3 papers
cs.CR2026
Dummy Backdoor as a Defense: Removing Unknown Backdoors via Shared Internal Mechanisms for Generative LLMs
Kazuki Iwahana, Masaru Matsubayashi, Takuma Koyama +3
Backdoor attacks pose a serious threat to the safety and reliability of Large Language Models (LLMs), as they cause models to behave normally on clean inputs while producing attack…
cs.LG2026
Is the Hard-Label Cryptanalytic Model Extraction Really Polynomial?
Akira Ito, Takayuki Miura, Yosuke Todo
Deep Neural Networks (DNNs) have attracted significant attention, and their internal models are now considered valuable intellectual assets. Extracting such a model via oracle acce…
cs.LG2025
Robust Backdoor Removal by Reconstructing Trigger-Activated Changes in Latent Representation
Kazuki Iwahana, Yusuke Yamasaki, Akira Ito +2
Backdoor attacks pose a critical threat to machine learning models, causing them to behave normally on clean data but misclassify poisoned data into a poisoned class. Existing defe…