6 papers
Routing Subspaces: Auditing Evaluation-to-Deployment Mismatch in Fine-Tuned Language Models
Phongsakon Mark Konrad, Toygar Tanyel, Serkan Ayvaz
Safety evaluations often assume that behavior observed during testing reflects behavior in ordinary use, but fine-tuning can break this assumption. A checkpoint can appear fixed un…
The Open-Box Fallacy: Why AI Deployment Needs a Calibrated Verification Regime
Phongsakon Mark Konrad, Tim Lukas Adam, Ane Cathrine Holst Merrild +4
AI deployment in sensitive domains such as health care, credit, employment, and criminal justice is often treated as unsafe to authorize until model internals can be explained. Thi…
Acceptance Cards:A Four-Diagnostic Standard for Safe Fine-Tuning Defense Claims
Phongsakon Mark Konrad, Toygar Tanyel, Serkan Ayvaz
Safe fine-tuning defenses are often endorsed on the basis of a held-out gap reduction, but the same reduction can come from sampling noise, subject artifacts, capability loss, or a…
Mammographic Breast Positioning Assessment via Deep Learning
Toygar Tanyel, Nurper Denizoglu, Mustafa Ege Seker +5
Breast cancer remains a leading cause of cancer-related deaths among women worldwide, with mammography screening as the most effective method for the early detection. Ensuring prop…
Developing Linguistic Patterns to Mitigate Inherent Human Bias in Offensive Language Detection
Toygar Tanyel, Besher Alkurdi, Serkan Ayvaz
With the proliferation of social media, there has been a sharp increase in offensive content, particularly targeting vulnerable groups, exacerbating social problems such as hatred,…
Interpretable ECG Analysis for Myocardial Infarction Detection through Counterfactuals
Toygar Tanyel, Sezgin Atmaca, Kaan Gökçe +4
In the evolving landscape of ECG signal analysis, the challenge of limited transparency in machine learning models remains a significant barrier to their effective integration into…