In real-world applications, graph data has garnered significant attention for its representation and analysis using Graph Neural Networks. Recent advancements have led to the development of Graph Foundation Models (GFMs), which aim to enhance cross-domain and cross-task generalization ability. Despite promising results from GFMs, a lack of standardized evaluation processes hinders comparative analysis and cross-domain applicability. To address this gap, we propose GFMBench, an open-source pipeline that standardizes the training, evaluation, and deployment of GFMs across diverse real-world graph applications. GFMBench integrates state-of-the-art GFMs and datasets, providing a modular design for comprehensive support across data preprocessing, model training, and evaluation. The pipeline includes a robust evaluation framework for benchmarking GFM generalization ability, encompassing supervised learning, cross-domain zero-shot and few-shot learning, and in-context learning. To validate the usability of GFMs, we deploy them on the Open Academic Graph, enabling applications such as topic search and author recommendation. This work provides a unified benchmark for GFMs, enabling deeper insights into their generalization ability across various graph tasks and domains. We further open-source GFMBench https://github.com/BUPT-GAMMA/ggfm and related documents https://ggfm.readthedocs.io/en/latest/.

Recommender systems (RSs) are designed to retrieve candidate items a user might be interested in from a large pool, with a typical approach being the use of graph neural networks (GNNs) to capture high-order interaction relationships. As large language models (LLMs) have demonstrated remarkable success across various domains, researchers are exploring ways to apply their capabilities for improving recommendation performance. However, existing work limits the use of LLMs to either re-ranking recommendation results of traditional RSs or pre-processing the datasets as data augmenters. Both lines of work failed to explore LLMs' capabilities during the filtering process of candidate items, which may lead to suboptimal performance. Instead, we propose to leverage LLMs' reasoning abilities during the candidate filtering process, and introduce Chain Of Retrieval ON grAphs (CORONA) to progressively narrow down the range of candidate items on interaction graphs with the help of LLMs: (1) First, LLM performs preference reasoning based on user profiles, with the response serving as a query to extract relevant users and items from the interaction graph as preference-assisted retrieval ; (2) Then, using the information retrieved in the previous step along with the purchase history of target user, LLM conducts intent reasoning to help refine an even smaller interaction subgraph as intent-assisted retrieval ; (3) Finally, we employ a GNN to capture high-order collaborative filtering information from the extracted subgraph, performing GNN-enhanced retrieval to generate the final recommendation results. The proposed framework leverages the reasoning capabilities of LLMs during the retrieval process, while seamlessly integrating GNNs to enhance overall recommendation performance. Extensive experiments on various datasets and settings demonstrate that our proposed CORONA achieves state-of-the-art (SOTA) performance with an 18.6% relative improvement in recall and an 18.4% relative improvement in NDCG on average. Our code is available on GitHub at https://github.com/BUPT-GAMMA/CORONA.

For DDoS attacks, Moving Target Defense (MTD) has emerged as a promising solution. However, existing MTD defense systems often overlook the issue of user access. In this paper, we implement a hierarchical Proof of Work (PoW) authentication mechanism for user access in a shuffling-based proxy-switching MTD system. Our mechanism integrates the PoW authentication with the proxy cluster architecture and dynamically adjusts the difficulty level of PoW based on information from multiple proxies. The mechanism was deployed on a real MTD defense system for performance evaluation. By adapting the PoW scheduling approach for MTD systems, the experimental results demonstrate that our mechanism can adapt to and leverage dynamic network structures. In terms of mitigating DDoS attacks and ensuring user experience, it shows improvements compared to directly migrating traditional methods.