Related papers: Classifying Web Exploits with Topic Modeling

Reward hacking, where a reasoning model exploits loopholes in a reward function to achieve high rewards without solving the intended task, poses a significant threat. This behavior may be explicit, i.e. verbalized in the model's…

Data breaches have begun to take on new dimensions and their prediction is becoming of great importance to organizations. Prior work has addressed this issue mainly from a technical perspective and neglected other interfering aspects such…

Currently, knowledge discovery in databases is an essential step to identify valid, novel and useful patterns for decision making. There are many real-world scenarios, such as bankruptcy prediction, option pricing or medical diagnosis,…

The escalating frequency of cyber-attacks poses significant challenges for organisations, particularly small enterprises constrained by limited in-house expertise, insufficient knowledge, and financial resources. This research presents a…

Deep image classification models trained on vast amounts of web-scraped data are susceptible to data poisoning - a mechanism for backdooring models. A small number of poisoned samples seen during training can severely undermine a model's…

Public disclosure of important security information, such as knowledge of vulnerabilities or exploits, often occurs in blogs, tweets, mailing lists, and other online sources months before proper classification into structured databases. In…

Leakage of confidential information represents a serious security risk. Despite a number of novel, theoretical advances, it has been unclear if and how quantitative approaches to measuring leakage of confidential information could be…

The Web is replete with tutorial-style content on how to accomplish programming tasks. Unfortunately, even top-ranked tutorials suffer from severe security vulnerabilities, such as cross-site scripting (XSS), and SQL injection (SQLi).…

The incremental diffusion of machine learning algorithms in supporting cybersecurity is creating novel defensive opportunities but also new types of risks. Multiple researches have shown that machine learning methods are vulnerable to…

Recent studies have demonstrated the vulnerability of recommender systems to data privacy attacks. However, research on the threat to model privacy in recommender systems, such as model stealing attacks, is still in its infancy. Some…

Topic models analyze text from a set of documents. Documents are modeled as a mixture of topics, with topics defined as probability distributions on words. Inferences of interest include the most probable topics and characterization of a…

Information leakage issues in machine learning-based Web applications have attracted increasing attention. While the risk of data privacy leakage has been rigorously analyzed, the theory of model function leakage, known as Model Extraction…

Deep neural networks are vulnerable to adversarial attacks, such as backdoor attacks in which a malicious adversary compromises a model during training such that specific behaviour can be triggered at test time by attaching a specific word…

Building advanced machine learning (ML) models requires expert knowledge and many trials to discover the best architecture and hyperparameter settings. Previous work demonstrates that model information can be leveraged to assist other…

Phishing attacks are the most common type of cyber-attacks used to obtain sensitive information and have been affecting individuals as well as organisations across the globe. Various techniques have been proposed to identify the phishing…

Neural network models trained on text data have been found to encode undesirable linguistic or sensitive concepts in their representation. Removing such concepts is non-trivial because of a complex relationship between the concept, text…

Large language models have gained significant popularity because of their ability to generate human-like text and potential applications in various fields, such as Software Engineering. Large language models for code are commonly trained on…

Membership inference attacks seek to infer membership of individual training instances of a model to which an adversary has black-box access through a machine learning-as-a-service API. In providing an in-depth characterization of…

Topic popularity prediction in social networks has drawn much attention recently. Various elegant models have been proposed for this issue. However, different datasets and evaluation metrics they use lead to low comparability. So far there…

Terrorism has become one of the most tedious problems to deal with and a prominent threat to mankind. To enhance counter-terrorism, several research works are developing efficient and precise systems, data mining is not an exception.…