Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
End-to-End Hard-Label Cryptanalytic Model Extraction Using Efficient Sign Recovery
Akira Ito, Takayuki Miura, Yosuke Todo
The importance of deep neural networks (DNNs) is widely recognized, and the parameters obtained through training are regarded as valuable assets. Recently, attacks that extract the…
cs.CR2026
Dummy Backdoor as a Defense: Removing Unknown Backdoors via Shared Internal Mechanisms for Generative LLMs
Kazuki Iwahana, Masaru Matsubayashi, Takuma Koyama +4
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…