SLSichu Liang

Sichu Liang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Sichu Liang has a total of 12 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Auditing Partial Dataset Usage in Large Language Models via Fuzzy Membership Aggregation

    by Hongyu Zhu, Sichu Liang, Bofan Chen, Shi-Lin Wang, Zhuosheng Zhang, Weiping Ding

    The remarkable capabilities of Large Language Models (LLMs) are fueled by massive internet-scale corpora. However, scraped data owners often do not consent to its use for training, raising significant legal and ethical concerns over copyright and privacy. Data auditing techniques seek to verify whether a protected dataset was used in training a target LLM, typically framing the task as membership inference: estimating binary sample-level membership and aggregating to a dataset-level decision. In this paper, we identify a fundamental limitation of this crisp binary paradigm: in realistic training pipelines, datasets are rarely used in full. Instead, models are trained on mixtures of partial subsets drawn from multiple sources. Existing auditing techniques, built upon an all-or-none assumption—declaring a dataset either entirely present or absent from training—collapse in partial dataset usage scenarios. Their predictions fluctuate unpredictably with the member ratio, causing unstable performance and high false-negative rates. Inspired by fuzzy set theory, we relax the crisp notion of binary membership to a continuous fuzzy membership in [0,1], quantifying each sample's degree of inclusion in the model's training set. We establish a theoretical bridge between sample-level fuzzy memberships and the dataset-level usage ratio, facilitating inference of the proportion of a protected dataset used during training. A neural network fuzzifier first estimates sample-level fuzzy memberships from binary labels in a reference set, then refines them using dataset-level member ratios as higher-order supervision. Finally, a defuzzification stage aggregates calibrated memberships to determine partial usage. Across LLMs of varying scales and multiple auditing datasets, our Fuzzy Auditor substantially outperforms state-of-the-art crisp binary techniques in detecting partial usage, estimating member proportions, and identifying individual member samples.

  • Open Access

    Revisiting Data Auditing in Large Vision-Language Models

    by Hongyu Zhu, Sichu Liang, Wenwen Wang, Boheng Li, Tongxin Yuan, Fangqi Li, Hanyi Wang, Shi-Lin Wang, Zhuosheng Zhang


  • Open Access

    Reliable Model Watermarking: Defending against Theft without Compromising on Evasion

    by Hongyu Zhu, Sichu Liang, Wentao Hu, Li Fangqi, Ju Jia, Shi-Lin Wang

    With the rise of Machine Learning as a Service (MLaaS) platforms, safeguarding the intellectual property of deep learning models is becoming paramount. Among various protective measures, trigger set watermarking has emerged as a flexible and effective strategy for preventing unauthorized model distribution. However, this paper identifies an inherent flaw in the current paradigm of trigger set watermarking: evasion adversaries can readily exploit the shortcuts created by models memorizing watermark samples that deviate from the main task distribution, significantly impairing their generalization in adversarial settings. To counteract this, we leverage diffusion models to synthesize unrestricted adversarial examples as trigger sets. By learning the model to accurately recognize them, unique watermark behaviors are promoted through knowledge injection rather than error memorization, thus avoiding exploitable shortcuts. Furthermore, we uncover that the resistance of current trigger set watermarking against removal attacks primarily relies on significantly damaging the decision boundaries during embedding, intertwining unremovability with adverse impacts. By optimizing the knowledge transfer properties of protected models, our approach conveys watermark behaviors to extraction surrogates without aggressive decision boundary perturbation. Experimental results on CIFAR-10/100 and Imagenette datasets demonstrate the effectiveness of our method, showing not only improved robustness against evasion adversaries but also superior resistance to watermark removal attacks compared to state-of-the-art solutions.