Related papers: TestREx: a Framework for Repeatable Exploits
Security must be considered in almost every software system. Unfortunately, selecting and implementing security features remains challenging due to the variety of security threats and possible countermeasures. While security standards are…
In this study, we reproduced the work done in the paper "XRec: Large Language Models for Explainable Recommendation" by Ma et al. (2024). The original authors introduced XRec, a model-agnostic collaborative instruction-tuning framework that…
Any human-designed system can potentially be exploited in ways that its designers did not envision, and information systems or networks using quantum components do not escape this reality. We are presented with a unique but quickly waning…
Attestation is a fundamental building block to establish trust over software systems. When used in conjunction with trusted execution environments, it guarantees the genuineness of the code executed against powerful attackers and threats,…
In the cybersecurity research community, there is no one-size-fits-all solution for merging large numbers of heterogeneous resources and experimentation capabilities from disparate specialized testbeds into integrated experiments. The…
Detection of malicious activities in corporate environments is a very complex task and much effort has been invested into research of its automation. However, vast majority of existing methods operate only in a narrow scope which limits…
Agile development processes and component-based software architectures are two software engineering approaches that contribute to enable the rapid building and evolution of applications. Nevertheless, few approaches have proposed a…
Traditional security scanners fail when facing new attack patterns they haven't seen before. They rely on fixed rules and predetermined signatures, making them blind to novel threats. We present a fundamentally different approach: instead…
Mainstream software applications and tools are the configurable platforms with an enormous number of parameters along with their values. Certain settings and possible interactions between these parameters may harden (or soften) the security…
We release Terminal Wrench, a subset of 331 terminal-agent benchmark environments, copied from the popular open benchmarks that are demonstrably reward-hackable. The data set includes 3,632 hack trajectories and 2,352 legitimate baseline…
Although Retrieval-Augmented Generation (RAG) systems have been widely applied, the privacy and security risks they face, such as data leakage and data poisoning, have not been systematically addressed yet. Existing defense strategies…
With the rise of the Internet of Things (IoT) and Edge computing, a considerable amount of system services are moving from reliable Cloud data centers to less reliable infrastructures closer to the end-users. However, the constrained…
A number of automated techniques and tools were proposed in the research literature over the years which aim to support the spreadsheet developer in the process of testing and debugging a faulty spreadsheet. One underlying assumption of…
Exceptions and errors occurring within mission critical applications due to hardware failures have a high cost. With the emerging Next Generation Platforms (NGPs), the rate of hardware failures will invariably increase. Therefore, designing…
Reproducing and comparing results in news recommendation research has become increasingly difficult. This is due to a fragmented ecosystem of diverse codebases, varied configurations, and mainly due to resource-intensive models. We…
Regular expressions are used for diverse purposes, including input validation and firewalls. Unfortunately, they can also lead to a security vulnerability called ReDoS (Regular Expression Denial of Service), caused by a super-linear…
With the rise of increasingly complex autonomous systems powered by black box AI models, there is a growing need for Run Time Assurance (RTA) systems that provide online safety filtering to untrusted primary controller output. Currently,…
Penetration testing is an essential means of proactive defense in the face of escalating cybersecurity incidents. Traditional manual penetration testing methods are time-consuming, resource-intensive, and prone to human errors. Current…
Machine Learning as a Service (MLaaS) enables users to leverage powerful machine learning models through cloud-based APIs, offering scalability and ease of deployment. However, these services are vulnerable to model extraction attacks,…
Jailbreak attacks are crucial for identifying and mitigating the security vulnerabilities of Large Language Models (LLMs). They are designed to bypass safeguards and elicit prohibited outputs. However, due to significant differences among…