arXiv subjects

Haizhou Wang

Publications and source records attributed to Haizhou Wang.

At least 19 recordsLinked to original sources

arXiv2026

Zero-shot Tweet-Level Stance Detection Enhanced by External Knowledge and Reflective Chain-of-Thought Reasoning

Zero-shot tweet-level stance detection confronts two primary challenges: (1) mitigating the context sparsity inherent in short texts, and (2) establishing the relevance between implicit targets and textual content. While existing methods primarily focus on incorporating external knowledge, they neglect the intrinsic semantic cues embedded within key intra-textual entities. Furthermore, current models exhibit limited capability in determining the relevance of unseen targets to the given text, thereby struggling to differentiate between "neutral" and "irrelevant" stance labels. To address these issues, we first construct a four-class, multi-topic Japanese tweet dataset. To our knowledge, this is the first Japanese tweet-level dataset for stance detection. We then propose KIRP, a zero-shot stance detection framework. It integrates external knowledge with entity reorganization for data augmentation and employs prompt chaining for reasoning. Specifically, the framework incorporates knowledge graphs to supplement and reorganize key textual entities, while reflective Chain-of-Thought (CoT) reasoning extracts and validates implicit targets. To better distinguish "neutral" from "irrelevant" labels, we adopt stance-aware contrastive learning to capture discriminative features and design a three-layer iterative prototype network for fine-grained classification. Experimental results on SemEval-2016, WT-WT, and KIRP-D show that KIRP achieves state-of-the-art performance. KIRP obtains F1 scores of 84.05% (three-class) on SemEval-2016, and 84.99% and 79.18% (four-class) on WT-WT and KIRP-D, respectively.

cs.CL↗

arXiv2026

Detecting Avalanche Effect in Adversarial Settings: Spotting the Encryption Loops in Ransomware

Spotting encryption loops in binary-only ransomware is a critical reverse engineering task. Since the existence of avalanche effect, an intrinsic characteristic of any secure encryption algorithms, is unavoidable during a victim data encryption attack, it is a very promising direction to spot encryption loops through avalanche effect detection. Unfortunately, no existing work in this direction ensures that the being-checked effect is the avalanche effect itself. Although CipherXRay is inspired by avalanche effect, it only checks whether a "ripple effect" (i.e., a necessary but non-sufficient condition) of avalanche effect exists, allowing a straightforward counterattack to succeed. In this work, we present a new approach that checks the avalanche effect itself. Because the detection is conducted in adversarial settings (e.g., the ransomware author may obfuscate the code), a viable approach must tolerate inaccurate input \& output identification and must be resilient to adversarial evasion. These challenges are addressed by a novel record-and-replay detection mechanism that takes advantage of the statistical guarantees provided by the Shapiro-Wilk normality test. The experimental results show that our approach achieves 0.0\% false negative rate and 1.1\% false positive rate. When our tool is employed to reverse engineer real-world ransomware samples, it succeeds in analyzing all the ransomware samples selected from ten representative families.

cs.CR↗

arXiv2026

EvoJail: Evolutionary Diverse Jailbreak Prompt Generation for Large Language Models

As LLMs continue to shape real-world applications, automated jailbreak generation becomes essential to reveal safety weaknesses and guide model improvement. Existing automatic jailbreak generation methods have not yet fully considered two important aspects: adaptability to evolving safety-finetuned models, which affects their effectiveness on newer model versions, and diversity in generated prompts, which can cause narrow or repetitive attack patterns. To address these issues, we propose EvoJail, an instruction-fusion-driven evolutionary jailbreak generation framework that formalizes jailbreak prompt generation as a multi-objective black-box optimization problem and leverages the principles of evolutionary algorithms to search for jailbreak prompts that can adapt across different model versions and exhibit diverse attack patterns. Specifically, EvoJail integrates jailbreak prompt generation into an iterative evolutionary loop, where at each iteration candidate prompts are evaluated directly against the target model and then selected and varied based on the target model's responses, enabling the generation process to continuously adapt to model updates. To enhance diversity, EvoJail introduces field-aware instruction fusion to construct diverse starting points and incorporates diversity-aware objectives into the evolutionary fitness function, guiding the search toward prompts with richer semantic variation, while further designing multi-level LLM-based mutation operators that modify prompt structures at different granularities to promote structural diversity throughout the evolutionary process. Results demonstrate that EvoJail has stronger adaptability and can achieve over $93\%$ attack success rate and more than $5.6\%$ improvement in diversity metrics over state-of-the-art methods.

cs.NE↗

arXiv2026

A GAN and LLM-Driven Data Augmentation Framework for Dynamic Linguistic Pattern Modeling in Chinese Sarcasm Detection

Sarcasm is a rhetorical device that expresses criticism or emphasizes characteristics of certain individuals or situations through exaggeration, irony, or comparison. Existing methods for Chinese sarcasm detection are constrained by limited datasets and high construction costs, and they mainly focus on textual features, overlooking user-specific linguistic patterns that shape how opinions and emotions are expressed. This paper proposes a Generative Adversarial Network (GAN) and Large Language Model (LLM)-driven data augmentation framework to dynamically model users' linguistic patterns for enhanced Chinese sarcasm detection. First, we collect raw data from various topics on Sina Weibo. Then, we train a GAN on these data and apply a GPT-3.5 based data augmentation technique to synthesize an extended sarcastic comment dataset, named SinaSarc. This dataset contains target comments, contextual information, and user historical behavior. Finally, we extend the BERT architecture to incorporate multi-dimensional information, particularly user historical behavior, enabling the model to capture dynamic linguistic patterns and uncover implicit sarcastic cues in comments. Experimental results demonstrate the effectiveness of our proposed method. Specifically, our model achieves the highest F1-scores on both the non-sarcastic and sarcastic categories, with values of 0.9138 and 0.9151 respectively, which outperforms all existing state-of-the-art (SOTA) approaches. This study presents a novel framework for dynamically modeling users' long-term linguistic patterns in Chinese sarcasm detection, contributing to both dataset construction and methodological advancement in this field.

cs.CL↗

arXiv2026

TRACE-Bot: Detecting Emerging LLM-Driven Social Bots via Implicit Semantic Representations and AIGC-Enhanced Behavioral Patterns

Large Language Model-driven (LLM-driven) social bots pose a growing threat to online discourse by generating human-like content that evades conventional detection. Existing methods suffer from limited detection accuracy due to overreliance on single-modality signals, insufficient sensitivity to the specific generative patterns of Artificial Intelligence-Generated Content (AIGC), and a failure to adequately model the interplay between linguistic patterns and behavioral dynamics. To address these limitations, we propose TRACE-Bot, a unified dual-channel framework that jointly models implicit semantic representations and AIGC-enhanced behavioral patterns. TRACE-Bot constructs fine-grained representations from heterogeneous sources, including personal information data, interaction behavior data and tweet data. A dual-channel architecture captures linguistic representations via a pretrained language model and behavioral irregularities via multidimensional activity features augmented with signals from state-of-the-art (SOTA) AIGC detectors. The fused representations are then classified through a lightweight prediction head. Experiments on two public LLM-driven social bot datasets demonstrate SOTA performance, achieving accuracies of 98.46% and 97.50%, respectively. The results further indicate strong robustness against advanced bot strategies, highlighting the effectiveness of jointly leveraging implicit semantic representations and AIGC-enhanced behavioral patterns for emerging LLM-driven social bot detection.

cs.AI↗

arXiv2026

KryptoPilot: An Open-World Knowledge-Augmented LLM Agent for Automated Cryptographic Exploitation

Capture-the-Flag (CTF) competitions play a central role in modern cybersecurity as a platform for training practitioners and evaluating offensive and defensive techniques derived from real-world vulnerabilities. Despite recent advances in large language models (LLMs), existing LLM-based agents remain ineffective on high-difficulty cryptographic CTF challenges, which require precise cryptanalytic knowledge, stable long-horizon reasoning, and disciplined interaction with specialized toolchains. Through a systematic exploratory study, we show that insufficient knowledge granularity, rather than model reasoning capacity, is a primary factor limiting successful cryptographic exploitation: coarse or abstracted external knowledge often fails to support correct attack modeling and implementation. Motivated by this observation, we propose KryptoPilot, an open-world knowledge-augmented LLM agent for automated cryptographic exploitation. KryptoPilot integrates dynamic open-world knowledge acquisition via a Deep Research pipeline, a persistent workspace for structured knowledge reuse, and a governance subsystem that stabilizes reasoning through behavioral constraints and cost-aware model routing. This design enables precise knowledge alignment while maintaining efficient reasoning across heterogeneous subtasks. We evaluate KryptoPilot on two established CTF benchmarks and in six real-world CTF competitions. KryptoPilot achieves a complete solve rate on InterCode-CTF, solves between 56 and 60 percent of cryptographic challenges on the NYU-CTF benchmark, and successfully solves 26 out of 33 cryptographic challenges in live competitions, including multiple earliest-solved and uniquely-solved instances. These results demonstrate the necessity of open-world, fine-grained knowledge augmentation and governed reasoning for scaling LLM-based agents to real-world cryptographic exploitation.

cs.CR↗

arXiv2026

Differentiation Between Faults and Cyberattacks through Combined Analysis of Cyberspace Logs and Physical Measurements

In recent years, cyberattacks - along with physical faults - have become an increasing factor causing system failures, especially in DER (Distributed Energy Resources) systems. In addition, according to the literature, a number of faults have been reported to remain undetected. Consequently, unlike anomaly detection works that only identify abnormalities, differentiating undetected faults and cyberattacks is a challenging task. Although several works have studied this problem, they crucially fall short of achieving an accurate distinction due to the reliance on physical laws or physical measurements. To resolve this issue, the industry typically conducts an integrated analysis with physical measurements and cyberspace information. Nevertheless, this industry approach consumes a significant amount of time due to the manual efforts required in the analysis. In this work, we focus on addressing these crucial gaps by proposing a non-trivial approach of distinguishing undetected faults and cyberattacks in DER systems. Specifically, first, a special kind of dependency graph is constructed using a novel virtual physical variable-oriented taint analysis (PVOTA) algorithm. Then, the graph is simplified using an innovative node pruning technique, which is based on a set of context-dependent operations. Next, a set of patterns capturing domain-specific knowledge is derived to bridge the semantic gaps between the cyber and physical sides. Finally, these patterns are matched to the relevant events that occurred during failure incidents, and possible root causes are concluded based on the pattern matching results. In the end, the efficacy of the proposed semi-automatic integrated analysis is evaluated through five case studies covering failure incidents caused by FDI attacks, system faults, and memory corruption attacks, including a false-classification scenario.

cs.CR↗

arXiv2025

Deep Pathomic Learning Defines Prognostic Subtypes and Molecular Drivers in Colorectal Cancer

Precise prognostic stratification of colorectal cancer (CRC) remains a major clinical challenge due to its high heterogeneity. The conventional TNM staging system is inadequate for personalized medicine. We aimed to develop and validate a novel multiple instance learning model TDAM-CRC using histopathological whole-slide images for accurate prognostic prediction and to uncover its underlying molecular mechanisms. We trained the model on the TCGA discovery cohort (n=581), validated it in an independent external cohort (n=1031), and further we integrated multi-omics data to improve model interpretability and identify novel prognostic biomarkers. The results demonstrated that the TDAM-CRC achieved robust risk stratification in both cohorts. Its predictive performance significantly outperformed the conventional clinical staging system and multiple state-of-the-art models. The TDAM-CRC risk score was confirmed as an independent prognostic factor in multivariable analysis. Multi-omics analysis revealed that the high-risk subtype is closely associated with metabolic reprogramming and an immunosuppressive tumor microenvironment. Through interaction network analysis, we identified and validated Mitochondrial Ribosomal Protein L37 (MRPL37) as a key hub gene linking deep pathomic features to clinical prognosis. We found that high expression of MRPL37, driven by promoter hypomethylation, serves as an independent biomarker of favorable prognosis. Finally, we constructed a nomogram incorporating the TDAM-CRC risk score and clinical factors to provide a precise and interpretable clinical decision-making tool for CRC patients. Our AI-driven pathological model TDAM-CRC provides a robust tool for improved CRC risk stratification, reveals new molecular targets, and facilitates personalized clinical decision-making.

cs.LG↗

arXiv2024

From Score-Driven to Value-Sharing: Understanding Chinese Family Use of AI to Support Decision Making of College Applications

This study investigates how 18-year-old students, parents, and experts in China utilize artificial intelligence (AI) tools to support decision-making in college applications during college entrance exam -- a highly competitive, score-driven, annual national exam. Through 32 interviews, we examine the use of Quark GaoKao, an AI tool that generates college application lists and acceptance probabilities based on exam scores, historical data, preferred locations, etc. Our findings show that AI tools are predominantly used by parents with limited involvement from students, and often focus on immediate exam results, failing to address long-term career goals. We also identify challenges such as misleading AI recommendations, and irresponsible use of AI by third-party consultant agencies. Finally, we offer design insights to better support multi-stakeholders' decision-making in families, especially in the Chinese context, and discuss how emerging AI tools create barriers for families with fewer resources.

cs.HC↗

arXiv2024

Unmasking the Shadows: Pinpoint the Implementations of Anti-Dynamic Analysis Techniques in Malware Using LLM

Sandboxes and other dynamic analysis processes are prevalent in malware detection systems nowadays to enhance the capability of detecting 0-day malware. Therefore, techniques of anti-dynamic analysis (TADA) are prevalent in modern malware samples, and sandboxes can suffer from false negatives and analysis failures when analyzing the samples with TADAs. In such cases, human reverse engineers will get involved in conducting dynamic analysis manually (i.e., debugging, patching), which in turn also gets obstructed by TADAs. In this work, we propose a Large Language Model (LLM) based workflow that can pinpoint the location of the TADA implementation in the code, to help reverse engineers place breakpoints used in debugging. Our evaluation shows that we successfully identified the locations of 87.80% known TADA implementations adopted from public repositories. In addition, we successfully pinpoint the locations of TADAs in 4 well-known malware samples that are documented in online malware analysis blogs.

cs.CR↗

arXiv2024

Hide Your Malicious Goal Into Benign Narratives: Jailbreak Large Language Models through Carrier Articles

Large Language Model (LLM) jailbreak refers to a type of attack aimed to bypass the safeguard of an LLM to generate contents that are inconsistent with the safe usage guidelines. Based on the insights from the self-attention computation process, this paper proposes a novel blackbox jailbreak approach, which involves crafting the payload prompt by strategically injecting the prohibited query into a carrier article. The carrier article maintains the semantic proximity to the prohibited query, which is automatically produced by combining a hypernymy article and a context, both of which are generated from the prohibited query. The intuition behind the usage of carrier article is to activate the neurons in the model related to the semantics of the prohibited query while suppressing the neurons that will trigger the objectionable text. Carrier article itself is benign, and we leveraged prompt injection techniques to produce the payload prompt. We evaluate our approach using JailbreakBench, testing against four target models across 100 distinct jailbreak objectives. The experimental results demonstrate our method's superior effectiveness, achieving an average success rate of 63% across all target models, significantly outperforming existing blackbox jailbreak methods.

cs.CR↗

arXiv2024

A hybrid LLM workflow can help identify user privilege related variables in programs of any size

Many programs involves operations and logic manipulating user privileges, which is essential for the security of an organization. Therefore, one common malicious goal of attackers is to obtain or escalate the privileges, causing privilege leakage. To protect the program and the organization against privilege leakage attacks, it is important to eliminate the vulnerabilities which can be exploited to achieve such attacks. Unfortunately, while memory vulnerabilities are less challenging to find, logic vulnerabilities are much more imminent, harmful and difficult to identify. Accordingly, many analysts choose to find user privilege related (UPR) variables first as start points to investigate the code where the UPR variables may be used to see if there exists any vulnerabilities, especially the logic ones. In this paper, we introduce a large language model (LLM) workflow that can assist analysts in identifying such UPR variables, which is considered to be a very time-consuming task. Specifically, our tool will audit all the variables in a program and output a UPR score, which is the degree of relationship (closeness) between the variable and user privileges, for each variable. The proposed approach avoids the drawbacks introduced by directly prompting a LLM to find UPR variables by focusing on leverage the LLM at statement level instead of supplying LLM with very long code snippets. Those variables with high UPR scores are essentially potential UPR variables, which should be manually investigated. Our experiments show that using a typical UPR score threshold (i.e., UPR score >0.8), the false positive rate (FPR) is only 13.49%, while UPR variable found is significantly more than that of the heuristic based method.

cs.CR↗

arXiv2024

Identifying Non-Control Security-Critical Data through Program Dependence Learning

As control-flow protection gets widely deployed, it is difficult for attackers to corrupt control-data and achieve control-flow hijacking. Instead, data-oriented attacks, which manipulate non-control data, have been demonstrated to be feasible and powerful. In data-oriented attacks, a fundamental step is to identify non-control, security-critical data. However, critical data identification processes are not scalable in previous works, because they mainly rely on tedious human efforts to identify critical data. To address this issue, we propose a novel approach that combines traditional program analysis with deep learning. At a higher level, by examining how analysts identify critical data, we first propose dynamic analysis algorithms to identify the program semantics (and features) that are correlated with the impact of a critical data. Then, motivated by the unique challenges in the critical data identification task, we formalize the distinguishing features and use customized program dependence graphs (PDG) to embed the features. Different from previous works using deep learning to learn basic program semantics, this paper adopts a special neural network architecture that can capture the long dependency paths (in the PDG), through which a critical variable propagates its impact. We have implemented a fully-automatic toolchain and conducted comprehensive evaluations. According to the evaluations, our model can achieve 90% accuracy. The toolchain uncovers 80 potential critical variables in Google FuzzBench. In addition, we demonstrate the harmfulness of the exploits using the identified critical variables by simulating 7 data-oriented attacks through GDB.

cs.CR↗

arXiv2024

ROPNN: Detection of ROP Payloads Using Deep Neural Networks

Return-oriented programming (ROP) is a code reuse attack that chains short snippets of existing code to perform arbitrary operations on target machines. Existing detection methods against ROP exhibit unsatisfactory detection accuracy and/or have high runtime overhead. In this paper, we present ROPNN, which innovatively combines address space layout guided disassembly and deep neural networks to detect ROP payloads. The disassembler treats application input data as code pointers and aims to find any potential gadget chains, which are then classified by a deep neural network as benign or malicious. Our experiments show that ROPNN has high detection rate (99.3%) and a very low false positive rate (0.01%). ROPNN successfully detects all of the 100 real-world ROP exploits that are collected in-the-wild, created manually or created by ROP exploit generation tools. Additionally, ROPNN detects all 10 ROP exploits that can bypass Bin-CFI. ROPNN is non-intrusive and does not incur any runtime overhead to the protected program.

cs.CR↗

arXiv2023

An unprecedented synergy of high-temperature tensile strength and ductility in a NiCoCrAlTi high-entropy alloy

The present work reported a novel L12-strengthening NiCoCrAlTi high entropy alloy (HEA) with an outstanding synergy of tensile strength and ductility at both ambient and high temperatures. Transmission electron microscopy (TEM) characterization revealed a high density of rod-like and spheroidal L12 precipitates distributing in the micro/nanograins and non-recrystallized regions in the annealed specimens. The tremendously high yield stress, ultimate tensile stress (UTS), and ductility of the HEA at 600 C were ~1060 MPa, 1271 MPa, and 25%, respectively, which were significantly superior to most reported HEAs and Co- and Ni-based superalloys to date. Systematic TEM analysis unveiled that the cooperation among L12 precipitation, extensive stacking faults (SFs), deformation twins (DTs), immobile Lomer-Cottrell (L-C) locks formed from interactions between SFs and SFs/DTs, hierarchical SFs/DTs networks, as well as hetero-deformation-induced strengthening dominated the plastic deformation at 600 C. Such a unique deformation mechanism enabled extremely high tensile strength and sustained ductility of the HEA at a high temperature.

cond-mat.mtrl-sci↗

arXiv2023

ReZG: Retrieval-Augmented Zero-Shot Counter Narrative Generation for Hate Speech

The proliferation of hate speech (HS) on social media poses a serious threat to societal security. Automatic counter narrative (CN) generation, as an active strategy for HS intervention, has garnered increasing attention in recent years. Existing methods for automatically generating CNs mainly rely on re-training or fine-tuning pre-trained language models (PLMs) on human-curated CN corpora. Unfortunately, the annotation speed of CN corpora cannot keep up with the growth of HS targets, while generating specific and effective CNs for unseen targets remains a significant challenge for the model. To tackle this issue, we propose Retrieval-Augmented Zero-shot Generation (ReZG) to generate CNs with high-specificity for unseen targets. Specifically, we propose a multi-dimensional hierarchical retrieval method that integrates stance, semantics, and fitness, extending the retrieval metric from single dimension to multiple dimensions suitable for the knowledge that refutes HS. Then, we implement an energy-based constrained decoding mechanism that enables PLMs to use differentiable knowledge preservation, countering, and fluency constraint functions instead of in-target CNs as control signals for generation, thereby achieving zero-shot CN generation. With the above techniques, ReZG can integrate external knowledge flexibly and improve the specificity of CNs. Experimental results show that ReZG exhibits stronger generalization capabilities and outperforms strong baselines with significant improvements of 2.0%+ in the relevance and 4.5%+ in the countering success rate metrics.

cs.CL↗

arXiv2023

Multimodal Short Video Rumor Detection System Based on Contrastive Learning

With the rise of short video platforms as prominent channels for news dissemination, major platforms in China have gradually evolved into fertile grounds for the proliferation of fake news. However, distinguishing short video rumors poses a significant challenge due to the substantial amount of information and shared features among videos, resulting in homogeneity. To address the dissemination of short video rumors effectively, our research group proposes a methodology encompassing multimodal feature fusion and the integration of external knowledge, considering the merits and drawbacks of each algorithm. The proposed detection approach entails the following steps: (1) creation of a comprehensive dataset comprising multiple features extracted from short videos; (2) development of a multimodal rumor detection model: first, we employ the Temporal Segment Networks (TSN) video coding model to extract video features, followed by the utilization of Optical Character Recognition (OCR) and Automatic Speech Recognition (ASR) to extract textual features. Subsequently, the BERT model is employed to fuse textual and video features; (3) distinction is achieved through contrast learning: we acquire external knowledge by crawling relevant sources and leverage a vector database to incorporate this knowledge into the classification output. Our research process is driven by practical considerations, and the knowledge derived from this study will hold significant value in practical scenarios, such as short video rumor identification and the management of social opinions.

cs.CV↗

arXiv2022

ClueGraphSum: Let Key Clues Guide the Cross-Lingual Abstractive Summarization

Cross-Lingual Summarization (CLS) is the task to generate a summary in one language for an article in a different language. Previous studies on CLS mainly take pipeline methods or train the end-to-end model using the translated parallel data. However, the quality of generated cross-lingual summaries needs more further efforts to improve, and the model performance has never been evaluated on the hand-written CLS dataset. Therefore, we first propose a clue-guided cross-lingual abstractive summarization method to improve the quality of cross-lingual summaries, and then construct a novel hand-written CLS dataset for evaluation. Specifically, we extract keywords, named entities, etc. of the input article as key clues for summarization and then design a clue-guided algorithm to transform an article into a graph with less noisy sentences. One Graph encoder is built to learn sentence semantics and article structures and one Clue encoder is built to encode and translate key clues, ensuring the information of important parts are reserved in the generated summary. These two encoders are connected by one decoder to directly learn cross-lingual semantics. Experimental results show that our method has stronger robustness for longer inputs and substantially improves the performance over the strong baseline, achieving an improvement of 8.55 ROUGE-1 (English-to-Chinese summarization) and 2.13 MoverScore (Chinese-to-English summarization) scores over the existing SOTA.

cs.CL↗