21 citations · 30 across the 8 of their papers we have counts for
10 papers · 1 filter
Misleading the Planner through Deceptive Resumes: Registration-Time Injection in Centralized Multi-Agent Systems
Zhaofeng Yu, Haokai Ma, Dongyang Zhan +3
A centralized LLM-based multi-agent system (MAS) extends its functionality by registering new worker agents, whose descriptions are read by the planner to decide how a task is deco…
Securing Operating Systems Through Fine-grained Kernel Access Limitation for IoT Systems
Dongyang Zhan, Zhaofeng Yu, Xiangzhan Yu +3
With the development of Internet of Things (IoT), it is gaining a lot of attention. It is important to secure the embedded systems with low overhead. The Linux Seccomp is widely us…
Shrinking the Kernel Attack Surface Through Static and Dynamic Syscall Limitation
Dongyang Zhan, Zhaofeng Yu, Xiangzhan Yu +2
Linux Seccomp is widely used by the program developers and the system maintainers to secure the operating systems, which can block unused syscalls for different applications and co…
A High-performance Real-time Container File Monitoring Approach Based on Virtual Machine Introspection
Kai Tan, Dongyang Zhan, Lin Ye +3
As cloud computing continues to advance and become an integral part of modern IT infrastructure, container security has emerged as a critical factor in ensuring the smooth operatio…
An Adversarial Robust Behavior Sequence Anomaly Detection Approach Based on Critical Behavior Unit Learning
Dongyang Zhan, Kai Tan, Lin Ye +3
Sequential deep learning models (e.g., RNN and LSTM) can learn the sequence features of software behaviors, such as API or syscall sequences. However, recent studies have shown tha…
A Practical Adversarial Attack against Sequence-based Deep Learning Malware Classifiers
Kai Tan, Dongyang Zhan, Lin Ye +2
Sequence-based deep learning models (e.g., RNNs), can detect malware by analyzing its behavioral sequences. Meanwhile, these models are susceptible to adversarial attacks. Attacker…