Search Results - Xu, Qiongkai

Refine Results
  1. 1
    Deep Neural Networks for Learning Graph Representations

    Deep Neural Networks for Learning Graph Representations by Cao, Shaosheng, Lu, Wei, Xu, Qiongkai

    Get full text
    Items that cite this one
    Article
    Save to List
    Saved in:
  2. 2
    SEEP: Training Dynamics Grounds Latent Representation Search for Mitigating Backdoor Poisoning Attacks

    SEEP: Training Dynamics Grounds Latent Representation Search for Mitigating Backdoor Poisoning Attacks by He, Xuanli, Xu, Qiongkai, Wang, Jun, Rubinstein, Benjamin I. P., Cohn, Trevor

    Get full text
    Items that this one cites
    Article
    Save to List
    Saved in:
  3. 3
    Raster adaptive optics for video rate aberration correction and large FOV multiphoton imaging

    Raster adaptive optics for video rate aberration correction and large FOV multiphoton imaging by Li, Yongxiao, Lim, Yean J, Xu, Qiongkai, Beattie, Lynette, Gardiner, Elizabeth E, Gaus, Katharina, Heath, William R, Lee, Woei Ming

    Get full text
    Items that this one cites
    Items that cite this one
    Article
    Save to List
    Saved in:
  4. 4
    Protecting Intellectual Property of Language Generation APIs with Lexical Watermark

    Protecting Intellectual Property of Language Generation APIs with Lexical Watermark by He, Xuanli, Xu, Qiongkai, Lyu, Lingjuan, Wu, Fangzhao, Wang, Chenguang

    Get full text
    Items that cite this one
    Conference Proceeding
    Save to List
    Saved in:
  5. 5
    Seeing the Forest through the Trees: Data Leakage from Partial Transformer Gradients

    Seeing the Forest through the Trees: Data Leakage from Partial Transformer Gradients by Li, Weijun, Xu, Qiongkai, Dras, Mark

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:
  6. 6
    WET: Overcoming Paraphrasing Vulnerabilities in Embeddings-as-a-Service with Linear Transformation Watermarks

    WET: Overcoming Paraphrasing Vulnerabilities in Embeddings-as-a-Service with Linear Transformation Watermarks by Shetty, Anudeex, Xu, Qiongkai, Jey Han Lau

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:
  7. 7
    Training-free Lexical Backdoor Attacks on Language Models

    Training-free Lexical Backdoor Attacks on Language Models by Huang, Yujin, Terry Yue Zhuo, Xu, Qiongkai, Hu, Han, Yuan, Xingliang, Chen, Chunyang

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:
  8. 8
    Fingerprint Attack: Client De-Anonymization in Federated Learning

    Fingerprint Attack: Client De-Anonymization in Federated Learning by Xu, Qiongkai, Cohn, Trevor, Ohrimenko, Olga

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:
  9. 9
    WARDEN: Multi-Directional Backdoor Watermarks for Embedding-as-a-Service Copyright Protection

    WARDEN: Multi-Directional Backdoor Watermarks for Embedding-as-a-Service Copyright Protection by Shetty, Anudeex, Teng, Yue, He, Ke, Xu, Qiongkai

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:
  10. 10
    Generative Models are Self-Watermarked: Declaring Model Authentication through Re-Generation

    Generative Models are Self-Watermarked: Declaring Model Authentication through Re-Generation by Desu, Aditya, He, Xuanli, Xu, Qiongkai, Lu, Wei

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:
  11. 11
    Boot and Switch: Alternating Distillation for Zero-Shot Dense Retrieval

    Boot and Switch: Alternating Distillation for Zero-Shot Dense Retrieval by Jiang, Fan, Xu, Qiongkai, Drummond, Tom, Cohn, Trevor

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:
  12. 12
    Mitigating Backdoor Poisoning Attacks through the Lens of Spurious Correlation

    Mitigating Backdoor Poisoning Attacks through the Lens of Spurious Correlation by He, Xuanli, Xu, Qiongkai, Wang, Jun, Rubinstein, Benjamin, Cohn, Trevor

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:
  13. 13
    Humanly Certifying Superhuman Classifiers

    Humanly Certifying Superhuman Classifiers by Xu, Qiongkai, Walder, Christian, Xu, Chenchen

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:
  14. 14
    G3Detector: General GPT-Generated Text Detector

    G3Detector: General GPT-Generated Text Detector by Zhan, Haolan, He, Xuanli, Xu, Qiongkai, Wu, Yuxiang, Stenetorp, Pontus

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:
  15. 15
    Rethinking Round-Trip Translation for Machine Translation Evaluation

    Rethinking Round-Trip Translation for Machine Translation Evaluation by Terry Yue Zhuo, Xu, Qiongkai, He, Xuanli, Cohn, Trevor

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:
  16. 16
    TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning

    TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning by He, Xuanli, Wang, Jun, Xu, Qiongkai, Minervini, Pasquale, Stenetorp, Pontus, Rubinstein, Benjamin I P, Cohn, Trevor

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:
  17. 17
    Extracted BERT Model Leaks More Information than You Think

    Extracted BERT Model Leaks More Information than You Think by He, Xuanli, Chen, Chen, Lyu, Lingjuan, Xu, Qiongkai

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:
  18. 18
    IDT: Dual-Task Adversarial Attacks for Privacy Protection

    IDT: Dual-Task Adversarial Attacks for Privacy Protection by Faustini, Pedro, Tonni, Shakila Mahjabin, McIver, Annabelle, Xu, Qiongkai, Dras, Mark

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:
  19. 19
    Here's a Free Lunch: Sanitizing Backdoored Models with Model Merge

    Here's a Free Lunch: Sanitizing Backdoored Models with Model Merge by Arora, Ansh, He, Xuanli, Mozes, Maximilian, Swain, Srinibas, Dras, Mark, Xu, Qiongkai

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:
  20. 20
    Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIs

    Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIs by Xu, Qiongkai, He, Xuanli, Lyu, Lingjuan, Qu, Lizhen, Haffari, Gholamreza

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:

Search Tools: