arXiv subjects

Yuekang Li

Publications and source records attributed to Yuekang Li.

69 records · Page 4Linked to original sources

arXiv2024

PentestGPT: An LLM-empowered Automatic Penetration Testing Tool

Penetration testing, a crucial industrial practice for ensuring system security, has traditionally resisted automation due to the extensive expertise required by human professionals. Large Language Models (LLMs) have shown significant advancements in various domains, and their emergent abilities suggest their potential to revolutionize industries. In this research, we evaluate the performance of LLMs on real-world penetration testing tasks using a robust benchmark created from test machines with platforms. Our findings reveal that while LLMs demonstrate proficiency in specific sub-tasks within the penetration testing process, such as using testing tools, interpreting outputs, and proposing subsequent actions, they also encounter difficulties maintaining an integrated understanding of the overall testing scenario. In response to these insights, we introduce PentestGPT, an LLM-empowered automatic penetration testing tool that leverages the abundant domain knowledge inherent in LLMs. PentestGPT is meticulously designed with three self-interacting modules, each addressing individual sub-tasks of penetration testing, to mitigate the challenges related to context loss. Our evaluation shows that PentestGPT not only outperforms LLMs with a task-completion increase of 228.6\% compared to the \gptthree model among the benchmark targets but also proves effective in tackling real-world penetration testing challenges. Having been open-sourced on GitHub, PentestGPT has garnered over 4,700 stars and fostered active community engagement, attesting to its value and impact in both the academic and industrial spheres.

cs.SE↗

arXiv2024

A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models

Large Language Models (LLMS) have increasingly become central to generating content with potential societal impacts. Notably, these models have demonstrated capabilities for generating content that could be deemed harmful. To mitigate these risks, researchers have adopted safety training techniques to align model outputs with societal values to curb the generation of malicious content. However, the phenomenon of "jailbreaking", where carefully crafted prompts elicit harmful responses from models, persists as a significant challenge. This research conducts a comprehensive analysis of existing studies on jailbreaking LLMs and their defense techniques. We meticulously investigate nine attack techniques and seven defense techniques applied across three distinct language models: Vicuna, LLama, and GPT-3.5 Turbo. We aim to evaluate the effectiveness of these attack and defense techniques. Our findings reveal that existing white-box attacks underperform compared to universal techniques and that including special tokens in the input significantly affects the likelihood of successful attacks. This research highlights the need to concentrate on the security facets of LLMs. Additionally, we contribute to the field by releasing our datasets and testing framework, aiming to foster further research into LLM security. We believe these contributions will facilitate the exploration of security measures within this domain.

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

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

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

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

ASTER: Automatic Speech Recognition System Accessibility Testing for Stutterers

The popularity of automatic speech recognition (ASR) systems nowadays leads to an increasing need for improving their accessibility. Handling stuttering speech is an important feature for accessible ASR systems. To improve the accessibility of ASR systems for stutterers, we need to expose and analyze the failures of ASR systems on stuttering speech. The speech datasets recorded from stutterers are not diverse enough to expose most of the failures. Furthermore, these datasets lack ground truth information about the non-stuttered text, rendering them unsuitable as comprehensive test suites. Therefore, a methodology for generating stuttering speech as test inputs to test and analyze the performance of ASR systems is needed. However, generating valid test inputs in this scenario is challenging. The reason is that although the generated test inputs should mimic how stutterers speak, they should also be diverse enough to trigger more failures. To address the challenge, we propose ASTER, a technique for automatically testing the accessibility of ASR systems. ASTER can generate valid test cases by injecting five different types of stuttering. The generated test cases can both simulate realistic stuttering speech and expose failures in ASR systems. Moreover, ASTER can further enhance the quality of the test cases with a multi-objective optimization-based seed updating algorithm. We implemented ASTER as a framework and evaluated it on four open-source ASR models and three commercial ASR systems. We conduct a comprehensive evaluation of ASTER and find that it significantly increases the word error rate, match error rate, and word information loss in the evaluated ASR systems. Additionally, our user study demonstrates that the generated stuttering audio is indistinguishable from real-world stuttering audio clips.

cs.SD↗

arXiv2023

ACETest: Automated Constraint Extraction for Testing Deep Learning Operators

Deep learning (DL) applications are prevalent nowadays as they can help with multiple tasks. DL libraries are essential for building DL applications. Furthermore, DL operators are the important building blocks of the DL libraries, that compute the multi-dimensional data (tensors). Therefore, bugs in DL operators can have great impacts. Testing is a practical approach for detecting bugs in DL operators. In order to test DL operators effectively, it is essential that the test cases pass the input validity check and are able to reach the core function logic of the operators. Hence, extracting the input validation constraints is required for generating high-quality test cases. Existing techniques rely on either human effort or documentation of DL library APIs to extract the constraints. They cannot extract complex constraints and the extracted constraints may differ from the actual code implementation. To address the challenge, we propose ACETest, a technique to automatically extract input validation constraints from the code to build valid yet diverse test cases which can effectively unveil bugs in the core function logic of DL operators. For this purpose, ACETest can automatically identify the input validation code in DL operators, extract the related constraints and generate test cases according to the constraints. The experimental results on popular DL libraries, TensorFlow and PyTorch, demonstrate that ACETest can extract constraints with higher quality than state-of-the-art (SOTA) techniques. Moreover, ACETest is capable of extracting 96.4% more constraints and detecting 1.95 to 55 times more bugs than SOTA techniques. In total, we have used ACETest to detect 108 previously unknown bugs on TensorFlow and PyTorch, with 87 of them confirmed by the developers. Lastly, five of the bugs were assigned with CVE IDs due to their security impacts.

cs.SE↗

arXiv2023

Automatic Code Summarization via ChatGPT: How Far Are We?

To support software developers in understanding and maintaining programs, various automatic code summarization techniques have been proposed to generate a concise natural language comment for a given code snippet. Recently, the emergence of large language models (LLMs) has led to a great boost in the performance of natural language processing tasks. Among them, ChatGPT is the most popular one which has attracted wide attention from the software engineering community. However, it still remains unclear how ChatGPT performs in (automatic) code summarization. Therefore, in this paper, we focus on evaluating ChatGPT on a widely-used Python dataset called CSN-Python and comparing it with several state-of-the-art (SOTA) code summarization models. Specifically, we first explore an appropriate prompt to guide ChatGPT to generate in-distribution comments. Then, we use such a prompt to ask ChatGPT to generate comments for all code snippets in the CSN-Python test set. We adopt three widely-used metrics (including BLEU, METEOR, and ROUGE-L) to measure the quality of the comments generated by ChatGPT and SOTA models (including NCS, CodeBERT, and CodeT5). The experimental results show that in terms of BLEU and ROUGE-L, ChatGPT's code summarization performance is significantly worse than all three SOTA models. We also present some cases and discuss the advantages and disadvantages of ChatGPT in code summarization. Based on the findings, we outline several open challenges and opportunities in ChatGPT-based code summarization.

cs.SE↗

arXiv2022

Morest: Model-based RESTful API Testing with Execution Feedback

RESTful APIs are arguably the most popular endpoints for accessing Web services. Blackbox testing is one of the emerging techniques for ensuring the reliability of RESTful APIs. The major challenge in testing RESTful APIs is the need for correct sequences of API operation calls for in-depth testing. To build meaningful operation call sequences, researchers have proposed techniques to learn and utilize the API dependencies based on OpenAPI specifications. However, these techniques either lack the overall awareness of how all the APIs are connected or the flexibility of adaptively fixing the learned knowledge. In this paper, we propose Morest, a model-based RESTful API testing technique that builds and maintains a dynamically updating RESTful-service Property Graph (RPG) to model the behaviors of RESTful-services and guide the call sequence generation. We empirically evaluated Morest and the results demonstrate that Morest can successfully request an average of 152.66%-232.45% more API operations, cover 26.16%-103.24% more lines of code, and detect 40.64%-215.94% more bugs than state-of-the-art techniques. In total, we applied Morest to 6 real-world projects and found 44 bugs (13 of them cannot be detected by existing approaches). Specifically, 2 of the confirmed bugs are from Bitbucket, a famous code management service with more than 6 million users.

cs.SE↗

arXiv2020

MUZZ: Thread-aware Grey-box Fuzzing for Effective Bug Hunting in Multithreaded Programs

Grey-box fuzz testing has revealed thousands of vulnerabilities in real-world software owing to its lightweight instrumentation, fast coverage feedback, and dynamic adjusting strategies. However, directly applying grey-box fuzzing to input-dependent multithreaded programs can be extremely inefficient. In practice, multithreading-relevant bugs are usually buried in sophisticated program flows. Meanwhile, the existing grey-box fuzzing techniques do not stress thread-interleavings which affect execution states in multithreaded programs. Therefore, mainstream grey-box fuzzers cannot effectively test problematic segments in multithreaded programs despite they might obtain high code coverage statistics. To this end, we propose MUZZ, a new grey-box fuzzing technique that hunts for bugs in multithreaded programs. MUZZ owns three novel thread-aware instrumentations, namely coverage-oriented instrumentation, thread-context instrumentation, and schedule-intervention instrumentation. During fuzzing, these instrumentations engender runtime feedback to stress execution states caused by thread interleavings. By leveraging the feedback in the dynamic seed selection and execution strategies, MUZZ preserves more valuable seeds that expose bugs in a multithreading context. We evaluate MUZZ on 12 real-world software programs. Experiments show that MUZZ outperforms AFL in both multithreading-relevant seed generation and concurrency-vulnerability detection. Further, by replaying the target programs against the generated seeds, MUZZ also reveals more concurrency-bugs (e.g., data-races, thread-leaks) than AFL. In total, MUZZ detected 8 new concurrency-vulnerabilities and 19 new concurrency-bugs. At the time of writing, 4 CVE IDs have been assigned to the reported issues.

cs.SE↗

arXiv2020

An Empirical Study on Benchmarks of Artificial Software Vulnerabilities

Recently, various techniques (e.g., fuzzing) have been developed for vulnerability detection. To evaluate those techniques, the community has been developing benchmarks of artificial vulnerabilities because of a shortage of ground-truth. However, people have concerns that such vulnerabilities cannot represent reality and may lead to unreliable and misleading results. Unfortunately, there lacks research on handling such concerns. In this work, to understand how close these benchmarks mirror reality, we perform an empirical study on three artificial vulnerability benchmarks - LAVA-M, Rode0day and CGC (2669 bugs) and various real-world memory-corruption vulnerabilities (80 CVEs). Furthermore, we propose a model to depict the properties of memory-corruption vulnerabilities. Following this model, we conduct intensive experiments and data analyses. Our analytic results reveal that while artificial benchmarks attempt to approach the real world, they still significantly differ from reality. Based on the findings, we propose a set of strategies to improve the quality of artificial benchmarks.

cs.CR↗

arXiv2020

LEOPARD: Identifying Vulnerable Code for Vulnerability Assessment through Program Metrics

Identifying potentially vulnerable locations in a code base is critical as a pre-step for effective vulnerability assessment; i.e., it can greatly help security experts put their time and effort to where it is needed most. Metric-based and pattern-based methods have been presented for identifying vulnerable code. The former relies on machine learning and cannot work well due to the severe imbalance between non-vulnerable and vulnerable code or lack of features to characterize vulnerabilities. The latter needs the prior knowledge of known vulnerabilities and can only identify similar but not new types of vulnerabilities. In this paper, we propose and implement a generic, lightweight and extensible framework, LEOPARD, to identify potentially vulnerable functions through program metrics. LEOPARD requires no prior knowledge about known vulnerabilities. It has two steps by combining two sets of systematically derived metrics. First, it uses complexity metrics to group the functions in a target application into a set of bins. Then, it uses vulnerability metrics to rank the functions in each bin and identifies the top ones as potentially vulnerable. Our experimental results on 11 real-world projects have demonstrated that, LEOPARD can cover 74.0% of vulnerable functions by identifying 20% of functions as vulnerable and outperform machine learning-based and static analysis-based techniques. We further propose three applications of LEOPARD for manual code review and fuzzing, through which we discovered 22 new bugs in real applications like PHP, radare2 and FFmpeg, and eight of them are new vulnerabilities.

cs.SE↗