5 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…
Beyond Known Reality: Exploiting Counterfactual Explanations for Medical Research
Toygar Tanyel, Serkan Ayvaz, Bilgin Keserci
The field of explainability in artificial intelligence (AI) has witnessed a growing number of studies and increasing scholarly interest. However, the lack of human-friendly and ind…
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…