Related papers: BEACON: Behavioral Malware Classification with Lar…

The awareness and mitigation of biases are of fundamental importance for the fair and transparent use of contextual language models, yet they crucially depend on the accurate detection of biases as a precursor. Consequently, numerous bias…

Autonomous control systems face significant challenges in performing complex tasks in the presence of latent risks. To address this, we propose an integrated framework that combines Large Language Models (LLMs), numerical optimization, and…

Malware still constitutes a major threat in the cybersecurity landscape, also due to the widespread use of infection vectors such as documents. These infection vectors hide embedded malicious code to the victim users, facilitating the use…

Machine-learning models have been recently used for detecting malicious Android applications, reporting impressive performances on benchmark datasets, even when trained only on features statically extracted from the application, such as…

Learning-based bug detectors promise to find bugs in large code bases by exploiting natural hints such as names of variables and functions or comments. Still, existing techniques tend to underperform when presented with realistic bugs. We…

Code metamorphism refers to a computer programming exercise wherein the program modifies its own code (partial or entire) consistently and automatically while retaining its core functionality. This technique is often used for online…

With the rapid growth of the number of devices on the Internet, malware poses a threat not only to the affected devices but also their ability to use said devices to launch attacks on the Internet ecosystem. Rapid malware classification is…

The widespread adoption of Large Language Models (LLMs) in critical applications has introduced severe reliability and security risks, as LLMs remain vulnerable to notorious threats such as hallucinations, jailbreak attacks, and backdoor…

Deep convolutional neural networks (CNNs) can be applied to malware binary detection via image classification. The performance, however, is degraded due to the imbalance of malware families (classes). To mitigate this issue, we propose a…

Software logs generated by sophisticated network emulators in the telecommunications industry, such as VIAVI TM500, are extremely complex, often comprising tens of thousands of text lines with minimal resemblance to natural language. Only…

Despite extensive alignment efforts, Large Vision-Language Models (LVLMs) remain vulnerable to jailbreak attacks, posing serious safety risks. To address this, existing detection methods either learn attack-specific parameters, which…

In recent years, malware becomes more threatening. Concerning the increasing malware variants, there comes Machine Learning (ML)-based and Deep Learning (DL)-based approaches for heuristic detection. Nevertheless, the prediction accuracy of…

Multimodal large language models (MLLMs) have achieved remarkable success in vision-language tasks, but their reliance on vast, internet-sourced data raises significant privacy and security concerns. Machine unlearning (MU) has emerged as a…

Repackaging is a technique that has been increasingly adopted by authors of Android malware. The main problem facing the research community working on devising techniques to detect this breed of malware is the lack of ground truth that…

With the rapid evolution of Android applications, traditional machine learning-based detection models suffer from concept drift. Additionally, they are constrained by shallow features, lacking deep semantic understanding and…

In the Bag-of-Words (BoW) model based image retrieval task, the precision of visual matching plays a critical role in improving retrieval performance. Conventionally, local cues of a keypoint are employed. However, such strategy does not…

Research into AI alignment has grown considerably since the recent introduction of increasingly capable Large Language Models (LLMs). Unfortunately, modern methods of alignment still fail to fully prevent harmful responses when models are…

Recent studies have revealed a security threat to natural language processing (NLP) models, called the Backdoor Attack. Victim models can maintain competitive performance on clean samples while behaving abnormally on samples with a specific…

The widespread distribution of Large Language Models (LLMs) through public platforms like Hugging Face introduces significant security challenges. While these platforms perform basic security scans, they often fail to detect subtle…

Multimodal Large Language Models (MLLMs) show impressive vision-language benchmark performance, yet growing concerns about data contamination (test set exposure during training) risk masking true generalization. This concern extends to…