相关论文: IntelliRadar: A Comprehensive Platform to Pinpoint…

Multimodal Large Language Models (MLLMs) achieve strong reasoning and perception capabilities but are increasingly vulnerable to jailbreak attacks. While existing work focuses on explicit attacks, where malicious content resides in a single…

Owing to recorded incidents of Information technology inclined organisations failing to respond effectively to threat incidents, this project outlines the benefits of conducting a comprehensive risk assessment which would aid proficiency in…

This paper presents a preliminary validation of common textual information retrieval techniques for mapping unstructured software vulnerability information to distinct software weaknesses. The validation is carried out with a dataset…

Modern machine learning (ML) systems demand substantial training data, often resorting to external sources. Nevertheless, this practice renders them vulnerable to backdoor poisoning attacks. Prior backdoor defense strategies have primarily…

Malware represents a significant security concern in today's digital landscape, as it can destroy or disable operating systems, steal sensitive user information, and occupy valuable disk space. However, current malware detection methods,…

LLM-based code interpreter agents are increasingly deployed in critical workflows, yet their robustness against risks introduced by their code execution capabilities remains underexplored. Existing benchmarks are limited to static datasets…

With the advent of large language models (LLMs), numerous software service providers (SSPs) are dedicated to developing LLMs customized for code generation tasks, such as CodeLlama and Copilot. However, these LLMs can be leveraged by…

Malicious software, or malware, presents a continuously evolving challenge in computer security. These embedded snippets of code in the form of malicious files or hidden within legitimate files cause a major risk to systems with their…

Performance issues in software-defined network (SDN) controllers can have serious impacts on the performance and availability of networks. In this paper, we consider a special class of SDN vulnerabilities called stateful performance issues…

Cyber Threat Intelligence (CTI) summarization involves generating concise and accurate highlights from web intelligence data, which is critical for providing decision-makers with actionable insights to swiftly detect and respond to cyber…

We present and evaluate a large-scale malware detection system integrating machine learning with expert reviewers, treating reviewers as a limited labeling resource. We demonstrate that even in small numbers, reviewers can vastly improve…

Software-Defined Networks have seen an increasing in their deployment because they offer better network manageability compared to traditional networks. Despite their immense success and popularity, various security issues in SDN remain open…

Existing research on malware classification focuses almost exclusively on two tasks: distinguishing between malicious and benign files and classifying malware by family. However, malware can be categorized according to many other types of…

Existing malicious code detection techniques demand the integration of multiple tools to detect different malware patterns, often suffering from high misclassification rates. Therefore, malicious code detection techniques could be enhanced…

In recent years, networked IoT systems have revolutionized connectivity, portability, and functionality, offering a myriad of advantages. However, these systems are increasingly targeted by adversaries due to inherent security…

Small and medium sized businesses (SMBs) face an escalating cybersecurity threat landscape, yet most lack the resources to staff full Security Operations Centers (SOCs) or deploy enterprise grade detection platforms. This paper presents…

Split Learning (SL) has emerged as a practical and efficient alternative to traditional federated learning. While previous attempts to attack SL have often relied on overly strong assumptions or targeted easily exploitable models, we seek…

With the increasing usage of open-source software (OSS) components, vulnerabilities embedded within them are propagated to a huge number of underlying applications. In practice, the timely application of security patches in downstream…

AI control protocols use monitors to detect attacks by untrusted AI agents, but standard single-score monitors face two limitations: they miss subtle attacks where outputs look clean but reasoning is off, and they collapse to near-zero…

Automated drug discovery offers significant potential for accelerating the development of novel therapeutics by substituting labor-intensive human workflows with machine-driven processes. However, molecules generated by artificial…