2 papers
cs.CR2026
MEASER: Malware embedding attacks on open-source LLMs
Ming Tan, Wei Li, Hu Tao +4
Open-source large language models (LLMs) have demonstrated considerable dominance over proprietary LLMs in resolving neural processing tasks, thanks to the collaborative and sharin…
cs.LG2024
Machine Unlearning in Forgettability Sequence
Junjie Chen, Qian Chen, Jian Lou +3
Machine unlearning (MU) is becoming a promising paradigm to achieve the "right to be forgotten", where the training trace of any chosen data points could be eliminated, while maint…