Related papers: InvisibleBench: A Deployment Gate for Caregiving R…
Spoken Dialogue Models (SDMs) have advanced rapidly, yet their ability to sustain genuinely interactive multi-turn conversations remains underexplored, as most benchmarks focus on single-turn exchanges. We introduce Multi-Bench, the first…
As the deployment of Artificial Intelligence (AI) systems in high-stakes sectors - like healthcare, finance, education, justice, and infrastructure has increased - the possibility and impact of failures of these systems have significantly…
The rapid advancement of vision-language models (VLMs) has brought a lot of attention to their safety alignment. However, existing methods have primarily focused on model undersafety, where the model responds to hazardous queries, while…
This study introduces an AI-driven platform for continuous and passive patient monitoring in hospital settings, developed by LookDeep Health. Leveraging advanced computer vision, the platform provides real-time insights into patient…
Vehicular Ad Hoc Networks (VANETs) are vulnerable to intelligent attackers who exploit the homogeneous treatment of traffic events in existing trust models. These attackers accumulate reputation by reporting correctly on low-priority events…
The rapid expansion of large language model (LLM) safety evaluation has produced a substantial benchmark ecosystem, but not a correspondingly coherent measurement ecosystem. We present AISafetyBenchExplorer, a structured catalogue of 195 AI…
Existing AI agent safety benchmarks focus on generic criminal harm (cybercrime, harassment, weapon synthesis), leaving a systematic blind spot for a distinct and commercially consequential threat category: agents harming their own…
Generative AI systems achieve impressive performance on standard benchmarks yet fail to deliver real-world utility, a disconnect we identify across 28 deployment cases spanning education, healthcare, software engineering, and law. We argue…
AI models are already deployed in societies affected by armed conflict, and journalists, humanitarian workers, governments and ordinary citizens rely on them for information or for their work processes. No established practice exists for…
With the advent of text-to-image models and concerns about their misuse, developers are increasingly relying on image safety classifiers to moderate their generated unsafe images. Yet, the performance of current image safety classifiers…
With the rise of personalized, persistent LLM agent frameworks such as OpenClaw, human-centered agentic social networks in which teams of collaborative AI agents serve individual users in a social network across multiple domains are…
Lack of awareness and knowledge of microservices-specific security challenges and solutions often leads to ill-informed security decisions in microservices system development. We claim that identifying and leveraging security discussions…
Cooperative multi-agent methods for embodied AI are almost universally evaluated under idealized communication: zero latency, no packet loss, and unlimited bandwidth. Real-world deployment on robots with wireless links, autonomous vehicles…
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…
Can generative agents be trusted in multimodal environments? Despite advances in large language and vision-language models that enable agents to act autonomously and pursue goals in rich settings, their ability to reason about safety,…
AI control protocols use monitors to detect attacks by untrusted AI agents, but standard single-score monitors face two limitations: they miss subtle attacks where outputs look clean but reasoning is off, and they collapse to near-zero…
Current LLM safety alignment techniques improve model robustness against adversarial attacks, but overlook whether and how LLMs can recover helpfulness when benign users clarify their intent. We introduce CarryOnBench, the first interactive…
As large language models (LLMs) are increasingly deployed as interactive agents, open-ended human-AI interactions can involve deceptive behaviors with serious real-world consequences, yet existing evaluations remain largely…
The mismatch between the growing demand for psychological counseling and the limited availability of services has motivated research into the application of Large Language Models (LLMs) in this domain. Consequently, there is a need for a…
This paper introduces DeepPsy-Agent, an innovative psychological support system that combines the three-stage helping theory in psychology with deep learning techniques. The system consists of two core components: (1) a multi-stage…