Thai Le
25 papers · 2020–2026 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
🗺️ Taxonomy Completionist (39) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🐣 Hot Topic Early Bird
🔬
Deep Specialist
(10)
🤝
Dynamic Duo
(13)
⚡
Prolific Year · Productive
🔥
Unstoppable · Bronze
❓
The Questioner
💎
Century Club · Bronze
🌈
Renaissance Researcher
(6)
🗃️
Keyword Collector
(99)
Top co-authors
Research topics
Machine Learning
(20)
Natural Language Processing
(16)
Artificial Intelligence
(15)
Core AI
(14)
Learning Types · Machine Learning
(13)
Application Areas
(10)
Applications · Natural Language Processing
(10)
Resources & Methods
(6)
Deep Learning
(5)
Core Methods
(5)
Generation
(4)
Learning Types · Deep Learning
(4)
Computer Science
(2)
Applications · Computer Science
(2)
Interdisciplinary
(1)
Keywords
adversarial attack
(9)
text classification
(8)
authorship attribution
(8)
large language model
(5)
language model
(4)
machine-generated text detection
(3)
authorship verification
(2)
explainable ai
(2)
authorship obfuscation
(2)
adversarial robustness
(2)
parameter-efficient fine-tuning
(2)
pre-trained language model
(2)
text perturbation
(2)
deepfake detection
(2)
black-box attack
(2)
adversarial defense
(2)
neural text generation
(2)
domain adaptation
(2)
misinformation detection
(2)
transformer model
(2)
Papers
PARASITE: Conditional System Prompt Poisoning to Hijack LLMs
ACL 2026
Style-First Authorship Verification for Academic Integrity in the Generative AI Era (Student Abstract)
AAAI 2026
Harry Potter is Still Here! Probing Knowledge Leakage in Targeted Unlearned Large Language Models
EMNLP 2025
NOMATTERXAI: Generating “No Matter What” Alterfactual Examples for Explaining Black-Box Text Classification Models
AAAI 2025
PlagBench: Exploring the Duality of Large Language Models in Plagiarism Generation and Detection
NAACL 2025
The Dangers of Indirect Prompt Injection Attacks on LLM-based Autonomous Web Navigation Agents: A Demonstration
EMNLP 2025
Turing's Echo: Investigating Linguistic Sensitivity of Deepfake Voice Detection via Gamification
Interspeech 2025
Unraveling Interwoven Roles of Large Language Models in Authorship Privacy: Obfuscation, Mimicking, and Verification
EMNLP 2025
What You Read Isn’t What You Hear: Linguistic Sensitivity in Deepfake Speech Detection
EMNLP 2025
A Curious Case of Searching for the Correlation between Training Data and Adversarial Robustness of Transformer Textual Models
ACL 2024
Adapters Mixup: Mixing Parameter-Efficient Adapters to Enhance the Adversarial Robustness of Fine-tuned Pre-trained Text Classifiers
EMNLP 2024
ALISON: Fast and Effective Stylometric Authorship Obfuscation
AAAI 2024
A Ship of Theseus: Curious Cases of Paraphrasing in LLM-Generated Texts
ACL 2024
Catch Me If You GPT: Tutorial on Deepfake Texts
NAACL 2024
Generalizability of Mixture of Domain-Specific Adapters from the Lens of Signed Weight Directions and its Application to Effective Model Pruning
ACL 2024
“Are Your Explanations Reliable?” Investigating the Stability of LIME in Explaining Text Classifiers by Marrying XAI and Adversarial Attack
EMNLP 2023
HANSEN: Human and AI Spoken Text Benchmark for Authorship Analysis
EMNLP 2023
MULTITuDE: Large-Scale Multilingual Machine-Generated Text Detection Benchmark
EMNLP 2023
UPTON: Preventing Authorship Leakage from Public Text Release via Data Poisoning
EMNLP 2023
Detecting False Claims in Low-Resource Regions: A Case Study of Caribbean Islands
ACL 2022
Perturbations in the Wild: Leveraging Human-Written Text Perturbations for Realistic Adversarial Attack and Defense
ACL 2022
SHIELD: Defending Textual Neural Networks against Multiple Black-Box Adversarial Attacks with Stochastic Multi-Expert Patcher
ACL 2022
A Sweet Rabbit Hole by DARCY: Using Honeypots to Detect Universal Trigger’s Adversarial Attacks
ACL 2021
TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation
EMNLP 2021
Authorship Attribution for Neural Text Generation
EMNLP 2020