相关论文: Cognitive Cybersecurity for Artificial Intelligenc…

Background Large language models (LLMs) are increasingly deployed in medical consultations, yet their safety under realistic user pressures remains understudied. Prior assessments focused on neutral conditions, overlooking vulnerabilities…

The widespread integration of autoregressive-large language models (AR-LLMs), such as ChatGPT, across established applications, like search engines, has introduced critical vulnerabilities with uniquely scalable characteristics. In this…

Over the past 15 years, researchers have identified an increasing number of security mechanisms that are so unusable that the intended users either circumvent them or give up on a service rather than suffer the security. With hindsight, the…

We draw on our experience working on system and software assurance and evaluation for systems important to society to summarise how safety engineering is performed in traditional critical systems, such as aircraft flight control. We analyse…

Large Language Models (LLMs) are swiftly advancing in architecture and capability, and as they integrate more deeply into complex systems, the urgency to scrutinize their security properties grows. This paper surveys research in the…

Artificial intelligence (AI) copilots are increasingly integrated into enterprise cybersecurity platforms to assist analysts in threat detection, triage, and remediation. However, the effectiveness of these systems depends not only on the…

Large language models (LLMs) have been shown to exhibit social bias, however, bias towards non-protected stigmatized identities remain understudied. Furthermore, what social features of stigmas are associated with bias in LLM outputs is…

Safety alignment mechanisms in Large Language Models (LLMs) often operate as latent internal states, obscuring the model's inherent capabilities. Building on this observation, we model the safety mechanism as an unobserved confounder from a…

Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks. However, they remain highly susceptible to jailbreak attacks that undermine their safety alignment. Existing defense mechanisms typically…

We present a framework for characterizing neurosis in embodied AI: behaviors that are internally coherent yet misaligned with reality, arising from interactions among planning, uncertainty handling, and aversive memory. In a grid navigation…

Vision-language-action models (VLAs) show potential as generalist robot policies. However, these models pose extreme safety challenges during real-world deployment, including the risk of harm to the environment, the robot itself, and…

As Large Language Models (LLMs) become increasingly autonomous and integrated into critical societal functions, the focus of AI safety must evolve from mitigating harmful content to evaluating underlying behavioral alignment. Current safety…

As large language models (LLMs) are increasingly integrated into real-world applications, ensuring their safety, robustness, and privacy compliance has become critical. We present OpenGuardrails, the first fully open-source platform that…

During the design of safety-critical systems, safety and security engineers make use of architecture patterns, such as Watchdog and Firewall, to address identified failures and threats. Often, however, the deployment of safety patterns has…

Recent breakthroughs in Large Language Models (LLMs) have led to their adoption across a wide range of tasks, ranging from code generation to machine translation and sentiment analysis, etc. Red teaming/Safety alignment efforts show that…

Artificial Intelligence (AI) is revolutionizing scientific research, yet its growing integration into laboratory environments presents critical safety challenges. Large language models (LLMs) and vision language models (VLMs) now assist in…

As artificial intelligence (AI) systems are increasingly deployed across critical domains, their security vulnerabilities pose growing risks of high-profile exploits and consequential system failures. Yet systematic approaches to evaluating…

Evaluating the correctness of code generated by AI is a challenging open problem. In this paper, we propose a fully automated method, named ACCA, to evaluate the correctness of AI-generated code for security purposes. The method uses…

As large language models (LLMs) constantly evolve, ensuring their safety remains a critical research problem. Previous red-teaming approaches for LLM safety have primarily focused on single prompt attacks or goal hijacking. To the best of…

Ensuring content safety in large language models (LLMs) is essential for their deployment in real-world applications. However, existing safety guardrails are predominantly tailored for high-resource languages, leaving a significant portion…