相关论文: PMANet: Malicious URL detection via post-trained l…

Social media platforms enable instant and ubiquitous connectivity and are essential to social interaction and communication in our technological society. Apart from its advantages, these platforms have given rise to negative behaviors in…

Cultural context profoundly shapes how people interpret online content, yet vision-language models (VLMs) remain predominantly trained through Western or English-centric lenses. This limits their fairness and cross-cultural robustness in…

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…

In evolving cyber landscapes, the detection of malicious URLs calls for cooperation and knowledge sharing across domains. However, collaboration is often hindered by concerns over privacy and business sensitivities. Federated learning…

Cybersecurity information is often technically complex and relayed through unstructured text, making automation of cyber threat intelligence highly challenging. For such text domains that involve high levels of expertise, pretraining on…

The widespread accessibility of the Internet has led to a surge in online fraudulent activities, underscoring the necessity of shielding users' sensitive information from cybercriminals. Phishing, a well-known cyberattack, revolves around…

The cyber-threat landscape has evolved tremendously in recent years, with new threat variants emerging daily, and large-scale coordinated campaigns becoming more prevalent. In this study, we propose CELEST (CollaborativE LEarning for…

Detecting hate speech and offensive language is essential for maintaining a safe and respectful digital environment. This study examines the limitations of state-of-the-art large language models (LLMs) in identifying offensive content…

Large Language Models (LLMs) are increasingly susceptible to jailbreak attacks, which are adversarial prompts that bypass alignment constraints and induce unauthorized or harmful behaviors. These vulnerabilities undermine the safety,…

Pre-trained neural language models bring significant improvement for various NLP tasks, by fine-tuning the models on task-specific training sets. During fine-tuning, the parameters are initialized from pre-trained models directly, which…

The growing cybersecurity threats make it essential to use high-quality data to train Machine Learning (ML) models for network traffic analysis, without noisy or missing data. By selecting the most relevant features for cyber-attack…

While scaling laws have been continuously validated in large language models (LLMs) with increasing model parameters, the inherent tension between the inference demands of LLMs and the limited resources of edge devices poses a critical…

Language models trained on large-scale unfiltered datasets curated from the open web acquire systemic biases, prejudices, and harmful views from their training data. We present a methodology for programmatically identifying and removing…

In the field of natural language processing, the prevalent approach involves fine-tuning pretrained language models (PLMs) using local samples. Recent research has exposed the susceptibility of PLMs to backdoor attacks, wherein the…

Large-scale pre-trained models such as CodeBERT, GraphCodeBERT have earned widespread attention from both academia and industry. Attributed to the superior ability in code representation, they have been further applied in multiple…

Many of today's machine learning (ML) systems are built by reusing an array of, often pre-trained, primitive models, each fulfilling distinct functionality (e.g., feature extraction). The increasing use of primitive models significantly…

The prevalence of memes on social media has created the need to sentiment analyze their underlying meanings for censoring harmful content. Meme censoring systems by machine learning raise the need for a semi-supervised learning solution to…

Discriminative pre-trained language models (PLMs) learn to predict original texts from intentionally corrupted ones. Taking the former text as positive and the latter as negative samples, the PLM can be trained effectively for…

Continual pre-training has been urgent for adapting a pre-trained model to a multitude of domains and tasks in the fast-evolving world. In practice, a continually pre-trained model is expected to demonstrate not only greater capacity when…

Hate speech detection on Chinese social networks presents distinct challenges, particularly due to the widespread use of cloaking techniques designed to evade conventional text-based detection systems. Although large language models (LLMs)…