247 citations
- Chinese Academy of SciencesCN108 papers
- Shandong UniversityCN87 papers
- Southwest Jiaotong UniversityCN87 papers
- Institute of High Energy PhysicsCN85 papers
- Hebei Normal UniversityCN75 papers
- Yunnan UniversityCN74 papers
- National Astronomical ObservatoriesCN56 papers
- University of Chinese Academy of SciencesCN55 papers
- Istituto Nazionale di Fisica Nucleare, Sezione di NapoliIT38 papers
- Tsinghua UniversityCN36 papers
- Istituto Nazionale di Fisica Nucleare, Roma Tor VergataIT31 papers
- Nanjing UniversityCN31 papers
Showing 2024 · cs.CLShow all
3 papers · 2 filters
cs.CL2024
TSCheater: Generating High-Quality Tibetan Adversarial Texts via Visual Similarity
Xi Cao, Quzong Gesang, Yuan Sun +2
Language models based on deep neural networks are vulnerable to textual adversarial attacks. While rich-resource languages like English are receiving focused attention, Tibetan, a…
cs.CL2024★ 5 cited
Pay Attention to the Robustness of Chinese Minority Language Models! Syllable-level Textual Adversarial Attack on Tibetan Script
Xi Cao, Dolma Dawa, Nuo Qun +1
The textual adversarial attack refers to an attack method in which the attacker adds imperceptible perturbations to the original texts by elaborate design so that the NLP (natural…
cs.CL2024★ 2 cited
Multi-Granularity Tibetan Textual Adversarial Attack Method Based on Masked Language Model
Xi Cao, Nuo Qun, Quzong Gesang +2
In social media, neural network models have been applied to hate speech detection, sentiment analysis, etc., but neural network models are susceptible to adversarial attacks. For i…