Related papers: SAGE: A Generic Framework for LLM Safety Evaluatio…

Small language models (SLMs) are increasingly deployed on edge devices, making their safety alignment crucial yet challenging. Current shallow alignment methods that rely on direct refusal of malicious queries fail to provide robust…

The emergence of Generative AI (Gen AI) and Large Language Models (LLMs) has enabled more advanced chatbots capable of human-like interactions. However, these conversational agents introduce a broader set of operational risks that extend…

Large language model-powered chatbots have transformed how people seek information, especially in high-stakes contexts like mental health. Despite their support capabilities, safe detection and response to crises such as suicidal ideation…

As large language models (LLMs) evolve from conversational assistants into autonomous agents, evaluating the safety of their actions becomes critical. Prior safety benchmarks have primarily focused on preventing generation of harmful…

The advent of Large Language Models (LLMs) has revolutionized various applications by providing advanced natural language processing capabilities. However, this innovation introduces new cybersecurity challenges. This paper explores the…

The emerging threat of AR-LLM-based Social Engineering (AR-LLM-SE) attacks (e.g. SEAR) poses a significant risk to real-world social interactions. In such an attack, a malicious actor uses Augmented Reality (AR) glasses to capture a target…

The proliferation of Large Language Models (LLMs) and Intelligent Virtual Agents acting as psychotherapists presents significant opportunities for expanding mental healthcare access. However, their deployment has also been linked to serious…

This study explores integrating large language models (LLMs) with situational awareness-based planning (SAP) to enhance the decision-making capabilities of AI agents in dynamic and uncertain environments. We employ a multi-agent reasoning…

Large language models (LLMs) are increasingly used to support question answering and decision-making in high-stakes, domain-specific settings such as natural hazard response and infrastructure planning, where effective answers must convey…

Large Language Models (LLMs) achieve strong performance on standard knowledge evaluation benchmarks, yet recent work shows that their knowledge capabilities remain brittle under question variants that test the same knowledge in different…

Large language models (LLMs) are increasingly used for mental health support, yet existing safety evaluations rely primarily on small, simulation-based test sets that have an unknown relationship to the linguistic distribution of real…

Large Language Models (LLMs) are increasingly applied in various science domains, yet their broader adoption remains constrained by a critical challenge: the lack of trustworthy, verifiable outputs. Current LLMs often generate answers…

Various AI safety datasets have been developed to measure LLMs against evolving interpretations of harm. Our evaluation of five recently published open-source safety benchmarks reveals distinct semantic clusters using UMAP dimensionality…

Text-to-image diffusion models have revolutionized visual content generation, yet their deployment is hindered by a fundamental limitation: safety mechanisms enforce rigid, uniform standards that fail to reflect diverse user preferences…

As generative large model capabilities advance, safety concerns become more pronounced in their outputs. To ensure the sustainable growth of the AI ecosystem, it's imperative to undertake a holistic evaluation and refinement of associated…

Many studies have demonstrated that large language models (LLMs) can produce harmful responses, exposing users to unexpected risks when LLMs are deployed. Previous studies have proposed comprehensive taxonomies of the risks posed by LLMs,…

Current safety alignment for Large Language Models (LLMs) implicitly optimizes for a "modal adult user," leaving models vulnerable to distributional shifts in user cognition. We present ChildSafe, a benchmark that quantifies alignment…

Large language model-based agents are rapidly evolving from simple conversational assistants into autonomous systems capable of performing complex, professional-level tasks in various domains. While these advancements promise significant…

Security incident analysis (SIA) poses a major challenge for security operations centers, which must manage overwhelming alert volumes, large and diverse data sources, complex toolchains, and limited analyst expertise. These difficulties…

Large Language Models (LLMs) continue to exhibit vulnerabilities despite deliberate safety alignment efforts, posing significant risks to users and society. To safeguard against the risk of policy-violating content, system-level moderation…