Other
Presentations, documents, spreadsheets, and other resources.
Grounding Safety Awareness in AI Models Through Internal Reasoning
Presentation on embedding safety considerations directly into AI model reasoning processes.
PresentationJun 2025
DeepSeek V3.2 Adversarial Robustness
Preliminary safety evaluation of DeepSeek V3.2 model vulnerabilities and adversarial attacks.
DocumentDec 2025
Medical LLM Attack Taxonomy
Comprehensive taxonomy of motivations and methods for attacking medical LLMs in healthcare settings.
SpreadsheetDec 2025
Adversarial Attacks on Multimodal LLMs in Medical Domain
Research presentation on adversarial attack methods targeting multimodal large language models in healthcare.
PresentationDec 2024
Evaluating Large Language Models in Medicine
Presentation on evaluation frameworks and methodologies for assessing LLM performance in medical applications.
PresentationSep 2024
Adversarial Attacks & Examples on Medical Imaging
Overview of adversarial attack techniques and real-world examples targeting medical imaging AI systems.
PresentationMar 2024