Double landmines: invisible textual backdoor attacks based on dual-trigger
Abstract Backdoor attacks pose an important security threat to textual large language models. Exploring textual backdoor attacks not only helps reveal the potential security risks of models, but also promotes innovation and development of defense mechanisms. Currently, most textual backdoor attack m...
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Artigo |
| Lingua: | Inglês |
| Pubblicazione: |
SpringerOpen
2025-12-01
|
| Serie: | Cybersecurity |
| Soggetti: | |
| Accesso online: | https://doi.org/10.1186/s42400-025-00512-z |
| Tags: |
Nessun Tag, puoi essere il primo ad aggiungerne!!
|