English
Related papers

Related papers: Unveiling the Vulnerability of Graph-LLMs: An Inte…

200 papers

In network link prediction, it is possible to hide a target link from being predicted with a small perturbation on network structure. This observation may be exploited in many real world scenarios, for example, to preserve privacy, or to…

Social and Information Networks · Computer Science 2020-04-06 Jinyin Chen , Jian Zhang , Zhi Chen , Min Du , Qi Xuan

Node injection attacks on Graph Neural Networks (GNNs) have received increasing attention recently, due to their ability to degrade GNN performance with high attack success rates. However, our study indicates that these attacks often fail…

Machine Learning · Computer Science 2023-09-26 Shuchang Tao , Qi Cao , Huawei Shen , Yunfan Wu , Liang Hou , Fei Sun , Xueqi Cheng

Large Language Models (LLMs) are increasingly vulnerable to adversarial prompts that exploit semantic ambiguities to bypass safety mechanisms, resulting in harmful or inappropriate outputs. Such attacks, including jailbreaking and prompt…

Cryptography and Security · Computer Science 2026-05-28 Xiang Fang , Wanlong Fang

With the rapid development of artificial intelligence, a number of machine learning algorithms, such as graph neural networks have been proposed to facilitate network analysis or graph data mining. Although effective, recent studies show…

Social and Information Networks · Computer Science 2021-06-25 Junhao Zhu , Yalu Shan , Jinhuan Wang , Shanqing Yu , Guanrong Chen , Qi Xuan

The emergence of large-scale pre-trained language models has revolutionized various AI research domains. Transformers-based Large Language Models (LLMs) have gradually replaced CNNs and RNNs to unify fields of computer vision and natural…

Computation and Language · Computer Science 2024-02-07 Ruosong Ye , Caiqi Zhang , Runhui Wang , Shuyuan Xu , Yongfeng Zhang

The latest advancements in large language models (LLMs) have revolutionized the field of natural language processing (NLP). Inspired by the success of LLMs in NLP tasks, some recent work has begun investigating the potential of applying…

Artificial Intelligence · Computer Science 2025-02-25 Shengyin Sun , Yuxiang Ren , Jiehao Chen , Chen Ma

Recent studies have demonstrated that hypergraph neural networks (HGNNs) are susceptible to adversarial attacks. However, existing methods rely on the specific information mechanisms of target HGNNs, overlooking the common vulnerability…

Cryptography and Security · Computer Science 2025-11-17 Meixia He , Peican Zhu , Le Cheng , Yangming Guo , Manman Yuan , Keke Tang

Safety alignment of Large Language Models (LLMs) can be compromised with manual jailbreak attacks and (automatic) adversarial attacks. Recent studies suggest that defending against these attacks is possible: adversarial attacks generate…

Cryptography and Security · Computer Science 2023-12-15 Sicheng Zhu , Ruiyi Zhang , Bang An , Gang Wu , Joe Barrow , Zichao Wang , Furong Huang , Ani Nenkova , Tong Sun

The rapid development of Multimodal Large Language Models (MLLMs) has enabled the integration of multiple modalities, including texts and images, within the large language model (LLM) framework. However, texts and images are usually…

Artificial Intelligence · Computer Science 2025-03-11 Yi Fang , Bowen Jin , Jiacheng Shen , Sirui Ding , Qiaoyu Tan , Jiawei Han

Multimodal Large Language Models (MLLMs), built upon LLMs, have recently gained attention for their capabilities in image recognition and understanding. However, while MLLMs are vulnerable to adversarial attacks, the transferability of…

Computer Vision and Pattern Recognition · Computer Science 2025-02-28 Chenhe Gu , Jindong Gu , Andong Hua , Yao Qin

Large Language Models (LLMs) may suffer from hallucinations in real-world applications due to the lack of relevant knowledge. In contrast, knowledge graphs encompass extensive, multi-relational structures that store a vast array of symbolic…

Computation and Language · Computer Science 2024-09-06 Jie Ma , Zhitao Gao , Qi Chai , Wangchun Sun , Pinghui Wang , Hongbin Pei , Jing Tao , Lingyun Song , Jun Liu , Chen Zhang , Lizhen Cui

Vulnerability identification is crucial to protect software systems from attacks for cyber-security. However, huge projects have more than millions of lines of code, and the complex dependencies make it hard to carry out traditional static…

Cryptography and Security · Computer Science 2023-11-01 Shuo Liu , Gail Kaiser

The rapid integration of Large Language Models (LLMs) into Multi-Agent Systems (MAS) has significantly enhanced their collaborative problem-solving capabilities, but it has also expanded their attack surfaces, exposing them to…

Cryptography and Security · Computer Science 2026-04-29 Pablo Mateo-Torrejón , Alfonso Sánchez-Macián

Large language models~(LLM) like ChatGPT have become indispensable to artificial general intelligence~(AGI), demonstrating excellent performance in various natural language processing tasks. In the real world, graph data is ubiquitous and…

Artificial Intelligence · Computer Science 2023-07-12 Jiayan Guo , Lun Du , Hengyu Liu , Mengyu Zhou , Xinyi He , Shi Han

The widespread use of pre-trained language models (PLMs) in natural language processing (NLP) has greatly improved performance outcomes. However, these models' vulnerability to adversarial attacks (e.g., camouflaged hints from drug…

Computation and Language · Computer Science 2024-04-19 Zi Xiong , Lizhi Qing , Yangyang Kang , Jiawei Liu , Hongsong Li , Changlong Sun , Xiaozhong Liu , Wei Lu

Graphs are commonly used to model complex networks prevalent in modern social media and literacy applications. Our research investigates the vulnerability of these graphs through the application of feature based adversarial attacks,…

Social and Information Networks · Computer Science 2024-03-06 Ying Xu , Michael Lanier , Anindya Sarkar , Yevgeniy Vorobeychik

Graph neural networks (GNNs) which apply the deep neural networks to graph data have achieved significant performance for the task of semi-supervised node classification. However, only few work has addressed the adversarial robustness of…

Machine Learning · Computer Science 2019-10-16 Kaidi Xu , Hongge Chen , Sijia Liu , Pin-Yu Chen , Tsui-Wei Weng , Mingyi Hong , Xue Lin

Heterogeneous Graph Neural Networks (HGNNs) are increasingly recognized for their performance in areas like the web and e-commerce, where resilience against adversarial attacks is crucial. However, existing adversarial attack methods, which…

Machine Learning · Computer Science 2024-01-19 He Zhao , Zhiwei Zeng , Yongwei Wang , Deheng Ye , Chunyan Miao

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by retrieving external data to mitigate hallucinations and outdated knowledge issues. Benefiting from the strong ability in facilitating diverse data sources and…

Cryptography and Security · Computer Science 2025-07-15 Tianzhe Zhao , Jiaoyan Chen , Yanchi Ru , Haiping Zhu , Nan Hu , Jun Liu , Qika Lin

Graph Neural Networks (GNNs) have become a cornerstone in graph-based data analysis, with applications in diverse domains such as bioinformatics, social networks, and recommendation systems. However, the interplay between model…

Machine Learning · Computer Science 2025-05-06 Kirill Lukyanov , Georgii Sazonov , Serafim Boyarsky , Ilya Makarov