arXiv subjects

Kailong Wang

Publications and source records attributed to Kailong Wang.

70 records · Page 4Linked to original sources

arXiv2024

Drowzee: Metamorphic Testing for Fact-Conflicting Hallucination Detection in Large Language Models

Large language models (LLMs) have transformed the landscape of language processing, yet struggle with significant challenges in terms of security, privacy, and the generation of seemingly coherent but factually inaccurate outputs, commonly referred to as hallucinations. Among these challenges, one particularly pressing issue is Fact-Conflicting Hallucination (FCH), where LLMs generate content that directly contradicts established facts. Tackling FCH poses a formidable task due to two primary obstacles: Firstly, automating the construction and updating of benchmark datasets is challenging, as current methods rely on static benchmarks that don't cover the diverse range of FCH scenarios. Secondly, validating LLM outputs' reasoning process is inherently complex, especially with intricate logical relations involved. In addressing these obstacles, we propose an innovative approach leveraging logic programming to enhance metamorphic testing for detecting Fact-Conflicting Hallucinations (FCH). Our method gathers data from sources like Wikipedia, expands it with logical reasoning to create diverse test cases, assesses LLMs through structured prompts, and validates their coherence using semantic-aware assessment mechanisms. Our method generates test cases and detects hallucinations across six different LLMs spanning nine domains, revealing hallucination rates ranging from 24.7% to 59.8%. Key observations indicate that LLMs encounter challenges, particularly with temporal concepts, handling out-of-distribution knowledge, and exhibiting deficiencies in logical reasoning capabilities. The outcomes underscore the efficacy of logic-based test cases generated by our tool in both triggering and identifying hallucinations. These findings underscore the imperative for ongoing collaborative endeavors within the community to detect and address LLM hallucinations.

cs.SE↗

arXiv2024

SPOLRE: Semantic Preserving Object Layout Reconstruction for Image Captioning System Testing

Image captioning (IC) systems, such as Microsoft Azure Cognitive Service, translate image content into descriptive language but can generate inaccuracies leading to misinterpretations. Advanced testing techniques like MetaIC and ROME aim to address these issues but face significant challenges. These methods require intensive manual labor for detailed annotations and often produce unrealistic images, either by adding unrelated objects or failing to remove existing ones. Additionally, they generate limited test suites, with MetaIC restricted to inserting specific objects and ROME limited to a narrow range of variations. We introduce SPOLRE, a novel automated tool for semantic-preserving object layout reconstruction in IC system testing. SPOLRE leverages four transformation techniques to modify object layouts without altering the image's semantics. This automated approach eliminates the need for manual annotations and creates realistic, varied test suites. Our tests show that over 75% of survey respondents find SPOLRE-generated images more realistic than those from state-of-the-art methods. SPOLRE excels in identifying caption errors, detecting 31,544 incorrect captions across seven IC systems with an average precision of 91.62%, surpassing other methods which average 85.65% accuracy and identify 17,160 incorrect captions. Notably, SPOLRE identified 6,236 unique issues within Azure, demonstrating its effectiveness against one of the most advanced IC systems.

cs.SE↗

arXiv2024

Continuous Embedding Attacks via Clipped Inputs in Jailbreaking Large Language Models

Security concerns for large language models (LLMs) have recently escalated, focusing on thwarting jailbreaking attempts in discrete prompts. However, the exploration of jailbreak vulnerabilities arising from continuous embeddings has been limited, as prior approaches primarily involved appending discrete or continuous suffixes to inputs. Our study presents a novel channel for conducting direct attacks on LLM inputs, eliminating the need for suffix addition or specific questions provided that the desired output is predefined. We additionally observe that extensive iterations often lead to overfitting, characterized by repetition in the output. To counteract this, we propose a simple yet effective strategy named CLIP. Our experiments show that for an input length of 40 at iteration 1000, applying CLIP improves the ASR from 62% to 83%

cs.CR↗

arXiv2024

WALLETRADAR: Towards Automating the Detection of Vulnerabilities in Browser-based Cryptocurrency Wallets

Cryptocurrency wallets, acting as fundamental infrastructure to the blockchain ecosystem, have seen significant user growth, particularly among browser-based wallets (i.e., browser extensions). However, this expansion accompanies security challenges, making these wallets prime targets for malicious activities. Despite a substantial user base, there is not only a significant gap in comprehensive security analysis but also a pressing need for specialized tools that can aid developers in reducing vulnerabilities during the development process. To fill the void, we present a comprehensive security analysis of browser-based wallets in this paper, along with the development of an automated tool designed for this purpose. We first compile a taxonomy of security vulnerabilities resident in cryptocurrency wallets by harvesting historical security reports. Based on this, we design WALLETRADAR, an automated detection framework that can accurately identify security issues based on static and dynamic analysis. Evaluation of 96 popular browser-based wallets shows WALLETRADAR's effectiveness, by successfully automating the detection process in 90% of these wallets with high precision. This evaluation has led to the discovery of 116 security vulnerabilities corresponding to 70 wallets. By the time of this paper, we have received confirmations of 10 vulnerabilities from 8 wallet developers, with over $2,000 bug bounties. Further, we observed that 12 wallet developers have silently fixed 16 vulnerabilities after our disclosure. WALLETRADAR can effectively automate the identification of security risks in cryptocurrency wallets, thereby enhancing software development quality and safety in the blockchain ecosystem.

cs.CR↗

arXiv2024

Glitch Tokens in Large Language Models: Categorization Taxonomy and Effective Detection

With the expanding application of Large Language Models (LLMs) in various domains, it becomes imperative to comprehensively investigate their unforeseen behaviors and consequent outcomes. In this study, we introduce and systematically explore the phenomenon of "glitch tokens", which are anomalous tokens produced by established tokenizers and could potentially compromise the models' quality of response. Specifically, we experiment on seven top popular LLMs utilizing three distinct tokenizers and involving a totally of 182,517 tokens. We present categorizations of the identified glitch tokens and symptoms exhibited by LLMs when interacting with glitch tokens. Based on our observation that glitch tokens tend to cluster in the embedding space, we propose GlitchHunter, a novel iterative clustering-based technique, for efficient glitch token detection. The evaluation shows that our approach notably outperforms three baseline methods on eight open-source LLMs. To the best of our knowledge, we present the first comprehensive study on glitch tokens. Our new detection further provides valuable insights into mitigating tokenization-related errors in LLMs.

cs.CL↗

arXiv2024

Large Language Models for Software Engineering: A Systematic Literature Review

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.

cs.SE↗

arXiv2024

The Devil Behind the Mirror: Tracking the Campaigns of Cryptocurrency Abuses on the Dark Web

The dark web has emerged as the state-of-the-art solution for enhanced anonymity. Just like a double-edged sword, it also inadvertently becomes the safety net and breeding ground for illicit activities. Among them, cryptocurrencies have been prevalently abused to receive illicit income while evading regulations. Despite the continuing efforts to combat illicit activities, there is still a lack of an in-depth understanding regarding the characteristics and dynamics of cryptocurrency abuses on the dark web. In this work, we conduct a multi-dimensional and systematic study to track cryptocurrency-related illicit activities and campaigns on the dark web. We first harvest a dataset of 4,923 cryptocurrency-related onion sites with over 130K pages. Then, we detect and extract the illicit blockchain transactions to characterize the cryptocurrency abuses, targeting features from single/clustered addresses and illicit campaigns. Throughout our study, we have identified 2,564 illicit sites with 1,189 illicit blockchain addresses, which account for 90.8 BTC in revenue. Based on their inner connections, we further identify 66 campaigns behind them. Our exploration suggests that illicit activities on the dark web have strong correlations, which can guide us to identify new illicit blockchain addresses and onions, and raise alarms at the early stage of their deployment.

cs.CR↗

arXiv2024

Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study

Large Language Models (LLMs), like ChatGPT, have demonstrated vast potential but also introduce challenges related to content constraints and potential misuse. Our study investigates three key research questions: (1) the number of different prompt types that can jailbreak LLMs, (2) the effectiveness of jailbreak prompts in circumventing LLM constraints, and (3) the resilience of ChatGPT against these jailbreak prompts. Initially, we develop a classification model to analyze the distribution of existing prompts, identifying ten distinct patterns and three categories of jailbreak prompts. Subsequently, we assess the jailbreak capability of prompts with ChatGPT versions 3.5 and 4.0, utilizing a dataset of 3,120 jailbreak questions across eight prohibited scenarios. Finally, we evaluate the resistance of ChatGPT against jailbreak prompts, finding that the prompts can consistently evade the restrictions in 40 use-case scenarios. The study underscores the importance of prompt structures in jailbreaking LLMs and discusses the challenges of robust jailbreak prompt generation and prevention.

cs.SE↗

arXiv2024

MeTMaP: Metamorphic Testing for Detecting False Vector Matching Problems in LLM Augmented Generation

Augmented generation techniques such as Retrieval-Augmented Generation (RAG) and Cache-Augmented Generation (CAG) have revolutionized the field by enhancing large language model (LLM) outputs with external knowledge and cached information. However, the integration of vector databases, which serve as a backbone for these augmentations, introduces critical challenges, particularly in ensuring accurate vector matching. False vector matching in these databases can significantly compromise the integrity and reliability of LLM outputs, leading to misinformation or erroneous responses. Despite the crucial impact of these issues, there is a notable research gap in methods to effectively detect and address false vector matches in LLM-augmented generation. This paper presents MeTMaP, a metamorphic testing framework developed to identify false vector matching in LLM-augmented generation systems. We derive eight metamorphic relations (MRs) from six NLP datasets, which form our method's core, based on the idea that semantically similar texts should match and dissimilar ones should not. MeTMaP uses these MRs to create sentence triplets for testing, simulating real-world LLM scenarios. Our evaluation of MeTMaP over 203 vector matching configurations, involving 29 embedding models and 7 distance metrics, uncovers significant inaccuracies. The results, showing a maximum accuracy of only 41.51\% on our tests compared to the original datasets, emphasize the widespread issue of false matches in vector matching methods and the critical need for effective detection and mitigation in LLM-augmented applications.

cs.SE↗

arXiv2024

Beyond Fidelity: Explaining Vulnerability Localization of Learning-based Detectors

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.

cs.CR↗

arXiv2024

Pandora: Jailbreak GPTs by Retrieval Augmented Generation Poisoning

Large Language Models~(LLMs) have gained immense popularity and are being increasingly applied in various domains. Consequently, ensuring the security of these models is of paramount importance. Jailbreak attacks, which manipulate LLMs to generate malicious content, are recognized as a significant vulnerability. While existing research has predominantly focused on direct jailbreak attacks on LLMs, there has been limited exploration of indirect methods. The integration of various plugins into LLMs, notably Retrieval Augmented Generation~(RAG), which enables LLMs to incorporate external knowledge bases into their response generation such as GPTs, introduces new avenues for indirect jailbreak attacks. To fill this gap, we investigate indirect jailbreak attacks on LLMs, particularly GPTs, introducing a novel attack vector named Retrieval Augmented Generation Poisoning. This method, Pandora, exploits the synergy between LLMs and RAG through prompt manipulation to generate unexpected responses. Pandora uses maliciously crafted content to influence the RAG process, effectively initiating jailbreak attacks. Our preliminary tests show that Pandora successfully conducts jailbreak attacks in four different scenarios, achieving higher success rates than direct attacks, with 64.3\% for GPT-3.5 and 34.8\% for GPT-4.

cs.CR↗

arXiv2024

MalModel: Hiding Malicious Payload in Mobile Deep Learning Models with Black-box Backdoor Attack

Mobile malware has become one of the most critical security threats in the era of ubiquitous mobile computing. Despite the intensive efforts from security experts to counteract it, recent years have still witnessed a rapid growth of identified malware samples. This could be partly attributed to the newly-emerged technologies that may constantly open up under-studied attack surfaces for the adversaries. One typical example is the recently-developed mobile machine learning (ML) framework that enables storing and running deep learning (DL) models on mobile devices. Despite obvious advantages, this new feature also inadvertently introduces potential vulnerabilities (e.g., on-device models may be modified for malicious purposes). In this work, we propose a method to generate or transform mobile malware by hiding the malicious payloads inside the parameters of deep learning models, based on a strategy that considers four factors (layer type, layer number, layer coverage and the number of bytes to replace). Utilizing the proposed method, we can run malware in DL mobile applications covertly with little impact on the model performance (i.e., as little as 0.4% drop in accuracy and at most 39ms latency overhead).

cs.CR↗

arXiv2024

Digger: Detecting Copyright Content Mis-usage in Large Language Model Training

Pre-training, which utilizes extensive and varied datasets, is a critical factor in the success of Large Language Models (LLMs) across numerous applications. However, the detailed makeup of these datasets is often not disclosed, leading to concerns about data security and potential misuse. This is particularly relevant when copyrighted material, still under legal protection, is used inappropriately, either intentionally or unintentionally, infringing on the rights of the authors. In this paper, we introduce a detailed framework designed to detect and assess the presence of content from potentially copyrighted books within the training datasets of LLMs. This framework also provides a confidence estimation for the likelihood of each content sample's inclusion. To validate our approach, we conduct a series of simulated experiments, the results of which affirm the framework's effectiveness in identifying and addressing instances of content misuse in LLM training processes. Furthermore, we investigate the presence of recognizable quotes from famous literary works within these datasets. The outcomes of our study have significant implications for ensuring the ethical use of copyrighted materials in the development of LLMs, highlighting the need for more transparent and responsible data management practices in this field.

cs.CR↗

arXiv2023

MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots

Large Language Models (LLMs) have revolutionized Artificial Intelligence (AI) services due to their exceptional proficiency in understanding and generating human-like text. LLM chatbots, in particular, have seen widespread adoption, transforming human-machine interactions. However, these LLM chatbots are susceptible to "jailbreak" attacks, where malicious users manipulate prompts to elicit inappropriate or sensitive responses, contravening service policies. Despite existing attempts to mitigate such threats, our research reveals a substantial gap in our understanding of these vulnerabilities, largely due to the undisclosed defensive measures implemented by LLM service providers. In this paper, we present Jailbreaker, a comprehensive framework that offers an in-depth understanding of jailbreak attacks and countermeasures. Our work makes a dual contribution. First, we propose an innovative methodology inspired by time-based SQL injection techniques to reverse-engineer the defensive strategies of prominent LLM chatbots, such as ChatGPT, Bard, and Bing Chat. This time-sensitive approach uncovers intricate details about these services' defenses, facilitating a proof-of-concept attack that successfully bypasses their mechanisms. Second, we introduce an automatic generation method for jailbreak prompts. Leveraging a fine-tuned LLM, we validate the potential of automated jailbreak generation across various commercial LLM chatbots. Our method achieves a promising average success rate of 21.58%, significantly outperforming the effectiveness of existing techniques. We have responsibly disclosed our findings to the concerned service providers, underscoring the urgent need for more robust defenses. Jailbreaker thus marks a significant step towards understanding and mitigating jailbreak threats in the realm of LLM chatbots.

cs.CR↗

arXiv2023

Empirical Study on Transformer-based Techniques for Software Engineering

Many Transformer-based pre-trained models for code have been developed and applied to code-related tasks. In this paper, we review the existing literature, examine the suitability of model architectures for different tasks, and look at the generalization ability of models on different datasets, and their resource consumption. We examine three very representative pre-trained models for code: CodeBERT, CodeGPT, and CodeT5, and conduct experiments on the top-4 most targeted software engineering tasks that we found in our literature survey: Code Summarization, Bug Fixing, Bug Detection, and Code Search. In our study, we showcase the capability of decoder-only models (CodeGPT) for specific generation tasks under state-of-the-art evaluation metrics and contest the common belief that the encoder-decoder architecture is optimal for general-purpose coding tasks. Additionally, we found that the most frequently used models are not necessarily the most suitable for certain applications and the developers' needs are not adequately addressed by current research. As well, we found that the benchmark and frequent dataset for Bug Fixing and Code Summarization both fail to enable models to generalize onto other datasets for the same task (the frequent dataset refers to the dataset with the highest frequency used in literature other than the benchmark). We use statistical testing to support our conclusions from experiments. Finally, CodeBERT is highly efficient for understanding tasks, whereas CodeT5's efficiency for generation tasks is in doubt, as the highest resource consumption does not guarantee a consistent better performance on different metrics. We also discuss the numerous practical issues in advancing future research on transformer-based models for code-related tasks.

cs.SE↗

arXiv2020

Plastic Scintillation Detectors for Time-of-Flight Mass Measurements

Fast timing detectors are an essential element in the experimental setup for time-of-flight (ToF) mass measurements of unstable nuclei. We have upgraded the scintillator detectors used in experiments at the National Superconducting Cyclotron Laboratory (NSCL) by increasing the number of photomultiplier tubes that read out their light signals to four per detector, and characterized them in a test experiment with $^{48}$Ca beam at the NSCL. The new detectors achieved a time resolution ($σ$) of 7.5 ps. We systematically investigated different factors that affect their timing performance. In addition, we evaluated the ability of positioning the hitting points on the scintillator using the timing information and obtained a resolution ($σ$) below 1 mm for well-defined beam spots.

physics.ins-det↗