Related papers: Hunting Vulnerability Variants in AI Infra: Measur…

It is increasingly suggested to identify Software Vulnerabilities (SVs) in code commits to give early warnings about potential security risks. However, there is a lack of effort to assess vulnerability-contributing commits right after they…

The rapid advancement of AI has expanded its capabilities across domains, yet introduced critical technical vulnerabilities, such as algorithmic bias and adversarial sensitivity, that pose significant societal risks, including…

Workspace learning requires AI agents to identify, reason over, exploit, and update explicit and implicit dependencies among heterogeneous files in a worker's workspace, enabling them to complete both routine and advanced tasks effectively.…

AI agents powered by large language models (LLMs) are being deployed at scale, yet we lack a systematic understanding of how the choice of backbone LLM affects agent security. The non-deterministic sequential nature of AI agents complicates…

The security guarantee of AI-enabled software systems (particularly using deep learning techniques as a functional core) is pivotal against the adversarial attacks exploiting software vulnerabilities. However, little attention has been paid…

Cyber-security vulnerabilities are usually published in form of short natural language descriptions (e.g., in form of MITRE's CVE list) that over time are further manually enriched with labels such as those defined by the Common…

Despite their impressive performance, deep neural networks exhibit striking failures on out-of-distribution inputs. One core idea of adversarial example research is to reveal neural network errors under such distribution shifts. We…

Despite the transformative impact of Artificial Intelligence (AI) across various sectors, cyber security continues to rely on traditional static and dynamic analysis tools, hampered by high false positive rates and superficial code…

AI model documentation is fragmented across platforms and inconsistent in structure, preventing policymakers, auditors, and users from reliably assessing safety claims, data provenance, and version-level changes. We analyzed documentation…

Shifts in data distribution can substantially harm the performance of clinical AI models and lead to misdiagnosis. Hence, various methods have been developed to detect the presence of such shifts at deployment time. However, the root causes…

Enterprise AI Assistants are increasingly deployed in domains where accuracy is paramount, making each erroneous output a potentially significant incident. This paper presents a comprehensive framework for monitoring, benchmarking, and…

Software vulnerabilities remain a critical security challenge, providing entry points for attackers into enterprise networks. Despite advances in security practices, the lack of high-quality datasets capturing diverse exploit behavior…

AI models are increasingly prevalent in high-stakes environments, necessitating thorough assessment of their capabilities and risks. Benchmarks are popular for measuring these attributes and for comparing model performance, tracking…

Recently, AI-manipulated face techniques have developed rapidly and constantly, which has raised new security issues in society. Although existing detection methods consider different categories of fake faces, the performance on detecting…

Currently, Application Programming Interfaces (APIs) are becoming increasingly popular to facilitate data transfer in a variety of mobile applications. These APIs often process sensitive user information through their endpoints, which are…

To understand and identify the unprecedented risks posed by rapidly advancing artificial intelligence (AI) models, Frontier AI Risk Management Framework in Practice presents a comprehensive assessment of their frontier risks. As Large…

The growing adoption of artificial intelligence (AI) has amplified concerns about trustworthiness, including integrity, privacy, robustness, and bias. To assess and attribute these threats, we propose ConceptLens, a generic framework that…

Context: The IoT system infrastructure platform facility vulnerability attack has become the main battlefield of network security attacks. Most of the traditional vulnerability mining methods rely on vulnerability detection tools to realize…

This study investigates the adoption and effectiveness of AI-based anomaly detection in cross-provider electronic health record (EHR) environments. It aims to (1) identify the organisational and digital capabilities required for successful…

Artificial Intelligence systems, which benefit from the availability of large-scale datasets and increasing computational power, have become effective solutions to various critical tasks, such as natural language understanding, speech…