Large language models (LLMs) have revolutionized language processing, but face critical challenges with security, privacy, and generating hallucinations — coherent but factually inaccurate outputs. A major issue is fact-conflicting hallucination (FCH), where LLMs produce content contradicting ground truth facts. Addressing FCH is difficult due to two key challenges: 1) Automatically constructing and updating benchmark datasets is hard, as existing methods rely on manually curated static benchmarks that cannot cover the broad, evolving spectrum of FCH cases. 2) Validating the reasoning behind LLM outputs is inherently difficult, especially for complex logical relations. To tackle these challenges, we introduce a novel logic-programming-aided metamorphic testing technique for FCH detection. We develop an extensive and extensible framework that constructs a comprehensive factual knowledge base by crawling sources like Wikipedia, seamlessly integrated into D rowzee . Using logical reasoning rules, we transform and augment this knowledge into a large set of test cases with ground truth answers. We test LLMs on these cases through template-based prompts, requiring them to provide reasoned answers. To validate their reasoning, we propose two semantic-aware oracles that assess the similarity between the semantic structures of the LLM answers and ground truth. Our approach automatically generates useful test cases and identifies hallucinations across six LLMs within nine domains, with hallucination rates ranging from 24.7% to 59.8%. Key findings include LLMs struggling with temporal concepts, out-of-distribution knowledge, and lack of logical reasoning capabilities. The results show that logic-based test cases generated by D rowzee effectively trigger and detect hallucinations. To further mitigate the identified FCHs, we explored model editing techniques, which proved effective on a small scale (with edits to fewer than 1000 knowledge pieces). Our findings emphasize the need for continued community efforts to detect and mitigate model hallucinations.

Machine learning and its promising branch deep learning have proven to be effective in a wide range of application domains. Recently, several efforts have shown success in applying deep learning techniques for automatic vulnerability discovery, as alternatives to traditional static bug detection. In principle, these learning-based approaches are built on top of classification models using supervised learning. Depending on the different granularities to detect vulnerabilities, these approaches rely on learning models which are typically trained with well-labeled source code to predict whether a program method, a program slice, or a particular code line contains a vulnerability or not. The effectiveness of these models is normally evaluated against conventional metrics including precision, recall and F1 score. In this paper, we show that despite yielding promising numbers, the above evaluation strategy can be insufficient and even misleading when evaluating the effectiveness of current learning-based approaches. This is because the underlying learning models only produce the classification results or report individual/isolated program statements, but are unable to pinpoint bug-triggering paths, which is an effective way for bug fixing and the main aim of static bug detection. Our key insight is that a program method or statement can only be stated as vulnerable in the context of a bug-triggering path. In this work, we systematically study the gap between recent learning-based approaches and conventional static bug detectors in terms of fine-grained metrics called BTP metrics using bug-triggering paths. We then characterize and compare the quality of the prediction results of existing learning-based detectors under different granularities. Finally, our comprehensive empirical study reveals several key issues and challenges in developing classification models to pinpoint bug-triggering paths and calls for more advanced learning-based bug detection techniques.

Software system complexity and security vulnerability diversity are plausible sources of the persistent challenges in software vulnerability research. Applying deep learning methods for automatic vulnerability detection has been proven an effective means to complement traditional detection approaches. Unfortunately, lacking well-qualified benchmark datasets could critically restrict the effectiveness of deep learning-based vulnerability detection techniques. Specifically, the long-term existence of erroneous labels in the existing vulnerability datasets may lead to inaccurate, biased, and even flawed results.

In the face of increased threats within software registries and management systems, we address the critical need for effective malicious code detection. In this paper, we propose an innovative approach that integrates source code slicing, inter-procedural analysis, and cross-file inter-procedural analysis, thereby enhancing the detection precision and reducing false positives. This approach has been encapsulated within a multi-analysis-based framework for automatic detection of malicious code in real-world software packages. In its application to major third-party software registries like PyPI and NPM, our framework has proven effective, identifying 130 malicious packages from a total of 169,640 monitored over a continuous period of five weeks. This work advances the current state-of-the-art solution to malicious code detection, demonstrating significant practical impact in strengthening the software supply chain defense.