Haoyu Wang

Xinyi Hou, Yanjie Zhao, Yue Liu et al.

Large Language Models (LLMs) have significantly impacted numerous domains, including Software Engineering (SE). Many recent publications have explored LLMs applied to various SE tasks. Nevertheless, a comprehensive understanding of the application, effects, and possible limitations of LLMs on SE is still in its early stages. To bridge this gap, we conducted a systematic literature review (SLR) on LLM4SE, with a particular focus on understanding how LLMs can be exploited to optimize processes and outcomes. We select and analyze 395 research papers from January 2017 to January 2024 to answer four key research questions (RQs). In RQ1, we categorize different LLMs that have been employed in SE tasks, characterizing their distinctive features and uses. In RQ2, we analyze the methods used in data collection, preprocessing, and application, highlighting the role of well-curated datasets for successful LLM for SE implementation. RQ3 investigates the strategies employed to optimize and evaluate the performance of LLMs in SE. Finally, RQ4 examines the specific SE tasks where LLMs have shown success to date, illustrating their practical contributions to the field. From the answers to these RQs, we discuss the current state-of-the-art and trends, identifying gaps in existing research, and flagging promising areas for future study. Our artifacts are publicly available at https://github.com/xinyi-hou/LLM4SE_SLR.

Yanzhe Hu, Shenao Wang, Tianyuan Nie et al.

Large Language Models (LLMs) have revolutionized artificial intelligence (AI), driving breakthroughs in natural language understanding, text generation, and autonomous systems. However, the rapid growth of LLMs presents significant challenges in the security and reliability of the Large Language Model Supply Chain (LLMSC), a complex network of open-source components, libraries, and tools essential for LLM development and deployment. Despite its critical importance, the LLMSC remains underexplored, particularly regarding its structural characteristics, domain composition, and security vulnerabilities. To address this gap, we conduct the first empirical study of the LLMSC, analyzing a curated dataset of open-source packages from PyPI and NPM across 14 functional domains. We construct a directed dependency graph comprising 13,486 nodes, 28,704 edges, and 180 unique vulnerabilities to investigate the structural characteristics of the LLMSC and analyze how security risks propagate through its dependency network. Our findings reveal that the LLMSC exhibits a locally dense, globally sparse topology, with 72.38% of dependency trees containing fewer than 5 nodes, while a few large trees dominate the ecosystem, accounting for 77.66% of all nodes. The graph is characterized by high-degree hubs, with the top 5 most connected nodes averaging 1,207 dependents each. Security analysis shows that critical vulnerabilities propagate to an average of 142.1 nodes at the second layer of dependency trees and peak at 237.8 affected nodes at the third layer. Notably, cascading risks are concentrated in critical hub nodes such as \texttt{transformers}, which directly or indirectly affect over 1,300 downstream packages. These findings provide quantitative insights into the structural and security dynamics of the LLMSC and emphasize the need for targeted mitigation strategies to enhance ecosystem resilience.

Shenao Wang, Yanjie Zhao, Zhao Liu et al.

LLMs are rapidly transitioning from research prototypes to core components in production systems across industries such as finance and healthcare. These deployments rely on a growing ecosystem of open-source frameworks and components, collectively forming the LLM supply chain. However, the increasing complexity of this stack introduces critical security risks that remain underexplored. In this work, we present the first systematic and large-scale empirical study of vulnerabilities in the LLM supply chain, analyzing 529 real-world vulnerabilities spanning 77 widely adopted repositories across 12 lifecycle stages. Our findings reveal that the disclosed vulnerabilities are heavily concentrated in the application layer and model integration layer. Among these, 18.5% of the vulnerabilities are LLM-specific, arising from unique architectural and workflow characteristics, such as improper handling of critical resources like model files, prompt templates, and datasets, as well as generative output validation errors. To understand the real-world impact, we examine 63,243 publicly exposed LLM services and find that 45.6% are affected by at least one remotely exploitable vulnerability, over 70% of which are critical or high severity. By correlating these vulnerabilities with their potential exploit scenarios in the wild, we observed that these issues can lead to serious security consequences, including model tampering, sensitive dataset exposure, and unauthorized GPU resource abuse. Based on our findings, we distill 5 actionable insights that can guide engineering teams in auditing and securing LLM services. Our work offers a data-driven foundation for securing the LLM supply chain and highlights urgent directions for both industry and future research.

Ziyan Huang, Zhongying Deng, Jin Ye et al.

Although deep learning have revolutionized abdominal multi-organ segmentation, models often struggle with generalization due to training on small, specific datasets. With the recent emergence of large-scale datasets, some important questions arise: \textbf{Can models trained on these datasets generalize well on different ones? If yes/no, how to further improve their generalizability?} To address these questions, we introduce A-Eval, a benchmark for the cross-dataset Evaluation ('Eval') of Abdominal ('A') multi-organ segmentation. We employ training sets from four large-scale public datasets: FLARE22, AMOS, WORD, and TotalSegmentator, each providing extensive labels for abdominal multi-organ segmentation. For evaluation, we incorporate the validation sets from these datasets along with the training set from the BTCV dataset, forming a robust benchmark comprising five distinct datasets. We evaluate the generalizability of various models using the A-Eval benchmark, with a focus on diverse data usage scenarios: training on individual datasets independently, utilizing unlabeled data via pseudo-labeling, mixing different modalities, and joint training across all available datasets. Additionally, we explore the impact of model sizes on cross-dataset generalizability. Through these analyses, we underline the importance of effective data usage in enhancing models' generalization capabilities, offering valuable insights for assembling large-scale datasets and improving training strategies. The code and pre-trained models are available at \href{https://github.com/uni-medical/A-Eval}{https://github.com/uni-medical/A-Eval}.

Zhihao Lin, Wei Ma, Mingyi Zhou et al.

In recent years, Large Language Models (LLMs) have gained widespread use, raising concerns about their security. Traditional jailbreak attacks, which often rely on the model internal information or have limitations when exploring the unsafe behavior of the victim model, limiting their reducing their general applicability. In this paper, we introduce PathSeeker, a novel black-box jailbreak method, which is inspired by the game of rats escaping a maze. We think that each LLM has its unique "security maze", and attackers attempt to find the exit learning from the received feedback and their accumulated experience to compromise the target LLM's security defences. Our approach leverages multi-agent reinforcement learning, where smaller models collaborate to guide the main LLM in performing mutation operations to achieve the attack objectives. By progressively modifying inputs based on the model's feedback, our system induces richer, harmful responses. During our manual attempts to perform jailbreak attacks, we found that the vocabulary of the response of the target model gradually became richer and eventually produced harmful responses. Based on the observation, we also introduce a reward mechanism that exploits the expansion of vocabulary richness in LLM responses to weaken security constraints. Our method outperforms five state-of-the-art attack techniques when tested across 13 commercial and open-source LLMs, achieving high attack success rates, especially in strongly aligned commercial models like GPT-4o-mini, Claude-3.5, and GLM-4-air with strong safety alignment. This study aims to improve the understanding of LLM security vulnerabilities and we hope that this sturdy can contribute to the development of more robust defenses.

Yufei Li, Yanchi Liu, Haoyu Wang et al.

Logs play a crucial role in system monitoring and debugging by recording valuable system information, including events and states. Although various methods have been proposed to detect anomalies in log sequences, they often overlook the significance of considering relations among system components, such as services and users, which can be identified from log contents. Understanding these relations is vital for detecting anomalies and their underlying causes. To address this issue, we introduce GLAD, a Graph-based Log Anomaly Detection framework designed to detect relational anomalies in system logs. GLAD incorporates log semantics, relational patterns, and sequential patterns into a unified framework for anomaly detection. Specifically, GLAD first introduces a field extraction module that utilizes prompt-based few-shot learning to identify essential fields from log contents. Then GLAD constructs dynamic log graphs for sliding windows by interconnecting extracted fields and log events parsed from the log parser. These graphs represent events and fields as nodes and their relations as edges. Subsequently, GLAD utilizes a temporal-attentive graph edge anomaly detection model for identifying anomalous relations in these dynamic log graphs. This model employs a Graph Neural Network (GNN)-based encoder enhanced with transformers to capture content, structural and temporal features. We evaluate our proposed method on three datasets, and the results demonstrate the effectiveness of GLAD in detecting anomalies indicated by varying relational patterns.

Xiaogeng Liu, Minghui Li, Haoyu Wang et al.

Deep neural networks are proven to be vulnerable to backdoor attacks. Detecting the trigger samples during the inference stage, i.e., the test-time trigger sample detection, can prevent the backdoor from being triggered. However, existing detection methods often require the defenders to have high accessibility to victim models, extra clean data, or knowledge about the appearance of backdoor triggers, limiting their practicality. In this paper, we propose the test-time corruption robustness consistency evaluation (TeCo), a novel test-time trigger sample detection method that only needs the hard-label outputs of the victim models without any extra information. Our journey begins with the intriguing observation that the backdoor-infected models have similar performance across different image corruptions for the clean images, but perform discrepantly for the trigger samples. Based on this phenomenon, we design TeCo to evaluate test-time robustness consistency by calculating the deviation of severity that leads to predictions' transition across different corruptions. Extensive experiments demonstrate that compared with state-of-the-art defenses, which even require either certain information about the trigger types or accessibility of clean data, TeCo outperforms them on different backdoor attacks, datasets, and model architectures, enjoying a higher AUROC by 10% and 5 times of stability.

Xin-Cheng Wen, Cuiyun Gao, Feng Luo et al.

Prior studies generally focus on software vulnerability detection and have demonstrated the effectiveness of Graph Neural Network (GNN)-based approaches for the task. Considering the various types of software vulnerabilities and the associated different degrees of severity, it is also beneficial to determine the type of each vulnerable code for developers. In this paper, we observe that the distribution of vulnerability type is long-tailed in practice, where a small portion of classes have massive samples (i.e., head classes) but the others contain only a few samples (i.e., tail classes). Directly adopting previous vulnerability detection approaches tends to result in poor detection performance, mainly due to two reasons. First, it is difficult to effectively learn the vulnerability representation due to the over-smoothing issue of GNNs. Second, vulnerability types in tails are hard to be predicted due to the extremely few associated samples.To alleviate these issues, we propose a Long-taIled software VulnerABiLity typE classification approach, called LIVABLE. LIVABLE mainly consists of two modules, including (1) vulnerability representation learning module, which improves the propagation steps in GNN to distinguish node representations by a differentiated propagation method. A sequence-to-sequence model is also involved to enhance the vulnerability representations. (2) adaptive re-weighting module, which adjusts the learning weights for different types according to the training epochs and numbers of associated samples by a novel training loss.

Xinyu She, Yue Liu, Yanjie Zhao et al.

Modern language models (LMs) have been successfully employed in source code generation and understanding, leading to a significant increase in research focused on learning-based code intelligence, such as automated bug repair, and test case generation. Despite their great potential, language models for code intelligence (LM4Code) are susceptible to potential pitfalls, which hinder realistic performance and further impact their reliability and applicability in real-world deployment. Such challenges drive the need for a comprehensive understanding - not just identifying these issues but delving into their possible implications and existing solutions to build more reliable language models tailored to code intelligence. Based on a well-defined systematic research approach, we conducted an extensive literature review to uncover the pitfalls inherent in LM4Code. Finally, 67 primary studies from top-tier venues have been identified. After carefully examining these studies, we designed a taxonomy of pitfalls in LM4Code research and conducted a systematic study to summarize the issues, implications, current solutions, and challenges of different pitfalls for LM4Code systems. We developed a comprehensive classification scheme that dissects pitfalls across four crucial aspects: data collection and labeling, system design and learning, performance evaluation, and deployment and maintenance. Through this study, we aim to provide a roadmap for researchers and practitioners, facilitating their understanding and utilization of LM4Code in reliable and trustworthy ways.

Zhibo Zhang, Wuxia Bai, Yuxi Li et al.

Large language models (LLMs) have achieved unprecedented success in the field of natural language processing. However, the black-box nature of their internal mechanisms has brought many concerns about their trustworthiness and interpretability. Recent research has discovered a class of abnormal tokens in the model's vocabulary space and named them "glitch tokens". Those tokens, once included in the input, may induce the model to produce incorrect, irrelevant, or even harmful results, drastically undermining the reliability and practicality of LLMs. In this work, we aim to enhance the understanding of glitch tokens and propose techniques for their detection and mitigation. We first reveal the characteristic features induced by glitch tokens on LLMs, which are evidenced by significant deviations in the distributions of attention patterns and dynamic information from intermediate model layers. Based on the insights, we develop GlitchProber, a tool for efficient glitch token detection and mitigation. GlitchProber utilizes small-scale sampling, principal component analysis for accelerated feature extraction, and a simple classifier for efficient vocabulary screening. Taking one step further, GlitchProber rectifies abnormal model intermediate layer values to mitigate the destructive effects of glitch tokens. Evaluated on five mainstream open-source LLMs, GlitchProber demonstrates higher efficiency, precision, and recall compared to existing approaches, with an average F1 score of 0.86 and an average repair rate of 50.06%. GlitchProber unveils a novel path to address the challenges posed by glitch tokens and inspires future research toward more robust and interpretable LLMs.

Xiaogeng Liu, Haoyu Wang, Yechao Zhang et al.

The data-centric machine learning aims to find effective ways to build appropriate datasets which can improve the performance of AI models. In this paper, we mainly focus on designing an efficient data-centric scheme to improve robustness for models towards unforeseen malicious inputs in the black-box test settings. Specifically, we introduce a noised-based data augmentation method which is composed of Gaussian Noise, Salt-and-Pepper noise, and the PGD adversarial perturbations. The proposed method is built on lightweight algorithms and proved highly effective based on comprehensive evaluations, showing good efficiency on computation cost and robustness enhancement. In addition, we share our insights about the data-centric robust machine learning gained from our experiments.

Xinyi Hou, Yanjie Zhao, Haoyu Wang

LLM app stores have seen rapid growth, leading to the proliferation of numerous custom LLM apps. However, this expansion raises security concerns. In this study, we propose a three-layer concern framework to identify the potential security risks of LLM apps, i.e., LLM apps with abusive potential, LLM apps with malicious intent, and LLM apps with exploitable vulnerabilities. Over five months, we collected 786,036 LLM apps from six major app stores: GPT Store, FlowGPT, Poe, Coze, Cici, and Character.AI. Our research integrates static and dynamic analysis, the development of a large-scale toxic word dictionary (i.e., ToxicDict) comprising over 31,783 entries, and automated monitoring tools to identify and mitigate threats. We uncovered that 15,146 apps had misleading descriptions, 1,366 collected sensitive personal information against their privacy policies, and 15,996 generated harmful content such as hate speech, self-harm, extremism, etc. Additionally, we evaluated the potential for LLM apps to facilitate malicious activities, finding that 616 apps could be used for malware generation, phishing, etc. Our findings highlight the urgent need for robust regulatory frameworks and enhanced enforcement mechanisms.

Haoyu Wang, Ziyan Huang, Jin Ye et al.

Renal structure segmentation from computed tomography angiography~(CTA) is essential for many computer-assisted renal cancer treatment applications. Kidney PArsing~(KiPA 2022) Challenge aims to build a fine-grained multi-structure dataset and improve the segmentation of multiple renal structures. Recently, U-Net has dominated the medical image segmentation. In the KiPA challenge, we evaluated several U-Net variants and selected the best models for the final submission.

Jiarui Jin, Haoyu Wang, Hongyan Li et al.

Electrocardiogram (ECG) is essential for the clinical diagnosis of arrhythmias and other heart diseases, but deep learning methods based on ECG often face limitations due to the need for high-quality annotations. Although previous ECG self-supervised learning (eSSL) methods have made significant progress in representation learning from unannotated ECG data, they typically treat ECG signals as ordinary time-series data, segmenting the signals using fixed-size and fixed-step time windows, which often ignore the form and rhythm characteristics and latent semantic relationships in ECG signals. In this work, we introduce a novel perspective on ECG signals, treating heartbeats as words and rhythms as sentences. Based on this perspective, we first designed the QRS-Tokenizer, which generates semantically meaningful ECG sentences from the raw ECG signals. Building on these, we then propose HeartLang, a novel self-supervised learning framework for ECG language processing, learning general representations at form and rhythm levels. Additionally, we construct the largest heartbeat-based ECG vocabulary to date, which will further advance the development of ECG language processing. We evaluated HeartLang across six public ECG datasets, where it demonstrated robust competitiveness against other eSSL methods. Our data and code are publicly available at https://github.com/PKUDigitalHealth/HeartLang.

Zihan Zhou, Chong Li, Xinyi Chen et al.

Enlarging the context window of large language models (LLMs) has become a crucial research area, particularly for applications involving extremely long texts. In this work, we propose a novel training-free framework for processing long texts, utilizing a divide-and-conquer strategy to achieve comprehensive document understanding. The proposed LLM$\times$MapReduce framework splits the entire document into several chunks for LLMs to read and then aggregates the intermediate answers to produce the final output. The main challenge for divide-and-conquer long text processing frameworks lies in the risk of losing essential long-range information when splitting the document, which can lead the model to produce incomplete or incorrect answers based on the segmented texts. Disrupted long-range information can be classified into two categories: inter-chunk dependency and inter-chunk conflict. We design a structured information protocol to better cope with inter-chunk dependency and an in-context confidence calibration mechanism to resolve inter-chunk conflicts. Experimental results demonstrate that LLM$\times$MapReduce can outperform representative open-source and commercial long-context LLMs, and is applicable to several different models.

Ran Xu, Yuchen Zhuang, Yue Yu et al. · gatech

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by integrating external knowledge retrieved at inference time. While RAG demonstrates strong performance on benchmarks largely derived from general-domain corpora like Wikipedia, its effectiveness under realistic, diverse retrieval scenarios remains underexplored. We evaluated RAG systems using MassiveDS, a large-scale datastore with mixture of knowledge, and identified critical limitations: retrieval mainly benefits smaller models, rerankers add minimal value, and no single retrieval source consistently excels. Moreover, current LLMs struggle to route queries across heterogeneous knowledge sources. These findings highlight the need for adaptive retrieval strategies before deploying RAG in real-world settings. Our code and data can be found at https://github.com/ritaranx/RAG_in_the_Wild.

Yang Liu, Meng Xu, Shuo Wang et al.

Modern large language models (LLMs) should generally benefit individuals from various cultural backgrounds around the world. However, most recent advanced generative evaluation benchmarks tailed for LLMs mainly focus on English. To this end, we introduce OMGEval, the first Open-source Multilingual Generative test set that can assess the capability of LLMs in different languages. For each language, OMGEval provides 804 open-ended questions, covering a wide range of important capabilities of LLMs, such as general knowledge, logical reasoning, and so on. Each question is rigorously verified by human annotators. Notably, to sufficiently reflect the compatibility of LLMs in different cultural backgrounds, we perform localization for each non-English language. Specifically, the current version of OMGEval includes 5 languages (i.e., Zh, Ru, Fr, Es, Ar). Following AlpacaEval, we employ GPT-4 as the adjudicator to automatically score different model outputs, which is shown closely related to human evaluation. We evaluate several representative multilingual LLMs on the proposed OMGEval, which we believe will provide a valuable reference for the community to further understand and improve the multilingual capability of LLMs. OMGEval is available at https://github.com/blcuicall/OMGEval.

Haoyu Wang, Tong Teng, Tianyu Guo et al.

Handling long-context sequences efficiently remains a significant challenge in large language models (LLMs). Existing methods for token selection in sequence extrapolation either employ a permanent eviction strategy or select tokens by chunk, which may lead to the loss of critical information. We propose Efficient Selective Attention (ESA), a novel approach that extends context length by efficiently selecting the most critical tokens at the token level to compute attention. ESA reduces the computational complexity of token selection by compressing query and key vectors into lower-dimensional representations. We evaluate ESA on long sequence benchmarks with maximum lengths up to 256k using open-source LLMs with context lengths of 8k and 32k. ESA outperforms other selective attention methods, especially in tasks requiring the retrieval of multiple pieces of information, achieving comparable performance to full-attention extrapolation methods across various tasks, with superior results in certain tasks.

Yuxi Li, Zhibo Zhang, Kailong Wang et al.

Large Language Models (LLMs) have transformed numerous fields by enabling advanced natural language interactions but remain susceptible to critical vulnerabilities, particularly jailbreak attacks. Current jailbreak techniques, while effective, often depend on input modifications, making them detectable and limiting their stealth and scalability. This paper presents Targeted Model Editing (TME), a novel white-box approach that bypasses safety filters by minimally altering internal model structures while preserving the model's intended functionalities. TME identifies and removes safety-critical transformations (SCTs) embedded in model matrices, enabling malicious queries to bypass restrictions without input modifications. By analyzing distinct activation patterns between safe and unsafe queries, TME isolates and approximates SCTs through an optimization process. Implemented in the D-LLM framework, our method achieves an average Attack Success Rate (ASR) of 84.86% on four mainstream open-source LLMs, maintaining high performance. Unlike existing methods, D-LLM eliminates the need for specific triggers or harmful response collections, offering a stealthier and more effective jailbreak strategy. This work reveals a covert and robust threat vector in LLM security and emphasizes the need for stronger safeguards in model safety alignment.

Haoyu Wang, Xin Yuan, Qinqing Ren

Safety controllers is widely used to achieve safe reinforcement learning. Most methods that apply a safety controller are using handcrafted safety constraints to construct the safety controller. However, when the environment dynamics are sophisticated, handcrafted safety constraints become unavailable. Therefore, it worth to research on constructing safety controllers by learning algorithms. We propose a three-stage architecture for safe reinforcement learning, namely TU-Recovery Architecture. A safety critic and a recovery policy is learned before task training. They form a safety controller to ensure safety in task training. Then a phenomenon induced by disagreement between task policy and recovery policy, called adversarial phenomenon, which reduces learning efficiency and model performance, is described. Auxiliary reward is proposed to mitigate adversarial phenomenon, while help the task policy to learn to recover from high-risk states. A series of experiments are conducted in a robot navigation environment. Experiments demonstrate that TU-Recovery outperforms unconstrained counterpart in both reward gaining and constraint violations during task training, and auxiliary reward further improve TU-Recovery in reward-to-cost ratio by significantly reduce constraint violations.

Haoyu Wang, Yujia Fu, Zhu Zhang et al.

Long-form generation is crucial for a wide range of practical applications, typically categorized into short-to-long and long-to-long generation. While short-to-long generations have received considerable attention, generating long texts from extremely long resources remains relatively underexplored. The primary challenge in long-to-long generation lies in effectively integrating and analyzing relevant information from extensive inputs, which remains difficult for current large language models (LLMs). In this paper, we propose LLM$\times$MapReduce-V2, a novel test-time scaling strategy designed to enhance the ability of LLMs to process extremely long inputs. Drawing inspiration from convolutional neural networks, which iteratively integrate local features into higher-level global representations, LLM$\times$MapReduce-V2 utilizes stacked convolutional scaling layers to progressively expand the understanding of input materials. Both quantitative and qualitative experimental results demonstrate that our approach substantially enhances the ability of LLMs to process long inputs and generate coherent, informative long-form articles, outperforming several representative baselines. Both LLM$\times$MapReduce-V2 and SurveyEval are publicly available at https://github.com/thunlp/LLMxMapReduce .

Xian Zhan, Tianming Liu, Yepang Liu et al.

Third-party libraries (TPLs) have become a significant part of the Android ecosystem. Developers can employ various TPLs to facilitate their app development. Unfortunately, the popularity of TPLs also brings new security issues. For example, TPLs may carry malicious or vulnerable code, which can infect popular apps to pose threats to mobile users. Furthermore, TPL detection is essential for downstream tasks, such as vulnerabilities and malware detection. Thus, various tools have been developed to identify TPLs. However, no existing work has studied these TPL detection tools in detail, and different tools focus on different applications and techniques with performance differences. A comprehensive understanding of these tools will help us make better use of them. To this end, we conduct a comprehensive empirical study to fill the gap by evaluating and comparing all publicly available TPL detection tools based on six criteria: accuracy of TPL construction, effectiveness, efficiency, accuracy of version identification, resiliency to code obfuscation, and ease of use. Besides, we enhance these open-source tools by fixing their limitations, to improve their detection ability. Finally, we build an extensible framework that integrates all existing available TPL detection tools, providing an online service for the research community. We release the evaluation dataset and enhanced tools. According to our study, we also present the essential findings and discuss promising implications to the community. We believe our work provides a clear picture of existing TPL detection techniques and also gives a roadmap for future research.

Lijin Quan, Lei Wu, Haoyu Wang

As one of the representative Delegated Proof-of-Stake (DPoS) blockchain platforms, EOSIO's ecosystem grows rapidly in recent years. A number of vulnerabilities and corresponding attacks of EOSIO's smart contracts have been discovered and observed in the wild, which caused a large amount of financial damages. However, the majority of EOSIO's smart contracts are not open-sourced. As a result, the WebAssembly code may become the only available object to be analyzed in most cases. Unfortunately, current tools are web-application oriented and cannot be applied to EOSIO WebAssembly code directly, which makes it more difficult to detect vulnerabilities from those smart contracts. In this paper, we propose \toolname, a static analysis tool that can be used to detect vulnerabilities from EOSIO WASM code automatically. We focus on one particular type of vulnerabilities named \textit{fake-transfer}, and the exploitation of such vulnerabilities has led to millions of dollars in damages. To the best of our knowledge, it is the first attempt to build an automatic tool to detect vulnerabilities of EOSIO's smart contracts. The experimental results demonstrate that our tool is able to detect fake transfer vulnerabilities quickly and precisely. EVulHunter is available on GitHub\footnote{Tool and benchmarks: https://github.com/EVulHunter/EVulHunter} and YouTube\footnote{Demo video: https://youtu.be/5SJ0ZJKVZvw}.

Baijun Cheng, Shengming Zhao, Kailong Wang et al.

Vulnerability detectors based on deep learning (DL) models have proven their effectiveness in recent years. However, the shroud of opacity surrounding the decision-making process of these detectors makes it difficult for security analysts to comprehend. To address this, various explanation approaches have been proposed to explain the predictions by highlighting important features, which have been demonstrated effective in other domains such as computer vision and natural language processing. Unfortunately, an in-depth evaluation of vulnerability-critical features, such as fine-grained vulnerability-related code lines, learned and understood by these explanation approaches remains lacking. In this study, we first evaluate the performance of ten explanation approaches for vulnerability detectors based on graph and sequence representations, measured by two quantitative metrics including fidelity and vulnerability line coverage rate. Our results show that fidelity alone is not sufficient for evaluating these approaches, as fidelity incurs significant fluctuations across different datasets and detectors. We subsequently check the precision of the vulnerability-related code lines reported by the explanation approaches, and find poor accuracy in this task among all of them. This can be attributed to the inefficiency of explainers in selecting important features and the presence of irrelevant artifacts learned by DL-based detectors.

Liangxuan Wu, Chao Wang, Tianming Liu et al.

The growing adoption of large language models (LLMs) has led to a new paradigm in mobile computing--LLM-powered mobile AI agents--capable of decomposing and automating complex tasks directly on smartphones. However, the security implications of these agents remain largely unexplored. In this paper, we present the first comprehensive security analysis of mobile LLM agents, encompassing three representative categories: System-level AI Agents developed by original equipment manufacturers (e.g., YOYO Assistant), Third-party Universal Agents (e.g., Zhipu AI AutoGLM), and Emerging Agent Frameworks (e.g., Alibaba Mobile Agent). We begin by analyzing the general workflow of mobile agents and identifying security threats across three core capability dimensions: language-based reasoning, GUI-based interaction, and system-level execution. Our analysis reveals 11 distinct attack surfaces, all rooted in the unique capabilities and interaction patterns of mobile LLM agents, and spanning their entire operational lifecycle. To investigate these threats in practice, we introduce AgentScan, a semi-automated security analysis framework that systematically evaluates mobile LLM agents across all 11 attack scenarios. Applying AgentScan to nine widely deployed agents, we uncover a concerning trend: every agent is vulnerable to targeted attacks. In the most severe cases, agents exhibit vulnerabilities across eight distinct attack vectors. These attacks can cause behavioral deviations, privacy leakage, or even full execution hijacking. Based on these findings, we propose a set of defensive design principles and practical recommendations for building secure mobile LLM agents. Our disclosures have received positive feedback from two major device vendors. Overall, this work highlights the urgent need for standardized security practices in the fast-evolving landscape of LLM-driven mobile automation.

Hanting Chen, Yasheng Wang, Kai Han et al.

This work presents Pangu Embedded, an efficient Large Language Model (LLM) reasoner developed on Ascend Neural Processing Units (NPUs), featuring flexible fast and slow thinking capabilities. Pangu Embedded addresses the significant computational costs and inference latency challenges prevalent in existing reasoning-optimized LLMs. We propose a two-stage training framework for its construction. In Stage 1, the model is finetuned via an iterative distillation process, incorporating inter-iteration model merging to effectively aggregate complementary knowledge. This is followed by reinforcement learning on Ascend clusters, optimized by a latency-tolerant scheduler that combines stale synchronous parallelism with prioritized data queues. The RL process is guided by a Multi-source Adaptive Reward System (MARS), which generates dynamic, task-specific reward signals using deterministic metrics and lightweight LLM evaluators for mathematics, coding, and general problem-solving tasks. Stage 2 introduces a dual-system framework, endowing Pangu Embedded with a "fast" mode for routine queries and a deeper "slow" mode for complex inference. This framework offers both manual mode switching for user control and an automatic, complexity-aware mode selection mechanism that dynamically allocates computational resources to balance latency and reasoning depth. Experimental results on benchmarks including AIME 2024, GPQA, and LiveCodeBench demonstrate that Pangu Embedded with 7B parameters, outperforms similar-size models like Qwen3-8B and GLM4-9B. It delivers rapid responses and state-of-the-art reasoning quality within a single, unified model architecture, highlighting a promising direction for developing powerful yet practically deployable LLM reasoners.

Zihao Chen, Haomin Zhang, Xinhan Di et al.

Generating sound effects for product-level videos, where only a small amount of labeled data is available for diverse scenes, requires the production of high-quality sounds in few-shot settings. To tackle the challenge of limited labeled data in real-world scenes, we introduce YingSound, a foundation model designed for video-guided sound generation that supports high-quality audio generation in few-shot settings. Specifically, YingSound consists of two major modules. The first module uses a conditional flow matching transformer to achieve effective semantic alignment in sound generation across audio and visual modalities. This module aims to build a learnable audio-visual aggregator (AVA) that integrates high-resolution visual features with corresponding audio features at multiple stages. The second module is developed with a proposed multi-modal visual-audio chain-of-thought (CoT) approach to generate finer sound effects in few-shot settings. Finally, an industry-standard video-to-audio (V2A) dataset that encompasses various real-world scenarios is presented. We show that YingSound effectively generates high-quality synchronized sounds across diverse conditional inputs through automated evaluations and human studies. Project Page: \url{https://giantailab.github.io/yingsound/}

Haoyu Wang, Fengze Liu, Jiayao Zhang et al.

Event causality identification (ECI), a process that extracts causal relations between events from text, is crucial for distinguishing causation from correlation. Traditional approaches to ECI have primarily utilized linguistic patterns and multi-hop relational inference, risking false causality identification due to informal usage of causality and specious graphical inference. In this paper, we adopt the Rubin Causal Model to identify event causality: given two temporally ordered events, we see the first event as the treatment and the second one as the observed outcome. Determining their causality involves manipulating the treatment and estimating the resultant change in the likelihood of the outcome. Given that it is only possible to implement manipulation conceptually in the text domain, as a work-around, we try to find a twin for the protagonist from existing corpora. This twin should have identical life experiences with the protagonist before the treatment but undergoes an intervention of treatment. However, the practical difficulty of locating such a match limits its feasibility. Addressing this issue, we use the synthetic control method to generate such a twin' from relevant historical data, leveraging text embedding synthesis and inversion techniques. This approach allows us to identify causal relations more robustly than previous methods, including GPT-4, which is demonstrated on a causality benchmark, COPES-hard.

Yong Yang, Changjiang Li, Qingming Li et al.

Recently, large language models (LLMs) have garnered widespread attention for their exceptional capabilities. Prompts are central to the functionality and performance of LLMs, making them highly valuable assets. The increasing reliance on high-quality prompts has driven significant growth in prompt services. However, this growth also expands the potential for prompt leakage, increasing the risk that attackers could replicate original functionalities, create competing products, and severely infringe on developers' intellectual property. Despite these risks, prompt leakage in real-world prompt services remains underexplored. In this paper, we present PRSA, a practical attack framework designed for prompt stealing. PRSA infers the detailed intent of prompts through very limited input-output analysis and can successfully generate stolen prompts that replicate the original functionality. Extensive evaluations demonstrate PRSA's effectiveness across two main types of real-world prompt services. Specifically, compared to previous works, it improves the attack success rate from 17.8% to 46.1% in prompt marketplaces and from 39% to 52% in LLM application stores, respectively. Notably, in the attack on "Math", one of the most popular educational applications in OpenAI's GPT Store with over 1 million conversations, PRSA uncovered a hidden Easter egg that had not been revealed previously. Besides, our analysis reveals that higher mutual information between a prompt and its output correlates with an increased risk of leakage. This insight guides the design and evaluation of two potential defenses against the security threats posed by PRSA. We have reported these findings to the prompt service vendors, including PromptBase and OpenAI, and actively collaborate with them to implement defensive measures.

Haoyu Wang, Renyuan Ma, Gonzalo Mateos et al.

We introduce a principled generative framework for graph signals that enables explicit control of feature heterophily, a key property underlying the effectiveness of graph learning methods. Our model combines a Lipschitz graphon-based random graph generator with Gaussian node features filtered through a smooth spectral function of the rescaled Laplacian. We establish new theoretical guarantees: (i) a concentration result for the empirical heterophily score; and (ii) almost-sure convergence of the feature heterophily measure to a deterministic functional of the graphon degree profile, based on a graphon-limit law for polynomial averages of Laplacian eigenvalues. These results elucidate how the interplay between the graphon and the filter governs the limiting level of feature heterophily, providing a tunable mechanism for data modeling and generation. We validate the theory through experiments demonstrating precise control of homophily across graph families and spectral filters.

Haoyu Wang, Guangyan Zhang, Jiale Chen et al.

With the development of speech large language models (speech LLMs), users can now interact directly with assistants via speech. However, most existing models only convert response content into speech without fully capturing the rich emotional cues in user queries, where the same sentence may convey different meanings depending on the expression. Emotional understanding is thus essential for improving human-machine interaction. Most empathetic speech LLMs rely on massive datasets, demanding high computational cost. A key challenge is to build models that generate empathetic responses with limited data and without large-scale training. To this end, we propose Emotion Omni, a model that understands emotional content in user speech and generates empathetic responses. We further developed a data pipeline to construct a 200k emotional dialogue dataset supporting empathetic speech assistants. Experiments show that Emotion Omni achieves comparable instruction-following ability without large-scale pretraining, while surpassing existing models in speech quality (UTMOS:4.41) and empathy (Emotion GPT Score: 3.97). These results confirm its improvements in both speech fidelity and emotional expressiveness. Demos are available at https://w311411.github.io/omni_demo/.

Xuanzhe Liu, Diandian Gu, Zhenpeng Chen et al.

Deep learning (DL) has become a key component of modern software. In the "big model" era, the rich features of DL-based software substantially rely on powerful DL models, e.g., BERT, GPT-3, and the recently emerging GPT-4, which are trained on the powerful cloud with large datasets. Hence, training effective DL models has become a vital stage in the whole software lifecycle. When training deep learning models, especially those big models, developers need to parallelize and distribute the computation and memory resources amongst multiple devices in the training process, which is known as distributed deep learning training, or distributed training for short. However, the unique challenges that developers encounter in distributed training process have not been studied in the software engineering community. Given the increasingly heavy dependence of current DL-based software on distributed training, this paper aims to fill in the knowledge gap and presents the first comprehensive study on developers' issues in distributed training. To this end, we analyze 1,131 real-world developers' issues about using these frameworks reported on Stack Overflow and GitHub. We construct a fine-grained taxonomy consisting of 30 categories regarding the fault symptoms and summarize common fix patterns for different symptoms. Based on the results, we suggest actionable implications on research avenues that can potentially facilitate the distributed training to develop DL-based software, such as focusing on the frequent and common fix patterns when designing testing or debugging tools, developing efficient testing and debugging techniques for communication configuration along with the synthesis of network configuration analysis, designing new multi-device checkpoint-and-replay techniques to help reproduction, and designing serverless APIs for cloud platforms.

Ningyu He, Weihang Su, Zhou Yu et al.

The continuing expansion of the blockchain ecosystems has attracted much attention from the research community. However, although a large number of research studies have been proposed to understand the diverse characteristics of individual blockchain systems (e.g., Bitcoin or Ethereum), little is known at a comprehensive level on the evolution of blockchain ecosystems at scale, longitudinally, and across multiple blockchains. We argue that understanding the dynamics of blockchain ecosystems could provide unique insights that cannot be achieved through studying a single static snapshot or a single blockchain network alone. Based on billions of transaction records collected from three representative and popular blockchain systems (Bitcoin, Ethereum and EOSIO) over 10 years, we conduct the first study on the evolution of multiple blockchain ecosystems from different perspectives. Our exploration suggests that, although the overall blockchain ecosystem shows promising growth over the last decade, a number of worrying outliers exist that have disrupted its evolution.

Pengcheng Xia, Haoyu Wang, Zhou Yu et al.

DNS has always been criticized for its inherent design flaws, making the system vulnerable to kinds of attacks. Besides, DNS domain names are not fully controlled by the users, which can be easily taken down by the authorities and registrars. Since blockchain has its unique properties like immutability and decentralization, it seems to be promising to build a decentralized name service on blockchain. Ethereum Name Service (ENS), as a novel name service built atop Etheruem, has received great attention from the community. Yet, no existing work has systematically studied this emerging system, especially the security issues and misbehaviors in ENS. To fill the void, we present the first large-scale study of ENS by collecting and analyzing millions of event logs related to ENS. We characterize the ENS system from a number of perspectives. Our findings suggest that ENS is showing gradually popularity during its four years' evolution, mainly due to its distributed and open nature that ENS domain names can be set to any kinds of records, even censored and malicious contents. We have identified several security issues and misbehaviors including traditional DNS security issues and new issues introduced by ENS smart contracts. Attackers are abusing the system with thousands of squatting ENS names, a number of scam blockchain addresses and malicious websites, etc. Our exploration suggests that our community should invest more effort into the detection and mitigation of issues in Blockchain-based Name Services towards building an open and trustworthy name service.

Yuanchun Li, Jiayi Hua, Haoyu Wang et al.

Deep learning models are increasingly used in mobile applications as critical components. Unlike the program bytecode whose vulnerabilities and threats have been widely-discussed, whether and how the deep learning models deployed in the applications can be compromised are not well-understood since neural networks are usually viewed as a black box. In this paper, we introduce a highly practical backdoor attack achieved with a set of reverse-engineering techniques over compiled deep learning models. The core of the attack is a neural conditional branch constructed with a trigger detector and several operators and injected into the victim model as a malicious payload. The attack is effective as the conditional logic can be flexibly customized by the attacker, and scalable as it does not require any prior knowledge from the original model. We evaluated the attack effectiveness using 5 state-of-the-art deep learning models and real-world samples collected from 30 users. The results demonstrated that the injected backdoor can be triggered with a success rate of 93.5%, while only brought less than 2ms latency overhead and no more than 1.4% accuracy decrease. We further conducted an empirical study on real-world mobile deep learning apps collected from Google Play. We found 54 apps that were vulnerable to our attack, including popular and security-critical ones. The results call for the awareness of deep learning application developers and auditors to enhance the protection of deployed models.

Zhenpeng Chen, Huihan Yao, Yiling Lou et al.

Deep Learning (DL) is finding its way into a growing number of mobile software applications. These software applications, named as DL based mobile applications (abbreviated as mobile DL apps) integrate DL models trained using large-scale data with DL programs. A DL program encodes the structure of a desirable DL model and the process by which the model is trained using training data. Due to the increasing dependency of current mobile apps on DL, software engineering (SE) for mobile DL apps has become important. However, existing efforts in SE research community mainly focus on the development of DL models and extensively analyze faults in DL programs. In contrast, faults related to the deployment of DL models on mobile devices (named as deployment faults of mobile DL apps) have not been well studied. Since mobile DL apps have been used by billions of end users daily for various purposes including for safety-critical scenarios, characterizing their deployment faults is of enormous importance. To fill the knowledge gap, this paper presents the first comprehensive study on the deployment faults of mobile DL apps. We identify 304 real deployment faults from Stack Overflow and GitHub, two commonly used data sources for studying software faults. Based on the identified faults, we construct a fine-granularity taxonomy consisting of 23 categories regarding to fault symptoms and distill common fix strategies for different fault types. Furthermore, we suggest actionable implications and research avenues that could further facilitate the deployment of DL models on mobile devices.

Huiyi Wang, Liu Wang, Haoyu Wang

To help curb the spread of the COVID-19 pandemic, governments and public health authorities around the world have launched a number of contact-tracing apps. Although contact tracing apps have received extensive attentions from the research community, no existing work has characterized the users' adoption of contact tracing apps from the app market level. In this work, we perform the first market-level analysis of contact tracing apps. We perform a longitudinal empirical study (over 4 months) of eight government-backed COVID-19 contact tracing apps in iOS app store. We first collect all the daily meta information (e.g., app updates, app rating, app comments, etc.) of these contact tracing apps from their launch to 2020-07-31. Then we characterize them from release practice, app popularity, and mobile users' feedback. Our study reveals various issues related to contact tracing apps from the users' perspective, hoping to help improve the quality of contact tracing apps and thus achieving a high level of adoption in the population.

Shuyu Zheng, Haoyu Wang, Lei Wu et al.

WebAssemly is an emerging runtime for Web applications and has been supported in almost all browsers. Recently, WebAssembly is further regarded to be a the next-generation environment for blockchain applications, and has been adopted by Ethereum, namely eWASM, to replace the state-of-the-art EVM. However, whether and how well current eWASM outperforms EVM on blockchain clients is still unknown. This paper conducts the first measurement study, to measure the performance on WASM VM and EVM for executing smart contracts on blockchain. To our surprise, the current WASM VM does not perform in expected performance. The overhead introduced by WASM is really non-trivial. Our results highlight the challenges when deploying WASM in practice, and provide insightful implications for improvement space.

Bingyu Gao, Haoyu Wang, Pengcheng Xia et al.

The production of counterfeit money has a long history. It refers to the creation of imitation currency that is produced without the legal sanction of government. With the growth of the cryptocurrency ecosystem, there is expanding evidence that counterfeit cryptocurrency has also appeared. In this paper, we empirically explore the presence of counterfeit cryptocurrencies on Ethereum and measure their impact. By analyzing over 190K ERC-20 tokens (or cryptocurrencies) on Ethereum, we have identified 2, 117 counterfeit tokens that target 94 of the 100 most popular cryptocurrencies. We perform an end-to-end characterization of the counterfeit token ecosystem, including their popularity, creators and holders, fraudulent behaviors and advertising channels. Through this, we have identified two types of scams related to counterfeit tokens and devised techniques to identify such scams. We observe that over 7,104 victims were deceived in these scams, and the overall financial loss sums to a minimum of $ 17 million (74,271.7 ETH). Our findings demonstrate the urgency to identify counterfeit cryptocurrencies and mitigate this threat.

Wei Wang, Guozhu Meng, Haoyu Wang et al.

Authorship identification is the process of identifying and classifying authors through given codes. Authorship identification can be used in a wide range of software domains, e.g., code authorship disputes, plagiarism detection, exposure of attackers' identity. Besides the inherent challenges from legacy software development, framework programming and crowdsourcing mode in Android raise the difficulties of authorship identification significantly. More specifically, widespread third party libraries and inherited components (e.g., classes, methods, and variables) dilute the primary code within the entire Android app and blur the boundaries of code written by different authors. However, prior research has not well addressed these challenges. To this end, we design a two-phased approach to attribute the primary code of an Android app to the specific developer. In the first phase, we put forward three types of strategies to identify the relationships between Java packages in an app, which consist of context, semantic and structural relationships. A package aggregation algorithm is developed to cluster all packages that are of high probability written by the same authors. In the second phase, we develop three types of features to capture authors' coding habits and code stylometry. Based on that, we generate fingerprints for an author from its developed Android apps and employ several machine learning algorithms for authorship classification. We evaluate our approach in three datasets that contain 15,666 apps from 257 distinct developers and achieve a 92.5% accuracy rate on average. Additionally, we test it on 2,900 obfuscated apps and our approach can classify apps with an accuracy rate of 80.4%.

Pengcheng Xia, Haoyu Wang, Xiapu Luo et al.

As COVID-19 has been spreading across the world since early 2020, a growing number of malicious campaigns are capitalizing the topic of COVID-19. COVID-19 themed cryptocurrency scams are increasingly popular during the pandemic. However, these newly emerging scams are poorly understood by our community. In this paper, we present the first measurement study of COVID-19 themed cryptocurrency scams. We first create a comprehensive taxonomy of COVID-19 scams by manually analyzing the existing scams reported by users from online resources. Then, we propose a hybrid approach to perform the investigation by: 1) collecting reported scams in the wild; and 2) detecting undisclosed ones based on information collected from suspicious entities (e.g., domains, tweets, etc). We have collected 195 confirmed COVID-19 cryptocurrency scams in total, including 91 token scams, 19 giveaway scams, 9 blackmail scams, 14 crypto malware scams, 9 Ponzi scheme scams, and 53 donation scams. We then identified over 200 blockchain addresses associated with these scams, which lead to at least 330K US dollars in losses from 6,329 victims. For each type of scams, we further investigated the tricks and social engineering techniques they used. To facilitate future research, we have released all the well-labelled scams to the research community.

Ru Ji, Ningyu He, Lei Wu et al.

Cryptocurrency has seen an explosive growth in recent years, thanks to the evolvement of blockchain technology and its economic ecosystem. Besides Bitcoin, thousands of cryptocurrencies have been distributed on blockchains, while hundreds of cryptocurrency exchanges are emerging to facilitate the trading of digital assets. At the same time, it also attracts the attentions of attackers. Fake deposit, as one of the most representative attacks (vulnerabilities) related to exchanges and tokens, has been frequently observed in the blockchain ecosystem, causing large financial losses. However, besides a few security reports, our community lacks of the understanding of this vulnerability, for example its scale and the impacts. In this paper, we take the first step to demystify the fake deposit vulnerability. Based on the essential patterns we have summarized, we implement DEPOSafe, an automated tool to detect and verify (exploit) the fake deposit vulnerability in ERC-20 smart contracts. DEPOSafe incorporates several key techniques including symbolic execution based static analysis and behavior modeling based dynamic verification. By applying DEPOSafe to 176,000 ERC-20 smart contracts, we have identified over 7,000 vulnerable contracts that may suffer from two types of attacks. Our findings demonstrate the urgency to identify and prevent the fake deposit vulnerability.

Zhenpeng Chen, Yanbin Cao, Yuanqiang Liu et al.

Deep learning (DL) becomes increasingly pervasive, being used in a wide range of software applications. These software applications, named as DL based software (in short as DL software), integrate DL models trained using a large data corpus with DL programs written based on DL frameworks such as TensorFlow and Keras. A DL program encodes the network structure of a desirable DL model and the process by which the model is trained using the training data. To help developers of DL software meet the new challenges posed by DL, enormous research efforts in software engineering have been devoted. Existing studies focus on the development of DL software and extensively analyze faults in DL programs. However, the deployment of DL software has not been comprehensively studied. To fill this knowledge gap, this paper presents a comprehensive study on understanding challenges in deploying DL software. We mine and analyze 3,023 relevant posts from Stack Overflow, a popular Q&A website for developers, and show the increasing popularity and high difficulty of DL software deployment among developers. We build a taxonomy of specific challenges encountered by developers in the process of DL software deployment through manual inspection of 769 sampled posts and report a series of actionable implications for researchers, developers, and DL framework vendors.

Pengcheng Xia, Bowen Zhang, Ru Ji et al.

As the indispensable trading platforms of the ecosystem, hundreds of cryptocurrency exchanges are emerging to facilitate the trading of digital assets. While, it also attracts the attentions of attackers. A number of scam attacks were reported targeting cryptocurrency exchanges, leading to a huge mount of financial loss. However, no previous work in our research community has systematically studied this problem. In this paper, we make the first effort to identify and characterize the cryptocurrency exchange scams. We first identify over 1,500 scam domains and over 300 fake apps, by collecting existing reports and using typosquatting generation techniques. Then we investigate the relationship between them, and identify 94 scam domain families and 30 fake app families. We further characterize the impacts of such scams, and reveal that these scams have incurred financial loss of 520k US dollars at least. We further observe that the fake apps have been sneaked to major app markets (including Google Play) to infect unsuspicious users. Our findings demonstrate the urgency to identify and prevent cryptocurrency exchange scams. To facilitate future research, we have publicly released all the identified scam domains and fake apps to the community.

Yuheng Huang, Haoyu Wang, Lei Wu et al.

EOSIO has become one of the most popular blockchain platforms since its mainnet launch in June 2018. In contrast to the traditional PoW-based systems (e.g., Bitcoin and Ethereum), which are limited by low throughput, EOSIO is the first high throughput Delegated Proof of Stake system that has been widely adopted by many applications. Although EOSIO has millions of accounts and billions of transactions, little is known about its ecosystem, especially related to security and fraud. In this paper, we perform a large-scale measurement study of the EOSIO blockchain and its associated DApps. We gather a large-scale dataset of EOSIO and characterize activities including money transfers, account creation and contract invocation. Using our insights, we then develop techniques to automatically detect bots and fraudulent activity. We discover thousands of bot accounts (over 30\% of the accounts in the platform) and a number of real-world attacks (301 attack accounts). By the time of our study, 80 attack accounts we identified have been confirmed by DApp teams, causing 828,824 EOS tokens losses (roughly 2.6 million US\$) in total.

Zhuotao Liu, Yangxi Xiang, Jian Shi et al.

Blockchain interoperability, which allows state transitions across different blockchain networks, is critical functionality to facilitate major blockchain adoption. Existing interoperability protocols mostly focus on atomic token exchange between blockchains. However, as blockchains have been upgraded from passive distributed ledgers into programmable state machines (thanks to smart contracts), the scope of blockchain interoperability goes beyond just token exchange. In this paper, we present HyperService, the first platform that delivers interoperability and programmability across heterogeneous blockchains. HyperService is powered by two innovative designs: (i) a developer-facing programming framework that allows developers to build cross-chain applications in a unified programming model; and (ii) a secure blockchain-facing cryptography protocol that provably realizes those applications on blockchains. We implement a prototype of HyperService in about 35,000 lines of code to demonstrate its practicality. Our experiment results show that HyperService imposes reasonable latency, in order of seconds, on the end-to-end execution of cross-chain applications

Zeliang Kan, Haoyu Wang, Lei Wu et al.

With the popularity of Android apps, different techniques have been proposed to enhance app protection. As an effective approach to prevent reverse engineering, obfuscation can be used to serve both benign and malicious purposes. In recent years, more and more sensitive logic or data have been implemented as obfuscated native code because of the limitations of Java bytecode. As a result, native code obfuscation becomes a great obstacle for security analysis to understand the complicated logic. In this paper, we propose DiANa, an automated system to facilitate the deobfuscation of native binary code in Android apps. Specifically, given a binary obfuscated by Obfuscator-LLVM (the most popular native code obfuscator), DiANa is capable of recovering the original Control Flow Graph. To the best of our knowledge, DiANa is the first system that aims to tackle the problem of Android native binary deobfuscation. We have applied DiANa in different scenarios, and the experimental results demonstrate the effectiveness of DiANa based on generic similarity comparison metrics.

Haoyu Wang, Defu Lian, Yong Ge

The efficiency of top-K item recommendation based on implicit feedback are vital to recommender systems in real world, but it is very challenging due to the lack of negative samples and the large number of candidate items. To address the challenges, we firstly introduce an improved Graph Convolutional Network~(GCN) model with high-order feature interaction considered. Then we distill the ranking information derived from GCN into binarized collaborative filtering, which makes use of binary representation to improve the efficiency of online recommendation. However, binary codes are not only hard to be optimized but also likely to incur the loss of information during the training processing. Therefore, we propose a novel framework to convert the binary constrained optimization problem into an equivalent continuous optimization problem with a stochastic penalty. The binarized collaborative filtering model is then easily optimized by many popular solvers like SGD and Adam. The proposed algorithm is finally evaluated on three real-world datasets and shown the superiority to the competing baselines.

Haoyu Wang, Zhe Liu, Jingyue Liang et al.

China is one of the largest Android markets in the world. As Chinese users cannot access Google Play to buy and install Android apps, a number of independent app stores have emerged and compete in the Chinese app market. Some of the Chinese app stores are pre-installed vendor-specific app markets (e.g., Huawei, Xiaomi and OPPO), whereas others are maintained by large tech companies (e.g., Baidu, Qihoo 360 and Tencent). The nature of these app stores and the content available through them vary greatly, including their trustworthiness and security guarantees. As of today, the research community has not studied the Chinese Android ecosystem in depth. To fill this gap, we present the first large-scale comparative study that covers more than 6 million Android apps downloaded from 16 Chinese app markets and Google Play. We focus our study on catalog similarity across app stores, their features, publishing dynamics, and the prevalence of various forms of misbehavior (including the presence of fake, cloned and malicious apps). Our findings also suggest heterogeneous developer behavior across app stores, in terms of code maintenance, use of third-party services, and so forth. Overall, Chinese app markets perform substantially worse when taking active measures to protect mobile users and legit developers from deceptive and abusive actors, showing a significantly higher prevalence of malware, fake, and cloned apps than Google Play.