publications

2024

  1. Preprint
    Unveiling Concept Attribution in Diffusion Models
    Quang H Nguyen, Hoang Phan, and Khoa D Doan
    2024
  2. ICLR
    Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks
    Quang H Nguyen, Nguyen Ngoc-Hieu, The-Anh Ta, and 4 more authors
    In International Conference on Learning Representations, 2024
  3. Preprint
    MetaLLM: A High-performant and Cost-efficient Dynamic Framework for Wrapping LLMs
    Quang H Nguyen, Duy C Hoang, Juliette Decugis, and 3 more authors
    2024
  4. ACL Findings
    Fooling the Textual Fooler via Randomizing Latent Representations
    Duy C Hoang, Quang H Nguyen, Saurav Manchanda, and 3 more authors
    In Findings of the Association for Computational Linguistics: ACL 2024, 2024
  5. ICLR
    Understanding the Robustness of Randomized Feature Defense Against Query-Based Adversarial Attacks
    Quang H Nguyen, Yingjie Lao, Tung Pham, and 2 more authors
    In The Twelfth International Conference on Learning Representations, 2024

2023

  1. Preprint
    Synthesizing Physical Backdoor Datasets: An Automated Framework Leveraging Deep Generative Models
    Sze Jue Yang, Chinh D La, Quang H Nguyen, and 4 more authors
    2023
  2. NeurIPS Workshop
    Clean-label Backdoor Attacks by Selectively Poisoning with Limited Information from Target Class
    Quang H Nguyen, Ngoc-Hieu Nguyen, Thanh Nguyen-Tang, and 3 more authors
    In NeurIPS 2023 Workshop on Backdoors in Deep Learning-The Good, the Bad, and the Ugly, 2023
  3. Preprint
    Everyone Can Attack: Repurpose Lossy Compression as a Natural Backdoor Attack
    Sze Jue Yang, Quang H Nguyen, Chee Seng Chan, and 1 more author
    2023
  4. ICML Workshop
    A Cosine Similarity-based Method for Out-of-Distribution Detection
    Nguyen Ngoc-Hieu, Quang H Nguyen, The-Anh Ta, and 3 more authors
    In ICML 2023: The Second Workshop on Spurious Correlations, Invariance and Stability , 2023