Social event detection (SED) aims to detect events (news) on social media platforms, which is essential in various applications, such as public opinion surveillance, disaster control, and market monitoring. However, social media platforms are characterized by the generation of short, dynamic, and multi-source social messages. This makes annotating social messages time-consuming and difficult (label scarcity), and poses a challenge to the widespread application of SED. Despite efforts, existing unsupervised SED models rely on graph structures to address the lack of textual content, resulting in unstable performance in dynamic social messages. To solve the above challenges, this work proposes an unsupervised SED framework with an LLM enhancement and Heterogeneous Graph induction (LHG). Specifically, to address the label scarcity problem, LHG generates pseudo-labels for initial social messages through an LLM. Considering the unreliable nature of LLM-generated labels, LHG designed a Meta-Path Guided Label Similarity Selector (MPLSS). In detail, MPLSS in LHG calculates the similarity of these pseudo-labels and constructs the initial social messages corresponding to the pseudo-labels into triplets based on the meta-paths in the heterogeneous information graph (HIG), thereby mitigating problems caused by LLMs, such as hallucination. Afterward, to improve stability, LHG not only utilizes the structural information in HIG via MPLSS, but also reduces the embedding distortion of the hierarchical structure in HIG and sentences via a hyperbolic representation, thereby ensuring that there is sufficient available information in dynamic social messages. Extensive experiments show that LHG achieves state-of-the-art (SOTA) results on two widely used real-world datasets.
论文检索
输入标题、作者或关键词，从 100,903 篇学术成果中精准定位
Deductive and abductive reasoning are two critical paradigms for analyzing knowledge graphs, enabling applications from financial query answering to scientific discovery. Deductive reasoning on knowledge graphs usually involves retrieving entities that satisfy a complex logical query, while abductive reasoning generates plausible logical hypotheses from observations. Despite their clear synergistic potential, where deduction can validate hypotheses and abduction can uncover deeper logical patterns, existing methods address them in isolation. To bridge this gap, we propose DARK, a unified framework for Deductive and Abductive Reasoning in Knowledge graphs. As a masked diffusion model capable of capturing the bidirectional relationship between queries and conclusions, DARK has two key innovations. First, to better leverage deduction for hypothesis refinement during abductive reasoning, we introduce a self-reflective denoising process that iteratively generates and validates candidate hypotheses against the observed conclusion. Second, to discover richer logical associations, we propose a logic-exploration reinforcement learning approach that simultaneously masks queries and conclusions, enabling the model to explore novel reasoning compositions. Extensive experiments on multiple benchmark knowledge graphs show that DARK achieves competitive performance on both deductive and abductive reasoning tasks, demonstrating the significant benefits of our unified approach.
Entity alignment (EA) is to identify equivalent entities across different knowledge graphs (KGs), which can help fuse these KGs into a more comprehensive one. Previous EA methods mainly focus on aligning a pair of KGs, and to the best of our knowledge, no existing EA method considers aligning multiple (more than two) KGs. To fill this research gap, in this work, we study a novel problem of aligning multiple KGs and propose an effective framework named MultiEA to solve the problem. First, we embed the entities of all the candidate KGs into a common feature space by a shared KG encoder. Then, we explore three alignment strategies to minimize the distances among pre-aligned entities. In particular, we propose an innovative inference enhancement technique to improve the alignment performance by incorporating high-order similarities. Finally, to verify the effectiveness of MultiEA, we construct two new real-world benchmark datasets and conduct extensive experiments on them. The results show that our MultiEA can effectively and efficiently align multiple KGs in a single pass. We release the source code at: https://github.com/wzCSDN/MultiEA.
Long-term memory is critical for dialogue systems that support continuous, sustainable, and personalized interactions. However, existing methods rely on continuous summarization or OpenIE-based graph construction paired with fixed Top- k retrieval, leading to limited adaptability across query categories and high computational overhead. In this paper, we propose HingeMem, a boundary-guided long-term memory that operationalizes event segmentation theory to build an interpretable indexing interface via boundary-triggered hyperedges over four elements: person, time, location, and topic. When any such element changes, HingeMem draws a boundary and writes the current segment, thereby reducing redundant operations and preserving salient context. To enable robust and efficient retrieval under diverse information needs, HingeMem introduces query-adaptive retrieval mechanisms that jointly decide (a) what to retrieve: determine the query-conditioned routing over the element-indexed memory; (b) how much to retrieve: control the retrieval depth based on the estimated query type. Extensive experiments across LLM scales (from 0.6B to production-tier models; e.g., Qwen3-0.6B to Qwen-Flash) on LOCOMO show that HingeMem achieves approximately 20% relative improvement over strong baselines without query categories specification, while reducing computational cost (68%\downarrow question answering token cost compared to HippoRAG2). Beyond advancing memory modeling, HingeMem's adaptive retrieval makes it a strong fit for web applications requiring efficient and trustworthy memory over extended interactions.
Video captioning aims to describe the content of a given video with condensed natural language sentences. Such a captioning task is full of challenges since the high requirements for visual-textual relevance and multimodal fusion understanding. Previous works primarily focus on visual content modeling, often overlooking the rich semantic correlations between visual and textual modalities, which results in incomplete understanding of the multimodal context and suboptimal caption accuracy. In this paper, we propose a multimodal graph conditioned diffusion model for video captioning, named MGCDVc. The idea behind our model is to incorporate graph-based relational reasoning with diffusion-based generative modeling to jointly model cross-modal relationships and capture latent semantic structure. Specifically, we learn a set of latent concept anchors to bridge the visual and textual modality nodes, enabling the construction of a weighted multimodal graph. Then we introduce the graph conditioned diffusion strategy which generates the textual semantic nodes and associated edges under the graph structure awareness condition. Furthermore, a soft pruning mechanism is designed to filter out low-quality nodes, thus further refining the generated multimodal graph to provide more accurate semantic structural guidance for caption generation. Experimental results on several popular datasets demonstrate that our model achieves better performance in video captioning task.
Open-source ecosystems such as NPM and PyPI are increasingly targeted by supply chain attacks, yet existing detection methods either depend on fragile handcrafted rules or data-driven features that fail to capture evolving attack semantics. We present IntelGuard, a retrieval-augmented generation (RAG) based framework that integrates expert analytical reasoning into automated malicious package detection. IntelGuard constructs a structured knowledge base from over 8,000 threat intelligence reports, linking malicious code snippets with behavioral descriptions and expert reasoning. When analyzing new packages, it retrieves semantically similar malicious examples and applies LLM-guided reasoning to assess whether code behaviors align with intended functionality. Experiments on 4,027 real-world packages show that IntelGuard achieves 99% accuracy and a 0.50% false positive rate, while maintaining 96.5% accuracy on obfuscated code. Deployed on PyPI.org, it discovered 54 previously unreported malicious packages, demonstrating interpretable and robust detection guided by expert knowledge.
Anonymous proofs of account ownership (anonymous PAOs) enable a prover to convince a verifier that the prover owns a valid account at a server without revealing their identity. Importantly, no server-side changes are required - the server does not even learn that such a proof is taking place. This functionality is particularly valuable in sensitive applications such as whistleblowing, or in settings where infrastructural changes at the server are impractical. Anonymous PAOs were first introduced by Wang et al. (IEEE S&P 2019), who realized them in the email setting via secure channel injection (SCI), a technique that requires carefully engineered multi-party computation (MPC) protocols. In this work, we propose YouChoose, a new approach to anonymous PAO that avoids MPC entirely, relying instead on the verifier to selectively forward TLS records. Compared to SCI, YouChoose is simpler, faster, and more adaptable across services. We also provide the first formal security definition for anonymous PAOs, establishing a rigorous framework for analysis and future constructions. Finally, we present a prototype implementation of YouChoose, evaluate it in the context of email and other social media accounts, showing its better performance than SCI with minimal latency overhead in practice.
Phishing is a threat in which attackers masquerade as legitimate entities to steal sensitive data. While understanding the phishing ecosystem is critical for developing effective countermeasures, prior research has largely studied phishing through post-attack data, with limited examination of the attacker's perspective and how phishing campaigns are built. Critically, the Deep and Dark Web (D2Web) serves as the primary marketplace and knowledge-sharing platform where attackers acquire phishing tools (e.g., phishing kits), exchange techniques, and trade compromised credentials. Analyzing D2Web forums therefore provides unique visibility into the supply chain of phishing attacks pre-deployment, enabling proactive understanding of emerging threats and attack methodologies. This study addresses this gap through a comprehensive analysis of 394,034 posts (343,334 unique) collected from 13 D2Web forums spanning 2013 to 2025, from which 70,055 phishing-related posts are identified. We employ a LLM-based approach to efficiently extract key information, including phishing attack components (e.g., credentials, phishing pages, SMTP servers), targeted services (e.g., PayPal, Netflix), and component authors. This extracted data is mapped to a seven-stage attack scenario framework derived from empirical case studies. Our analysis reveals longitudinal trends in component availability, target service distribution, post type evolution, and the most active contributors annually, while characterizing pricing dynamics across different attack components. The results provide the first attacker-centric, macro-level longitudinal analysis of the phishing ecosystem, offering insights into how phishing infrastructure and markets have evolved over more than a decade. These findings contribute to a deeper understanding of the phishing supply chain and inform more effective detection and prevention strategies.
While machine learning has significantly advanced ad and tracker detection, existing systems face critical challenges in practice. They are vulnerable to adversarial attacks (57-92% evasion rates), fail to generalize to unseen domains due to data contamination, and suffer performance degradation over time, requiring costly retraining. To address these challenges, we present AdVersa, a client-side framework for robust and practical ad and tracker blocking. AdVersa leverages novel, hard-to-perturb latent features from code and URL embeddings to deliver state-of-the-art performance. On a 2.74M-request dataset, our results show that AdVersa achieves a 98.23% F1 score, twice the robustness against adversarial attacks, and strong generalization to unseen domains (91.47% F1 score). For sustainable protection, we demonstrate that a low-cost pseudo-labeling strategy can maintain near-optimal accuracy, reducing maintenance overhead by over 99.8% compared to filter-list curation. Finally, we implement AdVersa as a lightweight, standalone client-side application that ensures user privacy by operating without external dependencies.
Sanctioning blockchain addresses has become a common regulatory response to malicious activities. However, enforcement on permissionless blockchains remains challenging due to complex transaction flows and sophisticated fund-obfuscation techniques. Using cryptocurrency mixing tool Tornado Cash as a case study, we quantitatively assess the effectiveness of U.S. Office of Foreign Assets Control (OFAC) sanctions over a 957-day period, covering 6.79 million Ethereum blocks and 1.07 billion transactions. Our analysis reveals that while OFAC sanctions reduced overall Tornado Cash deposit volume by 71.03% to approximately 2 billion USD, attackers still relied on Tornado Cash in 78.33% of Ethereum-related security incidents, underscoring persistent evasion strategies. In this paper, we identify three significant, structural limitations in current sanction enforcement practices: (i) fragmented censorship in blockchain consensus and application layer; (ii) the complexity of obfuscation virtual asset services exploited by users; and (iii) the susceptibility of naive binary sanction classifications to dusting attacks. Our analysis and findings contribute to ongoing discussions around regulatory effectiveness in Decentralized Finance by providing empirical evidence, clarifying enforcement challenges, and informing future compliance strategies in response to sanctions and blockchain-based security risks.
Label flipping attacks stand as a potent and practical threat to the integrity of machine learning models. While extensive research has focused on designing sophisticated attack and defense mechanisms, the underlying factors that govern a model's susceptibility remain underexplored. This paper reveals a critical phenomenon: the impact of label flipping attacks is highly differential across classes, strongly correlated with the intrinsic confusability between the source and target classes. We provide a rigorous theoretical analysis, demonstrating that a lower standardized separation between classes fundamentally leads to greater vulnerability. Grounded in this insight, we propose Confusability-Aware Contrastive Learning (CACL), a targeted defense that maximizes the feature-space separation for the most vulnerable class pairs. Extensive experiments validate the strong link between class separability and vulnerability, and show that CACL significantly mitigates the attack's impact while providing superior protection for the most susceptible classes. Our code is available at https://github.com/Pinlong-Zhao/Unequal-Vulnerability.
To enable personalized and context-aware interactions, conversational AI systems have introduced a new mechanism: Memory. Memory creates what we refer to as the Algorithmic Self-portrait ---a new form of personalization derived from users' self-disclosed information divulged within private conversations. While memory enables more coherent exchanges, the underlying processes of memory creation remain opaque, raising critical questions about data sensitivity, user agency, and the fidelity of the resulting portrait. To bridge this research gap, we analyze 2,050 memory entries from 80 real-world ChatGPT users. Our analyses reveal three key findings: (1)~a striking 96% of memories in our dataset are created unilaterally by the conversational system, potentially shifting agency away from the user; (2)~Memories, in our dataset, contain a rich mix of GDPR-defined personal data (in 28% memories) along with psychological insights about participants (in 52% memories); and (3)~A significant majority of the memories (84%) are directly grounded in user context, indicating faithful representation of the conversations. Finally, we introduce a framework--- Attribution Shield ---that anticipates these inferences, alerts about potentially sensitive memory inferences, and suggests query reformulations to protect personal information without sacrificing utility.
Graph Neural Networks (GNNs) have demonstrated remarkable performance across web-centric applications, yet they are vulnerable to sophisticated adversarial attacks, particularly node injection attacks. The success of such attacks heavily relies on their stealthiness, the ability to blend in with the original graph and evade detection. However, existing methods often achieve stealthiness by relying on indirect proxy metrics, lacking consideration for the fundamental characteristics of the injected content, or focusing only on imitating local structures, which leads to the problem of local myopia. To overcome these limitations, we propose a dual-constraint stealthy node injection framework, called Joint Alignment of Nodal and Universal Structures (JANUS). At the local level, we introduce a local feature manifold alignment strategy to achieve geometric consistency in the feature space. At the global level, we incorporate structured latent variables and maximize the mutual information with the generated structures, ensuring the injected structures are consistent with the semantic patterns of the original graph. We model the injection attack as a sequential decision process, which is optimized by a reinforcement learning agent. Experiments on multiple standard datasets demonstrate that the JANUS framework significantly outperforms existing methods in terms of both attack effectiveness and stealthiness. Our code and scripts are available at https://github.com/jiahaozhang121/JANUS-WWW2026.
Copy trading has become the dominant entry strategy in meme coin markets. However, due to the market's extremely illiquid and volatile nature, the strategy exposes an exploitable attack surface: adversaries deploy manipulative bots to front-run trades, conceal positions, and fabricate sentiment, systematically extracting value from naïve copiers at scale. Despite its prevalence, bot-driven manipulation remains largely unexplored, and no robust defensive framework exists. We propose a manipulation-resistant copy-trading system based on a multi-agent architecture powered by a multi-modal large language model (LLM) and chain-of-thought (CoT) reasoning. Our approach outperforms zero-shot and most statistic-driven baselines in prediction accuracy as well as all baselines in economic performance, achieving an average copier return of 3% per meme coin investment under realistic market frictions. Overall, our results demonstrate the effectiveness of agent-based defenses and predictability of trader profitability in adversarial meme coin markets, providing a practical foundation for robust copy trading.