相关论文: Adversarial Moral Stress Testing of Large Language…

The wide-ranging applications of large language models (LLMs), especially in safety-critical domains, necessitate the proper evaluation of the LLM's adversarial robustness. This paper proposes an efficient tool to audit the LLM's…

As large language models (LLMs) expose systemic security challenges in high risk applications, including privacy leaks, bias amplification, and malicious abuse, there is an urgent need for a dynamic risk assessment and collaborative defence…

Large Language Models (LLMs) can elicit unintended and even harmful content when misaligned with human values, posing severe risks to users and society. To mitigate these risks, current evaluation benchmarks predominantly employ…

Multimodal Large Language Models (MLLMs) have enabled transformative advancements across diverse applications but remain susceptible to safety threats, especially jailbreak attacks that induce harmful outputs. To systematically evaluate and…

Despite their impressive capabilities, Multimodal Large Language Models (MLLMs) exhibit perceptual fragility when confronted with visually complex scenes. This weakness stems from a reliance on finite training datasets, which are…

Understanding how large language models (LLMs) process emotionally sensitive content is critical for building safe and reliable systems, particularly in mental health contexts. We investigate the scaling behavior of LLMs on two key tasks:…

AI-assisted code review is widely used to detect vulnerabilities before production release. Prior work shows that adversarial prompt manipulation can degrade large language model (LLM) performance in code generation. We test whether similar…

Large language models (LLMs) are increasingly deployed in medical contexts, raising critical concerns about safety, alignment, and susceptibility to adversarial manipulation. While prior benchmarks assess model refusal capabilities for…

Warning: This article includes red-teaming experiments, which contain examples of compromised LLM responses that may be offensive or upsetting. Large Language Models (LLMs) have the potential to create harmful content, such as generating…

The rapid advancement of Large Language Models (LLMs) and their potential integration into autonomous driving systems necessitates understanding their moral decision-making capabilities. While our previous study examined four prominent LLMs…

Although LLM-based agents, powered by Large Language Models (LLMs), can use external tools and memory mechanisms to solve complex real-world tasks, they may also introduce critical security vulnerabilities. However, the existing literature…

Large language models (LLMs) are increasingly considered for deployment as the control component of robotic health attendants, yet their safety in this context remains poorly characterized. We introduce a dataset of 270 harmful instructions…

Large Language Models (LLMs) have transformed software development, enabling AI-powered applications known as LLM-based agents that promise to automate tasks across diverse apps and workflows. Yet, the security implications of deploying…

Large Language Models (LLMs) are valuable for text classification, but their vulnerabilities must not be disregarded. They lack robustness against adversarial examples, so it is pertinent to understand the impacts of different types of…

Pluralism alignment with AI has the sophisticated and necessary goal of creating AI that can coexist with and serve morally multifaceted humanity. Research towards pluralism alignment has many efforts in enhancing the learning of large…

Transformer-based language models for code have shown remarkable performance in various software analytics tasks, but their adoption is hindered by high computational costs, slow inference speeds, and substantial environmental impact. Model…

Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models. We…

Traditional methods for evaluating the robustness of large language models (LLMs) often rely on standardized benchmarks, which can escalate costs and limit evaluations across varied domains. This paper introduces a novel framework designed…

Recent advances in Large Language Models (LLMs) have enabled human-like responses across various tasks, raising questions about their ethical decision-making capabilities and potential biases. This study systematically evaluates how nine…

Despite substantial efforts toward improving the moral alignment of Vision-Language Models (VLMs), it remains unclear whether their ethical judgments are stable in realistic settings. This work studies moral robustness in VLMs, defined as…