search involves a series of interactive queries and actions to fulfill user's complex information need. Current strategies typically prioritize sequential modeling for deep semantic understanding, overlooking the graph structure in interactions. While some approaches focus on capturing structural information, they use a generalized representation for documents, neglecting the word-level semantic modeling. In this paper, we propose Symbolic Graph Ranker (SGR), which aims to take advantage of both text-based and graph-based approaches by leveraging the power of recent Large Language Models (LLMs). Concretely, we first introduce a set of symbolic grammar rules to convert session graph into text. This allows integrating session history, interaction process, and task instruction seamlessly as inputs for the LLM. Moreover, given the natural discrepancy between LLMs pre-trained on textual corpora, and the symbolic language we produce using our graph-to-text grammar, our objective is to enhance LLMs' ability to capture graph structures within a textual format. To achieve this, we introduce a set of self-supervised symbolic learning tasks including link prediction, node content generation, and generative contrastive learning, to enable LLMs to capture the topological information from coarse-grained to fine-grained. Experiment results and comprehensive analysis on two benchmark datasets, AOL and Tiangong-ST, confirm the superiority of our approach. Our paradigm also offers a novel and effective methodology that bridges the gap between traditional search strategies and modern LLMs.
Document retrieval has greatly benefited from the advancements of large-scale pre-trained language models (PLMs). However, their effectiveness is often limited in theme-specific applications for specialized areas or industries, due to unique terminologies, incomplete contexts of user queries, and specialized search intents. To capture the theme-specific information and improve retrieval, we propose to use a corpus topical taxonomy, which outlines the latent topic structure of the corpus while reflecting user-interested aspects. We introduce ToTER (Topical Taxonomy Enhanced Retrieval) framework, which identifies the central topics of queries and documents with the guidance of the taxonomy, and exploits their topical relatedness to supplement missing contexts. As a plug-and-play framework, ToTER can be flexibly employed to enhance various PLM-based retrievers. Through extensive quantitative, ablative, and exploratory experiments on two real-world datasets, we ascertain the benefits of using topical taxonomy for retrieval in theme-specific applications and demonstrate the effectiveness of ToTER.
Ranking is at the core of many artificial intelligence (AI) applications, including search engines, recommender systems, etc. Modern ranking systems are often constructed with learning-to-rank (LTR) models built from user behavior signals. While previous studies have demonstrated the effectiveness of using user behavior signals (e.g., clicks) as both features and labels of LTR algorithms, we argue that existing LTR algorithms that indiscriminately treat behavior and non-behavior signals in input features could lead to suboptimal performance in practice. Because user behavior signals often have strong correlations with the ranking objective and can only be collected on items that have already been shown to users, directly using behavior signals in LTR could create an exploitation bias that hurts the system performance in the long run. To address the exploitation bias, we propose an uncertainty-aware empirical Bayes based ranking algorithm, referred to as EBRank. Specifically, EBRank uses a sole non-behavior feature-based prior model to get a prior estimation of relevance. In the dynamic training and serving of ranking systems, EBRank uses the observed user behaviors to update posterior relevance estimation instead of concatenating behaviors as features in ranking models. Besides, EBRank additionally applies an uncertainty-aware exploration strategy to explore actively and collect user behaviors for empirical Bayesian modeling. Experiments on three public datasets show that EBRank is effective, practical and significantly outperforms state-of-the-art ranking algorithms.
In mixed-initiative conversational search systems, clarifying questions aid users who struggle to express their intentions in a single query. These questions aim to uncover user's information needs and resolve query ambiguities. We hypothesize that in scenarios where multimodal information is pertinent, the clarification process can be improved by using non-textual information. Therefore, we propose to add images to clarifying questions and formulate the novel task of asking multimodal clarifying questions in open-domain, mixed-initiative conversational search systems. To facilitate research into this task, we collect a dataset named Melon that contains over 4k multimodal clarifying questions, enriched with over 14k images. We also propose a multimodal query clarification model named Marto and adopt a prompt-based, generative fine-tuning strategy to perform the training of different stages with different prompts. Several analyses are conducted to understand the importance of multimodal contents during the query clarification phase. Experimental results indicate that the addition of images leads to significant improvements of up to 90% in retrieval performance when selecting the relevant images. Extensive analyses are also performed to show the superiority of Marto compared with discriminative baselines.
Cognitive Personalized Search Integrating Large Language Models with an Efficient Memory Mechanism
PDF ↗Traditional search engines usually provide identical search results for all users, overlooking individual preferences. To counter this limitation, personalized search has been developed to re-rank results based on user preferences derived from query logs. Deep learning-based personalized search methods have shown promise, but they rely heavily on abundant training data, making them susceptible to data sparsity challenges. This paper proposes a Cognitive Personalized Search (CoPS) model, which integrates Large Language Models (LLMs) with a cognitive memory mechanism inspired by human cognition. CoPS employs LLMs to enhance user modeling and user search experience. The cognitive memory mechanism comprises sensory memory for quick sensory responses, working memory for sophisticated cognitive responses, and long-term memory for storing historical interactions. CoPS handles new queries using a three-step approach: identifying re-finding behaviors, constructing user profiles with relevant historical information, and ranking documents based on personalized query intent. Experiments show that CoPS outperforms baseline models in zero-shot scenarios.
Retrieval-augmented generation have become central in natural language processing due to their efficacy in generating factual content. While traditional methods employ single-time retrieval, more recent approaches have shifted towards multi-time retrieval for multi-hop reasoning tasks. However, these strategies are bound by predefined reasoning steps, potentially leading to inaccuracies in response generation. This paper introduces MetaRAG, an approach that combines the retrieval-augmented generation process with metacognition. Drawing from cognitive psychology, metacognition allows an entity to self-reflect and critically evaluate its cognitive processes. By integrating this, MetaRAG enables the model to monitor, evaluate, and plan its response strategies, enhancing its introspective reasoning abilities. Through a three-step metacognitive regulation pipeline, the model can identify inadequacies in initial cognitive responses and fixes them. Empirical evaluations show that MetaRAG significantly outperforms existing methods.
Recent research has shown that transformer networks can be used as differentiable search indexes by representing each document as a sequence of document ID tokens. These generative retrieval models cast the retrieval problem to a document ID generation problem for each query. Despite their elegant design, existing generative retrieval models only perform well on artificially-constructed and small-scale collections. This paper represents an important milestone in generative retrieval research by showing that generative retrieval models can be trained to perform effectively on large-scale standard retrieval benchmarks. In more detail, we propose RIPOR- an optimization framework for generative retrieval that is designed based on two often-overlooked fundamental design considerations. First, RIPOR introduces a novel prefix-oriented ranking optimization algorithm for accurate estimation of relevance score during sequential document ID generation. Second, RIPOR constructs document IDs based on the relevance associations between queries and documents. Evaluation on MSMARCO and TREC Deep Learning Track reveals that RIPOR surpasses state-of-the-art generative retrieval models by a large margin (e.g., 30.5% MRR improvements on MS MARCO Dev Set).