conftrace_
← Authors

Qiongkai Xu

29 papers · 2012–2026 · 9 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓
+11 more ↓ πŸƒ Academic Marathon (13) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (9) 🐝 Cross-Pollinator (13)
🐝 Cross-Pollinator (13) 🌈 Renaissance Researcher (7) πŸ—ΊοΈ Taxonomy Completionist (53) πŸ”¬ Deep Specialist (11) 🀝 Dynamic Duo (13) πŸ† Keyword Champion πŸ’Ž Century Club (28) πŸ“ˆ Trend Setter πŸ”₯ Unstoppable (9) ⚑ Prolific Year (5) πŸ—ƒοΈ Keyword Collector (129)

Conferences

EMNLP (12) ACL (8) COLING (2) NAACL (2) AAAI (1) ICLR (1) IJCNLP (1) NIPS (1) SEMEVAL (1)

Top co-authors

Xuanli He (13) Lizhen Qu (7) Trevor Cohn (5) Lingjuan Lyu (5) Gholamreza Haffari (4) Jun Wang (3) Chenchen Xu (3) Pasquale Minervini (2) Mark Dras (2) Zhuang Li (2)

Research topics

Privacy (4) Differential Privacy (1)

Keywords

backdoor attack (6) text generation (5) model extraction (5) natural language processing (3) text rewriting (3) adversarial attack (3) large language model (3) imitation attack (3) api security (3) intellectual property (3) data leakage (2) text classification (2) few-shot learning (2) knowledge distillation (2) adversarial defense (2) privacy leakage (2) zero-shot learning (2) domain adaptation (2) text simplification (2) natural language generation (2)

Papers

Activation Decomposition and Steering for LLM Backdoor Remediation ACL 2026 GRADA: Graph-based Reranking against Adversarial Documents Attack EMNLP 2025 PatentScore: Multi-dimensional Evaluation of LLM-Generated Patent Claims EMNLP 2025 NAP2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human EMNLP 2025 Cut the Deadwood Out: Backdoor Purification via Guided Module Substitution EMNLP 2025 WET: Overcoming Paraphrasing Vulnerabilities in Embeddings-as-a-Service with Linear Transformation Watermarks ACL 2025 ALGEN: Few-shot Inversion Attacks on Textual Embeddings via Cross-Model Alignment and Generation ACL 2025 TUBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning ACL 2025 Seeing the Forest through the Trees: Data Leakage from Partial Transformer Gradients EMNLP 2024 Here’s a Free Lunch: Sanitizing Backdoored Models with Model Merge ACL 2024 Backdoor Attacks on Multilingual Machine Translation NAACL 2024 WARDEN: Multi-Directional Backdoor Watermarks for Embedding-as-a-Service Copyright Protection ACL 2024 Security Challenges in Natural Language Processing Models EMNLP 2023 Humanly Certifying Superhuman Classifiers ICLR 2023 Rethinking Round-Trip Translation for Machine Translation Evaluation ACL 2023 Mitigating Backdoor Poisoning Attacks through the Lens of Spurious Correlation EMNLP 2023 Boot and Switch: Alternating Distillation for Zero-Shot Dense Retrieval EMNLP 2023 Variational Autoencoder with Disentanglement Priors for Low-Resource Task-Specific Natural Language Generation EMNLP 2022 Protecting Intellectual Property of Language Generation APIs with Lexical Watermark AAAI 2022 Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIs COLING 2022 Extracted BERT Model Leaks More Information than You Think! EMNLP 2022 CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks NIPS 2022 Model Extraction and Adversarial Transferability, Your BERT is Vulnerable! NAACL 2021 Personal Information Leakage Detection in Conversations EMNLP 2020 ALTER: Auxiliary Text Rewriting Tool for Natural Language Generation EMNLP 2019 ALTER: Auxiliary Text Rewriting Tool for Natural Language Generation IJCNLP 2019 EPUTION at SemEval-2018 Task 2: Emoji Prediction with User Adaption SEMEVAL 2018 Demographic Inference on Twitter using Recursive Neural Networks ACL 2017 Using Deep Linguistic Features for Finding Deceptive Opinion Spam COLING 2012