Related papers: MindGuard: Guardrail Classifiers for Multi-Turn Me…

The development of conversational agents to interact with patients and deliver clinical advice has attracted the interest of many researchers, particularly in light of the COVID-19 pandemic. The training of an end-to-end neural based dialog…

Malicious content generated by large language models (LLMs) can pose varying degrees of harm. Although existing LLM-based moderators can detect harmful content, they struggle to assess risk levels and may miss lower-risk outputs. Accurate…

Large Language Models (LLMs) are powerful tools for answering user queries, yet they remain highly vulnerable to jailbreak attacks. Existing guardrail methods typically rely on internal features or textual responses to detect malicious…

Large Language Models (LLMs) face a significant threat from multi-turn jailbreak attacks, where adversaries progressively steer conversations to elicit harmful outputs. However, the practical effectiveness of existing attacks is undermined…

Hidden malicious intent in multi-turn dialogue poses a growing threat to deployed large language models (LLMs). Rather than exposing a harmful objective in a single prompt, increasingly capable attackers can distribute their intent across…

Large language models (LLMs) are increasingly used for mental-health support; yet prevailing evaluation methods--fluency metrics, preference tests, and generic dialogue benchmarks--fail to capture the clinically critical dimensions of…

As Large Language Models (LLMs) and generative AI become increasingly widespread, concerns about content safety have grown in parallel. Currently, there is a clear lack of high-quality, human-annotated datasets that address the full…

While large language model-based agents demonstrate great potential in collaborative tasks, their interactivity also introduces security vulnerabilities. In this paper, we propose and model group collusive attacks, a highly destructive…

Large Language Models (LLMs) have been demonstrated to generate illegal or unethical responses, particularly when subjected to "jailbreak." Research on jailbreak has highlighted the safety issues of LLMs. However, prior studies have…

As older adults increasingly use LLM-based chatbots for companionship and assistance, a safety gap is emerging. Older adults may face vulnerabilities from social isolation, limited digital literacy, and cognitive decline, yet existing…

With the widespread application of Large Language Models (LLMs), their associated security issues have become increasingly prominent, severely constraining their trustworthy deployment in critical domains. This paper proposes a novel safety…

The deployment of Large Reasoning Models (LRMs) in high-stakes decision-making pipelines has introduced a novel and opaque attack surface: reasoning backdoors. In these attacks, the model's intermediate Chain-of-Thought (CoT) is manipulated…

Mental health disorders are among the most prevalent diseases worldwide, affecting nearly one in four people. Despite their widespread impact, the intervention rate remains below 25%, largely due to the significant cooperation required from…

The rapid development of Multimodal Large Reasoning Models (MLRMs) has demonstrated broad application potential, yet their safety and reliability remain critical concerns that require systematic exploration. To address this gap, we conduct…

Large language models have seen widespread adoption, yet they remain vulnerable to multi-turn jailbreak attacks, threatening their safe deployment. This has led to the task of training automated multi-turn attackers to probe model safety…

Recent advances in large language models (LLMs) have led to the development of powerful AI chatbots capable of engaging in natural and human-like conversations. However, these chatbots can be potentially harmful, exhibiting manipulative,…

We present MultiBreak, a scalable and diverse multi-turn jailbreak benchmark to evaluate large language model (LLM) safety. Multi-turn jailbreaks mimic natural conversational settings, making them easier to bypass safety-aligned LLM than…

We introduce findings and methods to facilitate evidence-based discussion about how large language models (LLMs) should behave in response to user signals of risk of suicidal thoughts and behaviors (STB). People are already using LLMs as…

Language models exhibit human-like cognitive vulnerabilities, such as emotional framing, that escape traditional behavioral alignment. We present CCS-7 (Cognitive Cybersecurity Suite), a taxonomy of seven vulnerabilities grounded in human…

As large language models (LLMs) increasingly mediate emotionally sensitive conversations, especially in mental health contexts, their ability to recognize and respond to high-risk situations becomes a matter of public safety. This study…