相关论文: PRISM: A Design Framework for Open-Source Foundati…
Large language models that exhibit instruction-following behaviour represent one of the biggest recent upheavals in conversational interfaces, a trend in large part fuelled by the release of OpenAI's ChatGPT, a proprietary large language…
Justifying the correct implementation of the non-functional requirements (e.g., safety, security) of mission-critical systems is crucial to prevent system failure. The later could have severe consequences such as the death of people and…
Research and industry are rapidly advancing the innovation and adoption of foundation model-based systems, yet the tools for managing these models have not kept pace. Understanding the provenance and lineage of models is critical for…
The absence of data protection measures in software applications leads to data breaches, threatening end-user privacy and causing instabilities in organisations that developed those software. Privacy Enhancing Technologies (PETs) emerge as…
Prominent AI companies are producing 'safety frameworks' as a type of voluntary self-governance. These statements purport to establish risk thresholds and safety procedures for the development and deployment of highly capable AI.…
LLM-enabled applications are rapidly reshaping the software ecosystem by using large language models as core reasoning components for complex task execution. This paradigm shift, however, introduces fundamentally new reliability challenges…
A program that maintains key safety properties even when interacting with arbitrary untrusted code is said to enjoy \emph{robust safety}. Proving that a program written in a mainstream language is robustly safe is typically challenging…
Open source projects play a significant role in software production. Most of the software projects reuse and build upon the existing open source projects and libraries. While reusing is a time and cost-saving strategy, some of the key…
A precise vulnerability discovery model (VDM) will provide a useful insight to assess software security, and could be a good prediction instrument for both software vendors and users to understand security trends and plan ahead patching…
Deploying large language model (LLM)-driven conversational agents in enterprise settings requires prompts that are simultaneously correct at launch and resilient to the non-deterministic behavioral drift that characterizes production LLM…
The desire to use reinforcement learning in safety-critical settings has inspired a recent interest in formal methods for learning algorithms. Existing formal methods for learning and optimization primarily consider the problem of…
Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…
Software privacy provides the ability to limit data access to unauthorized parties. Privacy is achieved through different means, such as implementing GDPR into software applications. However, previous research revealed that the lack of poor…
This paper extends the FAIR (Findable, Accessible, Interoperable, Reusable) guidelines to provide criteria for assessing if software conforms to best practices in open source. By adding 'USE' (User-Centered, Sustainable, Equitable),…
Current research in adversarial robustness of LLMs focuses on discrete input manipulations in the natural language space, which can be directly transferred to closed-source models. However, this approach neglects the steady progression of…
This paper focuses on Zero-Trust Foundation Models (ZTFMs), a novel paradigm that embeds zero-trust security principles into the lifecycle of foundation models (FMs) for Internet of Things (IoT) systems. By integrating core tenets, such as…
Most safety testing efforts for large language models (LLMs) today focus on evaluating foundation models. However, there is a growing need to evaluate safety at the application level, as components such as system prompts, retrieval…
Nowadays, advanced security mechanisms exist to protect data, systems, and networks. Most of these mechanisms are effective, and security experts can handle them to achieve a sufficient level of security for any given system. However, most…
Constructing stealthy malware has gained increasing popularity among cyber attackers to conceal their malicious intent. Nevertheless, the constructed stealthy malware still fails to survive the reverse engineering by security experts.…
Privacy-preservation for sensitive data has become a challenging issue in cloud computing. Threat modeling as a part of requirements engineering in secure software development provides a structured approach for identifying attacks and…