all AI news
TrojFSP: Trojan Insertion in Few-shot Prompt Tuning
March 20, 2024, 4:43 a.m. | Mengxin Zheng, Jiaqi Xue, Xun Chen, YanShan Wang, Qian Lou, Lei Jiang
cs.LG updates on arXiv.org arxiv.org
Abstract: Prompt tuning is one of the most effective solutions to adapting a fixed pre-trained language model (PLM) for various downstream tasks, especially with only a few input samples. However, the security issues, e.g., Trojan attacks, of prompt tuning on a few data samples are not well-studied. Transferring established data poisoning attacks directly to few-shot prompt tuning presents multiple challenges. One significant issue is the \textit{poisoned imbalance issue}, where non-target class samples are added to the …
abstract arxiv attacks cs.lg data few-shot however language language model prompt prompt tuning samples security solutions tasks type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US