Related papers: A Secure Design Pattern Approach Toward Tackling L…

Low-trust architectures work on, from the viewpoint of software, always-encrypted data, and significantly reduce the amount of hardware trust to a small software-free enclave component. In this paper, we perform a complete formal…

Trusted execution environments (TEEs) provide an environment for running workloads in the cloud without having to trust cloud service providers, by offering additional hardware-assisted security guarantees. However, main memory encryption…

Large language models (LLMs) are now routinely used to autonomously execute complex tasks, from natural language processing to dynamic workflows like web searches. The usage of tool-calling and Retrieval Augmented Generation (RAG) allows…

In recent years, machine learning models, especially deep neural networks, have been widely used for classification tasks in the security domain. However, these models have been shown to be vulnerable to adversarial manipulation: small…

Machine learning is vulnerable to adversarial manipulation. Previous literature has demonstrated that at the training stage attackers can manipulate data and data sampling procedures to control model behaviour. A common attack goal is to…

Architectural backdoors pose an under-examined but critical threat to deep neural networks, embedding malicious logic directly into a model's computational graph. Unlike traditional data poisoning or parameter manipulation, architectural…

Backdoor attacks significantly compromise the security of large language models by triggering them to output specific and controlled content. Currently, triggers for textual backdoor attacks fall into two categories: fixed-token triggers…

Large Language Models (LLMs), such as OpenAI's o1-series have demonstrated compelling capabilities for complex reasoning tasks via the extended chain-of-thought (CoT) reasoning mechanism. However, recent studies reveal substantial…

Tool-calling has changed Large Language Model (LLM) applications by integrating external tools, significantly enhancing their functionality across diverse tasks. However, this integration also introduces new security vulnerabilities,…

Due to the exceptional performance of Large Language Models (LLMs) in diverse downstream tasks,there has been an exponential growth in edge-device requests to cloud-based models.However, the current authentication mechanism using static…

Recently efficient model-checking tools have been developed to find flaws in security protocols specifications. These flaws can be interpreted as potential attacks scenarios but the feasability of these scenarios need to be confirmed at the…

Large Language Models (LLMs) are trained with safety alignment to prevent generating malicious content. Although some attacks have highlighted vulnerabilities in these safety-aligned LLMs, they typically have limitations, such as…

Software is prone to security vulnerabilities. Program analysis tools to detect them have limited effectiveness in practice due to their reliance on human labeled specifications. Large language models (or LLMs) have shown impressive code…

Recently, LoRA and its variants have become the de facto strategy for training and sharing task-specific versions of large pretrained models, thanks to their efficiency and simplicity. However, the issue of copyright protection for LoRA…

Logging systems are an essential component of security systems and their security has been widely studied. Recently (2017) it was shown that existing secure logging protocols are vulnerable to crash attack in which the adversary modifies…

Nowadays, we are more and more reliant on Deep Learning (DL) models and thus it is essential to safeguard the security of these systems. This paper explores the security issues in Deep Learning and analyses, through the use of experiments,…

The CERN LHC experiments have begun the LHC Computing Grid project in 2001. One of the project's aims is to develop common software infrastructure based on a development vision shared by the participating experiments. The SEAL project will…

Large language models (LLMs) have revolutionized software development through AI-assisted coding tools, enabling developers with limited programming expertise to create sophisticated applications. However, this accessibility extends to…

In LLM-based text-to-SQL systems, unanswerable and underspecified user queries may generate not only incorrect text but also executable programs that yield misleading results or violate safety constraints, posing a major barrier to safe…

software component misuse a privileged relationship with the hardware to by pass system protections, monitors, or forensic tools. These relationships are often not illegal and exist between system components by design. Hence, even a system…