Related papers: PrediQL: Automated Testing of GraphQL APIs with LL…

Large Language Models (LLMs) have demonstrated exceptional progress in multiple domains of software engineering including software vulnerability detection. Using LLMs to automate vulnerability detection in the wild is an important and…

Deep learning (DL) systems are increasingly applied to safety-critical domains such as autonomous driving cars. It is of significant importance to ensure the reliability and robustness of DL systems. Existing testing methodologies always…

Improving the general capabilities of large language models (LLMs) is an active research topic. As a common data structure in many real-world domains, understanding graph data is a crucial part of advancing general intelligence. To this…

LLM-based (Large Language Model) fuzz driver generation is a promising research area. Unlike traditional program analysis-based method, this text-based approach is more general and capable of harnessing a variety of API usage information,…

We propose a scalable and cost-efficient framework for deploying Graph-based Retrieval-Augmented Generation (GraphRAG) in enterprise environments. While GraphRAG has shown promise for multi- hop reasoning and structured retrieval, its…

Large language models (LLMs) have demonstrated their strong capabilities in various domains, and have been recently integrated for graph analysis as graph language models (GLMs). With LLMs as the predictor, some GLMs can interpret unseen…

In large-scale recommender systems, ultra-long user behavior sequences encode rich signals of evolving interests. Extending sequence length generally improves accuracy, but directly modeling such sequences in production is infeasible due to…

Automated vulnerability detection is a fundamental task in software security, yet existing learning-based methods still struggle to capture the structural dependencies, domain-specific vulnerability knowledge, and complex program semantics…

Large language models have gained widespread prominence, yet their vulnerability to prompt injection and other adversarial attacks remains a critical concern. This paper argues for a security-by-design AI paradigm that proactively mitigates…

Fuzzing is a technique of finding bugs by executing a software recurrently with a large number of abnormal inputs. Most of the existing fuzzers consider all parts of a software equally, and pay too much attention on how to improve the code…

Jailbreaking in Large Language Models (LLMs) threatens their safe use in sensitive domains like education by allowing users to bypass ethical safeguards. This study focuses on detecting jailbreaks in 2-Sigma, a clinical education platform…

GraphRAG-Causal introduces an innovative framework that combines graph-based retrieval with large language models to enhance causal reasoning in news analysis. Traditional NLP approaches often struggle with identifying complex, implicit…

Loop vulnerabilities are one major risky construct in software development. They can easily lead to infinite loops or executions, exhaust resources, or introduce logical errors that degrade performance and compromise security. The problem…

Recent advances in Large Language Models (LLMs) enable exciting LLM-integrated applications, which perform text-based tasks by utilizing their advanced language understanding capabilities. However, as LLMs have improved, so have the attacks…

Large Language Models (LLMs) increasingly rely on agentic capabilities-iterative retrieval, tool use, and decision-making-to overcome the limits of static, parametric knowledge. Yet existing agentic frameworks treat external information as…

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…

Large language models are increasingly used for vulnerability detection, yet their reliability under different prompt formulations remains uncharacterized. We present PromptAudit, a controlled evaluation framework that isolates prompt…

Large Language Models (LLMs) exhibit strong reasoning capabilities on structured tasks, yet the internal mechanisms underlying such behaviors remain poorly understood. Existing interpretation methods mainly focus on token-level…

Although Large Language Models (LLMs) have demonstrated potential in processing graphs, they struggle with comprehending graphical structure information through prompts of graph description sequences, especially as the graph size increases.…

Forecasting future links is a central task in temporal graph (TG) reasoning, requiring models to leverage historical interactions to predict upcoming ones. Traditional neural approaches, such as temporal graph neural networks, achieve…