Zobrazeno 1 - 10
of 4 382
pro vyhledávání: '"He Kun"'
Although vision-language pre-training (VLP) models have achieved remarkable progress on cross-modal tasks, they remain vulnerable to adversarial attacks. Using data augmentation and cross-modal interactions to generate transferable adversarial exampl
Externí odkaz:
http://arxiv.org/abs/2409.06726
Autor:
Li, Qiao, Wu, Cong, Chen, Jing, Zhang, Zijun, He, Kun, Du, Ruiying, Wang, Xinxin, Zhao, Qingchuang, Liu, Yang
Deep neural networks (DNNs) are increasingly used in critical applications such as identity authentication and autonomous driving, where robustness against adversarial attacks is crucial. These attacks can exploit minor perturbations to cause signifi
Externí odkaz:
http://arxiv.org/abs/2408.10647
Autor:
Liang, Ruichao, Chen, Jing, Wu, Cong, He, Kun, Wu, Yueming, Cao, Ruochen, Du, Ruiying, Liu, Yang, Zhao, Ziming
Smart contracts, the cornerstone of decentralized applications, have become increasingly prominent in revolutionizing the digital landscape. However, vulnerabilities in smart contracts pose great risks to user assets and undermine overall trust in de
Externí odkaz:
http://arxiv.org/abs/2408.10116
Recent studies emphasize the crucial role of data augmentation in enhancing the performance of object detection models. However,existing methodologies often struggle to effectively harmonize dataset diversity with semantic coordination.To bridge this
Externí odkaz:
http://arxiv.org/abs/2408.02891
Humans exhibit remarkable proficiency in visual classification tasks, accurately recognizing and classifying new images with minimal examples. This ability is attributed to their capacity to focus on details and identify common features between previ
Externí odkaz:
http://arxiv.org/abs/2408.01427
For an integer $b\ge 0$, a $b$-matching in a graph $G=(V,E)$ is a set $S\subseteq E$ such that each vertex $v\in V$ is incident to at most $b$ edges in $S$. We design a fully polynomial-time approximation scheme (FPTAS) for counting the number of $b$
Externí odkaz:
http://arxiv.org/abs/2407.04989
While tokenized graph Transformers have demonstrated strong performance in node classification tasks, their reliance on a limited subset of nodes with high similarity scores for constructing token sequences overlooks valuable information from other n
Externí odkaz:
http://arxiv.org/abs/2406.19258
Recently, the emerging graph Transformers have made significant advancements for node classification on graphs. In most graph Transformers, a crucial step involves transforming the input graph into token sequences as the model input, enabling Transfo
Externí odkaz:
http://arxiv.org/abs/2406.19249
Autor:
Liang, Ruichao, Chen, Jing, Wu, Cong, He, Kun, Wu, Yueming, Sun, Weisong, Du, Ruiying, Zhao, Qingchuan, Liu, Yang
Ponzi schemes, a form of scam, have been discovered in Ethereum smart contracts in recent years, causing massive financial losses. Existing detection methods primarily focus on rule-based approaches and machine learning techniques that utilize static
Externí odkaz:
http://arxiv.org/abs/2406.00921
The advent of Vision Transformers (ViTs) marks a substantial paradigm shift in the realm of computer vision. ViTs capture the global information of images through self-attention modules, which perform dot product computations among patchified image t
Externí odkaz:
http://arxiv.org/abs/2406.00427