paper-with-me

Papers

Medical Malice: A Dataset for Context-Aware Safety in Healthcare LLMs

2025-11-24 · Andrew Maranhão Ventura D'addario arxiv

The integration of Large Language Models (LLMs) into healthcare demands a safety paradigm rooted in \textit{primum non nocere}. However, current alignment techniques rely on generic definitions of harm that fail to capture context-dependent violations, such as administrative fraud and clinical discrimination. To address this, we introduce Medical Malice: a dataset of 214,219 adversarial prompts calibrated to the regulatory and ethical complexities of the Brazilian Unified Health System (SUS). Crucially, the dataset includes the reasoning behind each violation, enabling models to internalize ethical boundaries rather than merely memorizing a fixed set of refusals. Using an unaligned agent (Grok-4) within a persona-driven pipeline, we synthesized high-fidelity threats across seven taxonomies, ranging from procurement manipulation and queue-jumping to obstetric violence. We discuss the ethical design of releasing these "vulnerability signatures" to correct the information asymmetry between malicious actors and AI developers. Ultimately, this work advocates for a shift from universal to context-aware safety, providing the necessary resources to immunize healthcare AI against the nuanced, systemic threats inherent to high-stakes medical environments -- vulnerabilities that represent the paramount risk to patient safety and the successful integration of AI in healthcare systems.

📄 PDF Abstract BibTeX arXiv:2511.21757

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

A Multi-view Context-aware Approach to Android Malware Detection and Malicious Code Localization

2017-04-06 · Annamalai Narayanan, Mahinthan Chandramohan, Lihui Chen, Yang Liu

Existing Android malware detection approaches use a variety of features such as security sensitive APIs, system calls, control-flow structures and information flows in conjunction with Machine Learning classifiers to ach…

Android Malware DetectionMalware DetectionMULTI-VIEW LEARNING

CareGuardAI: Context-Aware Multi-Agent Guardrails for Clinical Safety & Hallucination Mitigation in Patient-Facing LLMs

2026-04-07 · Elham Nasarian, Abhilash Neog, Kwok-Leung Tsui, Niyousha HosseiniChimeh arxiv

Integrating large language models (LLMs) into patient-facing healthcare systems offers significant potential to improve access to medical information. However, ensuring clinical safety and factual reliability remains a c…

Question Answering

Enhancing the Medical Context-Awareness Ability of LLMs via Multifaceted Self-Refinement Learning

2025-11-13 · Yuxuan Zhou, Yubin Wang, Bin Wang, Chen Ning 외 arxiv

Large language models (LLMs) have shown great promise in the medical domain, achieving strong performance on several benchmarks. However, they continue to underperform in real-world medical scenarios, which often demand …

Knowledge Distillation

MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models

2024-03-06 · Tessa Han, Aounon Kumar, Chirag Agarwal, Himabindu Lakkaraju

As large language models (LLMs) develop increasingly sophisticated capabilities and find applications in medical settings, it becomes important to assess their medical safety due to their far-reaching implications for pe…

EthicsGeneral Knowledge

Video-SafetyBench: A Benchmark for Safety Evaluation of Video LVLMs

2025-05-17 · Xuannan Liu, Zekun Li, Zheqi He, Peipei Li 외

The increasing deployment of Large Vision-Language Models (LVLMs) raises safety concerns under potential malicious inputs. However, existing multimodal safety evaluations primarily focus on model vulnerabilities exposed …