PPaperPicks

Thai Le

17 papers at tracked venues · 7 at CORE A* · active 2024–2026

DBLP profile ↗ORCID search ↗

Venues

EMNLP ×5ACL ×4AAAI ×3AAMAS ×1ECAI ×1ICWSM ×1InterSpeech ×1NAACL ×1

Frequent coauthors

Dongwon Lee
×5
Tuc Nguyen
×4
Adaku Uchendu
×3
Viet Pham
×2
Binh Nguyen
×2
Saranya Venkatraman
×2
Jun Jang
×1
Bo Wang
×1
Bang Trinh Tran To
×1
James Michels
×1
Hua Shen
×1
Yiran Ye
×1

Papers

  1. PARASITE: Conditional System Prompt Poisoning to Hijack LLMs
    ACL 2026 ·
    Viet Pham
    , Thai Le
  2. Style-First Authorship Verification for Academic Integrity in the Generative AI Era (Student Abstract)
    AAAI 2026 ·
    Jun Jang
    , Thai Le,
    Bo Wang
  3. Harry Potter is Still Here! Probing Knowledge Leakage in Targeted Unlearned Large Language Models
    EMNLP 2025 ·
    Bang Trinh Tran To
    , Thai Le
  4. NOMATTERXAI: Generating "No Matter What" Alterfactual Examples for Explaining Black-Box Text Classification Models
    AAAI 2025 ·
    Tuc Van Nguyen
    ,
    James Michels
    ,
    Hua Shen
    , Thai Le
  5. NoisyHate: Mining Online Human-Written Perturbations for Realistic Robustness Benchmarking of Content Moderation Models
    ICWSM 2025 ·
    Yiran Ye
    , Thai Le,
    Dongwon Lee
  6. PlagBench: Exploring the Duality of Large Language Models in Plagiarism Generation and Detection
    NAACL 2025 ·
    Jooyoung Lee
    ,
    Toshini Agrawal
    ,
    Adaku Uchendu
    , Thai Le,
    Jinghui Chen
    ,
    Dongwon Lee
  7. The Dangers of Indirect Prompt Injection Attacks on LLM-based Autonomous Web Navigation Agents: A Demonstration
    EMNLP 2025 ·
    Sam Johnson
    ,
    Viet Pham
    , Thai Le
  8. Turing's Echo: Investigating Linguistic Sensitivity of Deepfake Voice Detection via Gamification
    InterSpeech 2025 ·
    Binh Nguyen
    , Thai Le
  9. Unraveling Interwoven Roles of Large Language Models in Authorship Privacy: Obfuscation, Mimicking, and Verification
    EMNLP 2025 ·
    Tuc Nguyen
    ,
    Yifan Hu
    , Thai Le
  10. What You Read Isn't What You Hear: Linguistic Sensitivity in Deepfake Speech Detection
    EMNLP 2025 ·
    Binh Nguyen
    ,
    Shuju Shi
    ,
    Ryan Ofman
    , Thai Le
  11. xSRL: Safety-Aware Explainable Reinforcement Learning - Safety as a Product of Explainability
    AAMAS 2025 ·
    Risal Shahriar Shefin
    ,
    Md Asifur Rahman
    , Thai Le,
    Sarra M. Alqahtani
  12. A Curious Case of Searching for the Correlation between Training Data and Adversarial Robustness of Transformer Textual Models
    ACL 2024 ·
    Cuong Dang
    ,
    Dung D. Le
    , Thai Le
  13. A Ship of Theseus: Curious Cases of Paraphrasing in LLM-Generated Texts
    ACL 2024 ·
    Nafis Irtiza Tripto
    ,
    Saranya Venkatraman
    ,
    Dominik Macko
    ,
    Róbert Móro
    ,
    Ivan Srba
    ,
    Adaku Uchendu
    , Thai Le,
    Dongwon Lee
  14. ALISON: Fast and Effective Stylometric Authorship Obfuscation
    AAAI 2024 ·
    Eric Xing
    ,
    Saranya Venkatraman
    , Thai Le,
    Dongwon Lee
  15. Adapters Mixup: Mixing Parameter-Efficient Adapters to Enhance the Adversarial Robustness of Fine-tuned Pre-trained Text Classifiers
    EMNLP 2024 ·
    Tuc Nguyen
    , Thai Le
  16. Generalizability of Mixture of Domain-Specific Adapters from the Lens of Signed Weight Directions and its Application to Effective Model Pruning
    ACL 2024 ·
    Tuc Nguyen
    , Thai Le
  17. TopFormer: Topology-Aware Authorship Attribution of Deepfake Texts with Diverse Writing Styles
    ECAI 2024 ·
    Adaku Uchendu
    , Thai Le,
    Dongwon Lee