15 papers · ranked by Valyu relevance
Zhengbin Zou, Tao Jiang, Yizheng Wang, Tiancheng Xue + 2 more
The increasing complexity of software systems has rendered code vulnerability detection a critical aspect of software security. While deep learning-based approaches have advanced this field, challenges such as coarse-grained function-level detection, scalability limitations, and constrained accuracy persist. Although…
Christian Santamaria, Felipe Grijalva, Karen Rosero, José Vega-Sánchez + 3 more
Sound Event Localization and Detection (SELD) integrates Sound Event Detection (SED) and Direction-of-Arrival Estimation (DOAE) to recognize and localize sound events in various applications, including urban sound sensing, wildlife monitoring, and home surveillance. Recently, advancements in machine learning…
Hossein Rafieizadeh, Hadi Zare, Mohsen Ghassemi Parsa, Hocine Cherifi + 1 more
Anomaly detection in attributed networks is critical for identifying threats such as financial fraud and intrusions across social, e-commerce, and cyber-physical domains. Existing graph-based methods face two limitations: (i) embedding-based approaches obscure fine-grained structural and attribute patterns, and (ii)…
Oleksandr Fedoruk, Konrad Klimaszewski, Michał Kruk, Steve Ling
Generative adversarial networks (GANs) typically require large datasets for effective training, which poses challenges for volumetric medical imaging tasks where data are scarce. This study addresses this limitation by extending adaptive discriminator augmentation (ADA) for three-dimensional (3D) StyleGAN2 to improve…
Ming-Feng Yeh, Ching-Chuan Luo, Cheng-Lin Lu, Nianbo Liu
Smart manufacturing relies on programmable logic controllers (PLCs) that translate sensor inputs into actuator commands. Generating PLC programs in legacy textual languages such as Mitsubishi FX-series Instruction List (IL) remains an expert-only task, and IL’s deprecation in IEC 61131-3 Edition 3.0 leaves it…
Tongcheng Geng, Muhammad Ahsan
Deep code models face security vulnerabilities through backdoor attacks. Previous approaches have primarily relied on single-trigger mechanisms, resulting in limited stealth and vulnerability to defense strategies. This paper proposes a novel hybrid backdoor attack method that combines function signature features and…
Adrien Mialland, Shuzo Fukunaga, Riku Katsuki, Yunfei Dong + 3 more
Understanding the relationship between protein sequence and function is central to protein engineering. Mapping this relationship accurately enables the rational design of proteins with novel or enhanced functions and supports the interpretation of mutations in both natural and engineered contexts (). In this setting…
Mingqi Wang, Yu Yang, Minna Gao, Jinliang Yuan + 2 more
Class imbalance remains a major obstacle to reliable network intrusion detection, particularly in Internet of Things (IoT) and sensor-network monitoring scenarios where rare attack categories are represented by only a small number of high-dimensional traffic samples. To improve minority-class augmentation, we propose…
Guanglong Sun, Ning Huang, Hongwei Yan, Jun Zhou + 4 more
Title: Summary Generalization is a fundamental criterion for evaluating learning effectiveness, a domain where biological intelligence excels yet artificial intelligence faces challenges. In biological learning and memory, the well-documented spacing effect shows that appropriately spaced intervals between learning…
Kees Schouhamer Immink, Jos H. Weber, Tuan Thanh Nguyen, Kui Cai + 2 more
The design of low-complexity and efficient constrained codes has been a major research item for many years. This paper reports on a versatile method named concatenated constrained codes for designing efficient fixed-length constrained codes with small complexity. A concatenated constrained code comprises two (or more)…
Peter E. Blöchl, Robert Schade, Lukas Allen-Rump, Sangeeta Rajpurohit + 4 more
from a User’s Perspective Authors: Peter E. Blöchl, Robert Schade, Lukas Allen-Rump, Sangeeta Rajpurohit, Amrith Rathnakaran, Konstantin Tamoev, Mani Lokamani, Thomas D. Kühne CP-PAW is a combined electronic structure and ab initio molecular dynamics code to perform mixed quantum and classical simulations of atomistic…
GyeongTaek Choi, Seungho Jeon
WebAssembly is a low-level binary format originally designed to enable high-performance applications to run in web browsers. As WebAssembly is increasingly being ported to various environments, the security verification of WebAssembly execution environments is becoming more critical. While a wide variety of WebAssembly…
Matthew H. Iveson, Emily L. Ball, Chris Wai Hang Lo, Matúš Falis + 2 more
Background Many people with depression do not respond well to the first antidepressant prescribed. Treatment Resistant Depression (TRD) refers to depression which does not respond to multiple subsequent antidepressant treatments. Identifying TRD in routinely-collected health records is challenging due to limited…
Kiran Nair, Hubert Cecotti
Non-invasive Brain-Computer Interfaces (BCIs) based on Code-Modulated Visual Evoked Potentials (C-VEPs) require highly robust decoding methods to address temporal variability and session-dependent noise in EEG signals. This study proposes and evaluates several deep learning architectures, including convolutional neural…
Aswathi Shiju, Samantha D. M. Arras, Allen G. Rodrigo, Anthony M. Poole + 1 more
In biology, changes to a DNA sequence can impact protein sequence but changes to protein sequences (phenotype) do not flow back into DNA (genotype). A system with bidirectional information flow (i.e., both translation and ‘reverse translation’) remains a theoretical possibility for an independent origin of life or an…