相关论文: Linking Common Vulnerabilities and Exposures to th…

Machine learning and Large language models (LLMs) for vulnerability detection has received significant attention in recent years. Unfortunately, state-of-the-art techniques show that LLMs are unsuccessful in even distinguishing the…

Cyber-defense systems are being developed to automatically ingest Cyber Threat Intelligence (CTI) that contains semi-structured data and/or text to populate knowledge graphs. A potential risk is that fake CTI can be generated and spread…

Peer-to-peer knowledge transfer in distributed environments has emerged as a promising method since it could accelerate learning and improve team-wide performance without relying on pre-trained teachers in deep reinforcement learning.…

The advent of Federated Learning (FL) as a distributed machine learning paradigm has introduced new cybersecurity challenges, notably adversarial attacks that threaten model integrity and participant privacy. This study proposes an…

Recent statements about the impressive capabilities of large language models (LLMs) are usually supported by evaluating on open-access benchmarks. Considering the vast size and wide-ranging sources of LLMs' training data, it could…

Text-to-image (T2I) diffusion models have achieved remarkable success in image synthesis, but their reliance on large-scale data and open ecosystems introduces serious backdoor security risks. Existing defenses, particularly input-level…

Vision Transformers (ViTs) have achieved strong performance in video action recognition, but their high computational cost limits their practicality. Lightweight CNNs are more efficient but suffer from accuracy gaps. Cross-Architecture…

Device driver isolation is a promising approach for protecting the kernel from faulty or malicious drivers, but the actual security provided by such frameworks is often not well understood. Recent research has identified Compartment…

Despite the substantial advancements in Vision-Language Pre-training (VLP) models, their susceptibility to adversarial attacks poses a significant challenge. Existing work rarely studies the transferability of attacks on VLP models,…

Graph knowledge models and ontologies are very powerful modeling and re asoning tools. We propose an effective approach to model network attacks and attack prediction which plays important roles in security management. The goals of this…

Platforms that support online commentary, from social networks to news sites, are increasingly leveraging machine learning to assist their moderation efforts. But this process does not typically provide feedback to the author that would…

Although large language models (LLMs) have achieved remarkable advancements, their security remains a pressing concern. One major threat is jailbreak attacks, where adversarial prompts bypass model safeguards to generate harmful or…

Adversarial attacks significantly threaten the robustness of deep neural networks (DNNs). Despite the multiple defensive methods employed, they are nevertheless vulnerable to poison attacks, where attackers meddle with the initial training…

Threat modeling for cyber-physical systems (CPS) remains a largely manual exercise. This project presents SMSI (System Model Security Inference), a hybrid neuro-symbolic pipeline that starts from a SysML architecture model and produces a…

Numerous self-supervised learning paradigms, such as contrastive learning and masked image modeling, have been proposed to acquire powerful and general representations from unlabeled data. However, these models are commonly pretrained…

Cyber Threat Intelligence (CTI) has emerged as a vital complementary approach that operates in the early phases of the cyber threat lifecycle. CTI involves collecting, processing, and analyzing threat data to provide a more accurate and…

Large Language Models (LLMs) have strong capabilities in code comprehension, but fine-tuning costs and semantic alignment issues limit their project-specific optimization; conversely, code models such CodeBERT are easy to fine-tune, but it…

Backdoor Attacks have been a serious vulnerability against Large Language Models (LLMs). However, previous methods only reveal such risk in specific models, or present tasks transferability after attacking the pre-trained phase. So, how…

Vision Transformers (ViTs) have emerged as state-of-the-art models for various vision tasks recently. However, their heavy computation costs remain daunting for resource-limited devices. To address this, researchers have dedicated…

Identifying vulnerabilities in source code is crucial, especially in critical software components. Existing methods such as static analysis, dynamic analysis, formal verification, and recently Large Language Models are widely used to detect…