Author name cluster

Zi Liang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

9 papers

2 author rows

AAAI Conference 2026 Conference Paper

Class-feature Watermark: A Resilient Black-box Watermark Against Model Extraction Attacks

Yaxin Xiao
Qingqing Ye
Zi Liang
Haoyang Li
Ronghua Li
Huadi Zheng
Haibo Hu

Machine learning models constitute valuable intellectual property, yet remain vulnerable to model extraction attacks (MEA), where adversaries replicate their functionality through black-box queries. Model watermarking counters MEAs by embedding forensic markers for ownership verification. Current black-box watermarks prioritize MEA survival through representation entanglement, yet inadequately explore resilience against sequential MEAs and removal attacks. Our study reveals that this risk is underestimated because existing removal methods are weakened by entanglement. To address this gap, we propose Watermark Removal attacK (WRK), which circumvents entanglement constraints by exploiting decision boundaries shaped by prevailing sample-level watermark artifacts. WRK effectively reduces watermark success rates by ≥88.79% across existing watermarking benchmarks. For robust protection, we propose Class-Feature Watermarks (CFW), which improve resilience by leveraging class-level artifacts. CFW constructs a synthetic class using out-of-domain samples, eliminating vulnerable decision boundaries between original domain samples and their artifact-modified counterparts (watermark samples). CFW concurrently optimizes both MEA transferability and post-MEA stability. Experiments across multiple domains show that CFW consistently outperforms prior methods in resilience, maintaining a watermark success rate of ≥70.15% in extracted models even under the combined MEA and WRK distortion, while preserving the utility of protected models.

PDF Details DOI

AAAI Conference 2026 Conference Paper

How Much Do Large Language Model Cheat on Evaluation? Benchmarking Overestimation Under the One-Time-Pad-Based Framework

Zi Liang
Liantong Yu
Zhang Shiyu
Qingqing Ye
Haibo Hu

Overestimation in evaluating large language models (LLMs) has become an increasing concern. Due to the contamination of public benchmarks or imbalanced model training, LLMs may achieve unreal evaluation results on public benchmarks, either intentionally or unintentionally, which leads to unfair comparisons among LLMs and undermines their realistic capability assessments. Existing benchmarks attempt to address these issues by keeping test cases permanently secret, mitigating contamination through human evaluation, or repeatedly collecting and constructing new samples. However, these approaches fail to ensure reproducibility, transparency, and high efficiency simultaneously. Moreover, the extent of overestimation in current LLMs remains unquantified. To address these issues, we propose ArxivRoll, a dynamic evaluation framework inspired by one-time pad encryption in cryptography. ArxivRoll comprises two key components: i) SCP (Sequencing, Cloze, and Prediction), an automated generator for private test cases, and ii) Rugged Scores (RS), metrics that measure the proportion of public benchmark contamination and training bias. Leveraging SCP, ArxivRoll constructs a new benchmark every six months using recent articles from ArXiv and employs them for one-time evaluations of LLM performance. Extensive experiments demonstrate the high quality of our benchmark, and we provide a systematic evaluation of current LLMs.

PDF Details DOI

ICML Conference 2025 Conference Paper

Does Low Rank Adaptation Lead to Lower Robustness against Training-Time Attacks?

Zi Liang
Haibo Hu 0001
Qingqing Ye 0001
Yaxin Xiao
Ronghua Li

Low rank adaptation (LoRA) has emerged as a prominent technique for fine-tuning large language models (LLMs) thanks to its superb efficiency gains over previous methods. While extensive studies have examined the performance and structural properties of LoRA, its behavior upon training-time attacks remain underexplored, posing significant security risks. In this paper, we theoretically investigate the security implications of LoRA’s low-rank structure during fine-tuning, in the context of its robustness against data poisoning and backdoor attacks. We propose an analytical framework that models LoRA’s training dynamics, employs the neural tangent kernel to simplify the analysis of the training process, and applies information theory to establish connections between LoRA’s low rank structure and its vulnerability against training-time attacks. Our analysis indicates that LoRA exhibits better robustness to backdoor attacks than full fine-tuning, while becomes more vulnerable to untargeted data poisoning due to its over-simplified information geometry. Extensive experimental evaluations have corroborated our theoretical findings.

Details

AAAI Conference 2025 Conference Paper

Exploring Intrinsic Alignments Within Text Corpus

Zi Liang
Pinghui Wang
Ruofei Zhang
Haibo Hu
Shuo Zhang
Qingqing Ye
Nuo Xu
Yaxin Xiao

Recent years have witnessed rapid advancements in the safety alignments of large language models (LLMs). Methods such as supervised instruction fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) have thus emerged as vital components in constructing LLMs. While these methods achieve robust and fine-grained alignment to human values, their practical application is still hindered by high annotation costs and incomplete human alignments. Besides, the intrinsic human values within training corpora have not been fully exploited. To address these issues, we propose ISAAC (Intrinsically Supervised Alignments by Assessing Corpus), a primary and coarse-grained safety alignment strategy for LLMs. ISAAC only relies on a prior assumption about the text corpus, and does not require preferences in RLHF or human responses selection in SFT. Specifically, it assumes a long-tail distribution of text corpus and employs a specialized sampling strategy to automatically sample high-quality responses. Theoretically, we prove that this strategy can improve the safety of LLMs under our assumptions. Empirically, our evaluations on mainstream LLMs show that ISAAC achieves a safety score comparable to current SFT solutions. Moreover, we conduct experiments on ISAAC for some RLHF-based LLMs, where we find that ISAAC can even improve the safety of these models under specific safety domains. These findings demonstrate that ISAAC can provide preliminary alignment to LLMs, thereby reducing the construction costs of existing human-feedback-based methods.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts

Li Bai
Qingqing Ye
Xinwei Zhang
Sen Zhang
Zi Liang
Jianliang Xu
Haibo Hu

Machine learning models are often vulnerable to inference attacks that expose sensitive information from their training data. Shadow model technique is commonly employed in such attacks, like membership inference. However, the need for a large number of shadow models leads to high computational costs, limiting their practical applicability. Such inefficiency mainly stems from the independent training and use of these shadow models. To address this issue, we present a novel shadow pool training framework SHAPOOL, which constructs multiple shared models and trains them jointly within a single process. In particular, we leverage the Mixture-of-Experts mechanism as the shadow pool to interconnect individual models, enabling them to share some sub-networks and thereby improving efficiency. To ensure the shared models closely resemble independent models and serve as effective substitutes, we introduce three novel modules: path-choice routing, pathway regularization, and pathway alignment. These modules guarantee random data allocation for pathway learning, promote diversity among shared models, and maintain consistency with target models. We evaluate SHAPOOL in the context of various membership inference attacks and show that it significantly reduces the computational cost of shadow model construction while maintaining comparable attack performance.

PDF Details

NeurIPS Conference 2025 Conference Paper

Virus Infection Attack on LLMs: Your Poisoning Can Spread "VIA" Synthetic Data

Zi Liang
Qingqing Ye
Xuan Liu
Yanyun Wang
Jianliang Xu
Haibo Hu

Synthetic data refers to artificial samples generated by models. While it has been validated to significantly enhance the performance of large language models (LLMs) during training and has been widely adopted in LLM development, potential security risks it may introduce remain uninvestigated. This paper systematically evaluates the resilience of synthetic-data-integrated training paradigm for LLMs against mainstream poisoning and backdoor attacks. We reveal that such a paradigm exhibits strong resistance to existing attacks, primarily thanks to the different distribution patterns between poisoning data and queries used to generate synthetic samples. To enhance the effectiveness of these attacks and further investigate the security risks introduced by synthetic data, we introduce a novel and universal attack framework, namely, Virus Infection Attack (VIA), which enables the propagation of current attacks through synthetic data even under purely clean queries. Inspired by the principles of virus design in cybersecurity, VIA conceals the poisoning payload within a protective “shell” and strategically searches for optimal hijacking points in benign samples to maximize the likelihood of generating malicious content. Extensive experiments on both data poisoning and backdoor attacks show that VIA significantly increases the presence of poisoning content in synthetic data and correspondingly raises the attack success rate (ASR) on downstream models to levels comparable to those observed in the poisoned upstream models.

PDF Details

AAAI Conference 2024 Conference Paper

MERGE: Fast Private Text Generation

Zi Liang
Pinghui Wang
Ruofei Zhang
Nuo Xu
Shuo Zhang
Lifeng Xing
Haitao Bai
Ziyang Zhou

The drastic increase in language models' parameters has led to a new trend of deploying models in cloud servers, raising growing concerns about private inference for Transformer-based models. Existing two-party privacy-preserving techniques, however, only take into account natural language understanding (NLU) scenarios. Private inference in natural language generation (NLG), crucial for applications like translation and code completion, remains underexplored. In addition, previous privacy-preserving techniques suffer from convergence issues during model training and exhibit poor inference speed when used with NLG models due to the neglect of time-consuming operations in auto-regressive generations. To address these issues, we propose a fast private text generation framework for Transformer-based language models, namely MERGE. MERGE reuses the output hidden state as the word embedding to bypass the embedding computation and reorganize the linear operations in the Transformer module to accelerate the forward procedure. Extensive experiments show that MERGE achieves a 26.5x speedup to the vanilla encrypted model under the sequence length 512, and reduces 80% communication cost, with an up to 10x speedup to state-of-the-art approximated models.

PDF Details DOI

ECAI Conference 2024 Conference Paper

TSFool: Crafting Highly-Imperceptible Adversarial Time Series Through Multi-Objective Attack

Yanyun Wang 0003
Dehui Du
Haibo Hu 0001
Zi Liang
Yuanhao Liu

Recent years have witnessed the success of recurrent neural network (RNN) models in time series classification (TSC). However, neural networks (NNs) are vulnerable to adversarial samples, which cause real-life adversarial attacks that undermine the robustness of AI models. To date, most existing attacks target at feed-forward NNs and image recognition tasks, but they cannot perform well on RNN-based TSC. This is due to the cyclical computation of RNN, which prevents direct model differentiation. In addition, the high visual sensitivity of time series to perturbations also poses challenges to local objective optimization of adversarial samples. In this paper, we propose an efficient method called TSFool to craft highly-imperceptible adversarial time series for RNN-based TSC. The core idea is a new global optimization objective known as “Camouflage Coefficient” that captures the imperceptibility of adversarial samples from the class distribution. Based on this, we reduce the adversarial attack problem to a multi-objective optimization problem that enhances the perturbation quality. Furthermore, to speed up the optimization process, we propose to use a representation model for RNN to capture deeply embedded vulnerable samples whose features deviate from the latent manifold. Experiments on 11 UCR and UEA datasets showcase that TSFool significantly outperforms six white-box and three black-box benchmark attacks in terms of effectiveness, efficiency and imperceptibility from various perspectives including standard measure, human study and real-world defense.

Details

AAAI Conference 2023 Conference Paper

Multi-Action Dialog Policy Learning from Logged User Feedback

Shuo Zhang
Junzhou Zhao
Pinghui Wang
Tianxiang Wang
Zi Liang
Jing Tao
Yi Huang
Junlan Feng

Multi-action dialog policy (MADP), which generates multiple atomic dialog actions per turn, has been widely applied in task-oriented dialog systems to provide expressive and efficient system responses. Existing MADP models usually imitate action combinations from the labeled multi-action dialog samples. Due to data limitations, they generalize poorly toward unseen dialog flows. While reinforcement learning-based methods are proposed to incorporate the service ratings from real users and user simulators as external supervision signals, they suffer from sparse and less credible dialog-level rewards. To cope with this problem, we explore to improve MADPL with explicit and implicit turn-level user feedback received for historical predictions (i.e., logged user feedback) that are cost-efficient to collect and faithful to real-world scenarios. The task is challenging since the logged user feedback provides only partial label feedback limited to the particular historical dialog actions predicted by the agent. To fully exploit such feedback information, we propose BanditMatch, which addresses the task from a feedback-enhanced semi-supervised learning perspective with a hybrid learning objective of SSL and bandit learning. BanditMatch integrates pseudo-labeling methods to better explore the action space through constructing full label feedback. Extensive experiments show that our BanditMatch improves MADPL over the state-of-the-art methods by generating more concise and informative responses. The source code and the appendix of this paper can be obtained from https://github.com/ShuoZhangXJTU/BanditMatch.

PDF Details DOI