3 papers
cs.CL2026
Powerful Training-Free Membership Inference Against Autoregressive Language Models
David IliÄ, David StanojeviÄ, Kostadin Cvejoski
Fine-tuned language models pose significant privacy risks, as they may memorize and expose sensitive information from their training data. Membership inference attacks (MIAs) provi…
cs.CL2026
Learning the Signature of Memorization in Autoregressive Language Models
David IliÄ, Kostadin Cvejoski, David StanojeviÄ +1
All prior membership inference attacks for fine-tuned language models use hand-crafted heuristics (e.g., loss thresholding, Min-K\%, reference calibration), each bounded by the des…
cs.CR2026
Protecting Private Code in IDE Autocomplete using Differential Privacy
Evgeny Grigorenko, David StanojeviÄ, David IliÄ +2
Modern Integrated Development Environments (IDEs) increasingly leverage Large Language Models (LLMs) to provide advanced features like code autocomplete. While powerful, training t…