Related papers: A Threat Modeling Framework for Evaluating Computi…

Recent works have identified a gap between research and practice in artificial intelligence security: threats studied in academia do not always reflect the practical use and security risks of AI. For example, while models are often studied…

Large Language Models (LLMs) have been suggested for use in automated vulnerability repair, but benchmarks showing they can consistently identify security-related bugs are lacking. We thus develop SecLLMHolmes, a fully automated evaluation…

Deep learning models deployed in safety critical applications like autonomous driving use simulations to test their robustness against adversarial attacks in realistic conditions. However, these simulations are non-differentiable, forcing…

Security threats such as jamming and route manipulation can have significant consequences on the performance of modern wireless networks. To increase the efficacy and stealthiness of such threats, a number of extremely challenging,…

While the applications and demands of Machine learning (ML) systems in mental health are growing, there is little discussion nor consensus regarding a uniquely challenging aspect: building security methods and requirements into these ML…

Software services are inevitably exposed to a fluctuating threat picture. Unfortunately, not all threats can be handled only with preventive measures during design and development, but also require adaptive mitigations at runtime. In this…

Automated machine learning (AutoML) has emerged as a promising paradigm for automating machine learning (ML) pipeline design, broadening AI adoption. Yet its reliability in complex domains such as cybersecurity remains underexplored. This…

Attestation means providing evidence that a remote target system is worthy of trust for some sensitive interaction. Although attestation is already used in network access control, security management, and trusted execution environments, it…

Security is an important quality of software systems, but there is a huge lack of security experts. To overcome this gap, we aim to make security design knowledge reusable for architects by proposing the SecuRe recommendation approach to…

Large language models (LLMs) are improving at an exceptional rate. However, these models are still susceptible to jailbreak attacks, which are becoming increasingly dangerous as models become increasingly powerful. In this work, we…

Machine learning (ML) models are susceptible to various risks to security, privacy, and fairness. Most defenses are designed to protect against each risk individually (intended interactions) but can inadvertently affect susceptibility to…

Integrating large language models (LLMs) into robotic systems has revolutionised embodied artificial intelligence, enabling advanced decision-making and adaptability. However, ensuring reliability, encompassing both security against…

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…

Large Language Model (LLM) systems are inherently compositional, with individual LLM serving as the core foundation with additional layers of objects such as plugins, sandbox, and so on. Along with the great potential, there are also…

Foundation Models (FMs) display exceptional performance in tasks such as natural language processing and are being applied across a growing range of disciplines. Although typically trained on large public datasets, FMs are often fine-tuned…

Sybil attacks are becoming increasingly widespread, and pose a significant threat to online social systems; a single adversary can inject multiple colluding identities in the system to compromise security and privacy. Recent works have…

Vulnerability of Frontier language models to misuse and jailbreaks has prompted the development of safety measures like filters and alignment training in an effort to ensure safety through robustness to adversarially crafted prompts. We…

Timing-based side and covert channels in processor caches continue to be a threat to modern computers. This work shows for the first time a systematic, large-scale analysis of Arm devices and the detailed results of attacks the processors…

Large Language Models (LLMs) remain vulnerable to multi-turn jailbreak attacks. We introduce HarmNet, a modular framework comprising ThoughtNet, a hierarchical semantic network; a feedback-driven Simulator for iterative query refinement;…

Modern machine learning (ML) models are expensive IP and business competitiveness often depends on keeping this IP confidential. This in turn restricts how these models are deployed; for example, it is unclear how to deploy a model…