Mengxin Zheng
12 papers · 2023–2026 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π Cross-Pollinator (4) π Renaissance Researcher (7) πΊοΈ Taxonomy Completionist (23) π Interdisciplinary Bridge
π§
Keyword Pioneer
π
Conference Polyglot
(7)
π€
Dynamic Duo
(11)
β‘
Prolific Year
(6)
π
Century Club
(11)
Conferences
EMNLP (4)
ACL (2)
NIPS (2)
CVPR (1)
ECCV (1)
ICLR (1)
NAACL (1)
Top co-authors
Research topics
Keywords
trojan attack
(3)
prompt injection
(2)
adversarial learning
(2)
backdoor attack
(2)
adversarial attack
(2)
neural network security
(1)
model security
(1)
vision transformer
(1)
medical text
(1)
factual accuracy
(1)
neural network training
(1)
text classification
(1)
black-box attack
(1)
text watermarking
(1)
fully homomorphic encryption
(1)
language model
(1)
data pruning
(1)
private neural network training
(1)
ciphertext computation
(1)
data poisoning
(1)
Papers
Conjunctive Prompt Attacks in Multi-Agent LLM Systems
ACL 2026
CipherPrune: Efficient and Scalable Private Transformer Inference
ICLR 2025
Evaluating the Robustness and Accuracy of Text Watermarking Under Real-World Cross-Lingual Manipulations
EMNLP 2025
Factuality Beyond Coherence: Evaluating LLM Watermarking Methods for Medical Texts
EMNLP 2025
Jailbreaking LLMs with Arabic Transliteration and Arabizi
EMNLP 2024
BadFair: Backdoored Fairness Attacks with Group-conditioned Triggers
EMNLP 2024
HEPrune: Fast Private Training of Deep Neural Networks With Encrypted Data Pruning
NIPS 2024
CR-UTP: Certified Robustness against Universal Text Perturbations on Large Language Models
ACL 2024
SSL-Cleanse: Trojan Detection and Mitigation in Self-Supervised Learning
ECCV 2024
TrojFSP: Trojan Insertion in Few-shot Prompt Tuning
NAACL 2024
TrojViT: Trojan Insertion in Vision Transformers
CVPR 2023
TrojLLM: A Black-box Trojan Prompt Attack on Large Language Models
NIPS 2023