Library fuzzing is essential for identifying vulnerabilities in software libraries. However, achieving high coverage remains challenging due to the difficulty of generating effective harness and seed inputs. We present LASGen, an automated framework that integrates static analysis and large language models (LLMs) to generate high-quality fuzzing inputs for arbitrary library functions. LASGen generates coupled harnesses and initial seeds, treating them as a unified task rather than separate steps. This design ensures the seeds are highly compatible with the harness, enabling deeper path exploration. To achieve this, LASGen extracts function-level context via slicing and data-flow analysis, then embeds it into structured prompts to guide LLMs during synthesis, ensuring that the outputs are valid. LASGen also incorporates a self-repair mechanism and seed validation loop to ensure correctness and effectiveness. Experiments on 11 libraries with 127 known vulnerabilities show that LASGen achieves 77.17% vulnerability coverage and 55.61% edge coverage, outperforming state-of-the-art fuzzers while maintaining a lower false-positive rate. When applied to 17 real-world libraries, LASGen discovered 33 previously unknown vulnerabilities, 26 of which have been confirmed and patched, including eight assigned CNVD IDs.

The rapid growth of the Internet of Things (IoT) has led to the widespread use of companion apps for device management. However, these apps expose a critical vulnerability in the IoT ecosystem: insufficient verification procedures during device firmware updates (DFU), often resulting in firmware leakage. Once leaked, the firmware reveals sensitive design details, creating a straightforward path for attackers to reverse-engineer devices. To address this issue, we designed an automated analysis tool called FirmProj. It systematically evaluates firmware leakage risks by examining IoT companion apps. FirmProj combines advanced static analysis techniques with large language models to identify DFU modules, extract firmware files, and detect security vulnerabilities. In a large-scale study involving 10,047 IoT companion apps, FirmProj successfully retrieved 3,434 firmware files, uncovering severe flaws in DFU implementations that can lead to firmware leakage. These findings resulted in the assignment of 35 CVE IDs. Our results highlight the urgent need to strengthen firmware protection mechanisms throughout the IoT ecosystem.

Graph Transformers (GTs) have emerged as a powerful paradigm for graph representation learning due to their ability to model diverse node interactions. However, existing GTs often rely on intricate architectural designs tailored to specific interactions, limiting their flexibly. To address this, we propose a unified hierarchical mask framework that reveals an underlying equivalence between model architecture and attention mask construction. This framework enables a consistent modeling paradigm by capturing diverse interactions through carefully designed attention masks. Theoretical analysis under this framework demonstrates that the probability of correct classification positively correlates with the receptive field size and label consistency, leading to a fundamental design principle: An effective attention mask should ensure both a sufficiently large receptive field and a high level of label consistency. While no single existing mask satisfies this principle across all scenarios, our analysis reveals that hierarchical masks offer complementary strengths—motivating their effective integration. Then, we introduce M$^3$Dphormer, a Mixture-of-Experts based Graph Transformer with Multi-Level Masking and Dual Attention Computation. M$^3$Dphormer incorporates three theoretically grounded hierarchical masks and employs a bi-level expert routing mechanism to adaptively integrate multi-level interaction information. To ensure scalability, we further introduce a dual attention computation scheme that dynamically switches between dense and sparse modes based on local mask sparsity. Extensive experiments across multiple benchmarks demonstrate that M$^3$Dphormer achieves state-of-the-art performance, validating the effectiveness of our unified framework and model design.

Graph neural networks (GNNs) have shown strong performance on graph-structured data but may inherit bias from training data, leading to discriminatory predictions based on sensitive attributes like gender and race. Existing fairness methods assume that training and testing data share the same distribution, but how fairness is affected under distribution shifts remains largely unexplored. To address this, we first identify theoretical factors that cause bias in graphs and explore how fairness is influenced by distribution shifts, particularly focusing on representation distances between groups in training and testing graphs. Based on this, we propose FatraGNN, which uses a graph generator to create biased graphs from different distributions and an alignment module to reduce representation distances for specific groups. This improves fairness and classification performance on unseen graphs. However, FatraGNN has limitations in generating realistic graphs and addressing group differentiation. To overcome these, we introduce AuCoGNN, which includes an automated graph generation module and a contrastive alignment mechanism. This ensures better fairness by maximizing the representation distance between the same certain groups while minimizing the representation distance between different groups. Experiments on real-world and semi-synthetic datasets demonstrate the effectiveness of both models in improving fairness and accuracy.

Monocular RGBD imaging, also known as simultaneous all-in-focus (AiF) imaging and monocular depth estimation (MDE), represents a significant yet challenging task in computer vision. The crux lies in devising optical coding techniques to maximize the modulation transfer function (MTF) across various depths while minimizing their cross-correlation, all while aligning with the capabilities of image processing algorithms. End-to-end design of optics and algorithms offers a promising avenue towards achieving this holistic objective, but these approaches require solving non-convex inverse problems with millions of parameters. In this paper, we introduce a lattice-focal shape capable of nearly achieving the MTF bound as an initial solution, followed by employing B-spline parameterization for surface geometry representation to reduce the number of optimization variables. Further integration with the Restormer-based neural network, which possesses a global perspective, achieves high-performance RGBD imaging quality. Compared against state-of-the-art monocular RGBD imaging methods, our proposed approach improves the imaging peak signal-to-noise ratio (PSNR) by 3.0 dB and reduces the depth mean absolute error (MAE) by 39%. Experiments in real indoor and outdoor scenes validate the effectiveness of our method. The proposed approach paves the way for the development of monocular RGBD imaging.

Graph Transformer, due to its global attention mechanism, has emerged as a new tool in dealing with graph-structured data. It is well recognized that the global attention mechanism considers a wider receptive field in a fully connected graph, leading many to believe that useful information can be extracted from all the nodes. In this paper, we challenge this belief: does the globalizing property always benefit Graph Transformers? We reveal the over-globalizing problem in Graph Transformer by presenting both empirical evidence and theoretical analysis, i.e., the current attention mechanism overly focuses on those distant nodes, while the near nodes, which actually contain most of the useful information, are relatively weakened. Then we propose a novel Bi-Level Global Graph Transformer with Collaborative Training (CoBFormer), including the inter-cluster and intra-cluster Transformers, to prevent the over-globalizing problem while keeping the ability to extract valuable information from distant nodes. Moreover, the collaborative training is proposed to improve the model's generalization ability with a theoretical guarantee. Extensive experiments on various graphs well validate the effectiveness of our proposed CoBFormer.

Graph neural networks (GNNs) have achieved remarkable performance on graph-structured data. However, GNNs may inherit prejudice from the training data and make discriminatory predictions based on sensitive attributes, such as gender and race. Recently, there has been an increasing interest in ensuring fairness on GNNs, but all of them are under the assumption that the training and testing data are under the same distribution, i.e., training data and testing data are from the same graph. Will graph fairness performance decrease under distribution shifts? How does distribution shifts affect graph fairness learning? All these open questions are largely unexplored from a theoretical perspective. To answer these questions, we first theoretically identify the factors that determine bias on a graph. Subsequently, we explore the factors influencing fairness on testing graphs, with a noteworthy factor being the representation distances of certain groups between the training and testing graph. Motivated by our theoretical analysis, we propose our framework FatraGNN. Specifically, to guarantee fairness performance on unknown testing graphs, we propose a graph generator to produce numerous graphs with significant bias and under different distributions. Then we minimize the representation distances for each certain group between the training graph and generated graphs. This empowers our model to achieve high classification and fairness performance even on generated graphs with significant bias, thereby effectively handling unknown testing graphs. Experiments on real-world and semi-synthetic datasets demonstrate the effectiveness of our model in terms of both accuracy and fairness.

Stylistic variation is critical to render the utterances generated by conversational agents natural and engaging.In this paper, we focus on sequence-to-sequence models for open-domain dialogue response generation and propose a new method to evaluate the extent to which such models are able to generate responses that reflect different personality traits.