LZLingchen Zhao

Lingchen Zhao

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Lingchen Zhao has a total of 82 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    PolyVoice: Exploiting Cluster-Level Vulnerabilities for One-to-Many Impersonation in Speaker Verification Systems

    by Yunjie Ge, Jinlong Jiang, Yuchen Liu, Huayi Duan, Shenyi Zhang, Lingchen Zhao, Chao Shen, Qian Wang

  • Open Access

    MMAligner: Safeguarding Multimodal Large Language Models through Representation Calibration

    by Shenyi Zhang, Keyan Guo, Zihao Wang, Xuebin Li, Lingchen Zhao, Hongxin Hu, Chao Shen, Qian Wang

  • Divide and Conquer: Policy-Aware Jailbreak Defense for Large Language Models

    by Yuchen Zhai, Shengnan Guo, Shenyi Zhang, Lingchen Zhao

  • Boosting Adversarial Transferability With Low-Cost Optimization via Maximin Expected Flatness

    by Chunlin Qiu, Ang Li, Yiheng Duan, Shenyi Zhang, Yuanjie Zhang, Lingchen Zhao, Qian Wang

    Transfer-based attacks craft adversarial examples on white-box surrogate models and directly deploy them against black-box target models, offering practical query-free threat scenarios. While flatness-enhanced methods have recently emerged to improve transferability by enhancing the loss surface flatness of adversarial examples, their divergent flatness definitions and heuristic attack designs suffer from unexamined optimization limitations and missing theoretical foundation, thus constraining their effectiveness and efficiency. This work exposes the severely imbalanced exploitation-exploration dynamics in flatness optimization, establishing the first theoretical foundation for flatness-based transferability and proposing a principled framework to overcome these optimization pitfalls. Specifically, we systematically unify fragmented flatness definitions across existing methods, revealing their imbalanced optimization limitations in over-exploration of sensitivity peaks or over-exploitation of local plateaus. To resolve these issues, we rigorously formalize average-case flatness and transferability gaps, proving that enhancing zeroth-order average-case flatness minimizes cross-model discrepancies. Building on this theory, we design a Maximin Expected Flatness (MEF) attack that enhances zeroth-order average-case flatness while balancing flatness exploration and exploitation. Extensive evaluations across 33 models and 43 current transfer-based attacks demonstrate MEF’s superiority: it surpasses the state-of-the-art PGN attack by 4% in attack success rate at half the computational cost and achieves 8% higher success rate under the same budget. When combined with input augmentation, MEF attains 15% additional gains against defense-equipped models, establishing new robustness benchmarks. Our code is available at https://github.com/SignedQiu/MEFAttack.


  • Open Access

    SyncGait: Robust Long-Distance Authentication for Drone Delivery via Implicit Gait Behaviors

    by Zijian Ling, Man Zhou, Hongda Zhai, Yating Huang, Lingchen Zhao, Qi Li, Chao Shen, Qian Wang

    In recent years, drone delivery, which utilizes unmanned aerial vehicles (UAVs) for package delivery and pickup, has gradually emerged as a crucial method in logistics. Since delivery drones are expensive and may carry valuable packages, they must maintain a safe distance from individuals until user-drone mutual authentication is confirmed. Despite numerous authentication schemes being developed, existing solutions are limited in authentication distance and lack resilience against sophisticated attacks. To this end, we introduce SyncGait, an implicit gait-based mutual authentication system for drone delivery. SyncGait leverages the user's unique arm swing as he walks toward the drone to achieve mutual authentication without requiring additional hardware or specific authentication actions. We conducted extensive experiments on 14 datasets collected from 31 subjects. The results demonstrate that SyncGait achieves an average accuracy of 99.84\% at a long distance ($>18m$) and exhibits strong resilience against various spoofing attacks, making it a robust, secure, and user-friendly solution in real-world scenarios.

  • When Unlearnable Examples Cooperate With Watermarking: A Dual Voice Data Protection Against Unauthorized Exploitation

    by Yunjie Ge, Ruxi Gu, Yuchen Liu, Lingchen Zhao, Bo Du, Qian Wang

    Voice data is crucial for modern artificial intelligence (AI) systems, powering various applications from speaker recognition (SR) to AI-generated content. The reliance on massive data raises serious concerns about privacy and property rights due to potential unauthorized misuse. Unfortunately, no effective method has been proposed to protect the privacy and copyright of voice data while meeting perceptual audio quality requirements. To bridge this gap, we introduce Volto, a unified dual-function framework for generating unlearnable yet traceable voice examples. Volto jointly integrates unlearnable perturbations and learnable watermarks, exploiting weaknesses in both human auditory perception and deep neural network (DNN) representations. This synergistic design enables Volto to corrupt critical model-sensitive features, hindering unauthorized model learning, while encoding watermark signals that remain recoverable for ownership verification. The unlearnable examples can confuse DNNs while preserving the perceptual quality, reducing the accuracy of unauthorized models by more than 21.44% in black-box scenarios. Volto also introduces a verifiable watermark, providing robust evidence of data ownership. Our work effectively balances protection effectiveness and usability, offering an effective defense for voice privacy.

  • When Deepfake Meets Backdoor: Leveraging GAN Fingerprints for Data Poisoning Attack

    by Yiru Zhao, Yiran Ma, Yunjie Ge, Lingchen Zhao, Lei Zhao, Qian Wang

    Deep Neural Networks are vulnerable to data poisoning attacks, which inject a backdoor by poisoning the training data set with a predefined trigger pattern. However, most existing studies design trigger patterns as exogenous features introduced to clean samples (such as a checkerboard patch), whereas the endogenous features inherited from sample origins (such as deep generative models) have not been investigated yet. In this study, we investigate the efficacy of utilizing Generative Adversarial Network fingerprints to design trigger patterns by examining three attack patterns: the all-label attack, label-specific attack, and semantic-specific attack. Specifically, we select training data that satisfies the requirements of various attack patterns, train a GAN model, and employ samples embedded with GAN fingerprints to generate poisoned data sets. Our evaluations on three data sets (CIFAR-10, GTSRB, and LSUN) demonstrate that employing GAN fingerprints as trigger patterns 1) can achieve average attack success rate results of 39.40% in all-label attack, 89.84% in label-specific attack, and 91.06% in semantic-specific attack, 2) is stealthy by reducing the probability of being exposed, and 3) can resist six existing backdoor detection techniques, three backdoor erasing techniques, and two deepfake detection techniques. Furthermore, it exhibits practical applicability in federated learning scenario.


  • WaveTrap: A Clean-Label Poisoning Attack Against Unauthorized Voice Data Collection

    by Yuanjie Zhang, Yunjie Ge, Lingchen Zhao, Qian Wang

    Voice data is essential for training audio intelligence systems, yet its collection often faces ethical and logistical barriers due to privacy concerns. The high cost of acquiring legally consented voice data incentivizes malicious actors to covertly harvest sensitive acoustic information. To counteract such threats, we propose Wave-Trap, a clean-label poisoning attack designed to sabotage voice data while preserving its human-perceivable intelligibility. Our method introduces imperceptible perturbations into audio signals, manipulating their Mel Frequency Cepstral Coefficients (MFCCs)—a critical feature representation in audio processing—to embed stealthy poisoning patterns. When poisoned data is utilized for model fine-tuning or training, these perturbed MFCCs degrade the efficacy of downstream audio intelligence tasks. Extensive experiments demonstrate the efficacy of WaveTrap against two typical audio recognition systems: speaker recognition (SR) and speech command recognition (SCR). For instance, the accuracy of VggVox drops by 30.34% when only 10% of the poisoned voice data is used for fine-tuning, and by 7.28% when 10% of the training data is poisoned.

  • IntentBreaker: Intent-Adaptive Jailbreak Attack on Large Language Models

    by Shengnan Guo, Yuchen Zhai, Shenyi Zhang, Lingchen Zhao, Zhangyi Wang


  • Sonicumos: An Enhanced Active Face Liveness Detection System via Ultrasonic and Video Signals

    by Yihao Wu, Peipei Jiang, Jianhao Cheng, Lingchen Zhao, Chao Shen, Cong Wang, Qian Wang

    Sonicumos is an enhanced behavior-based face liveness detection system that combines ultrasonic and video signals to sense the 3D head gestures. As face authentication becomes increasingly prevalent, the need for a reliable liveness detection system is paramount. Traditional behavior-based liveness detection methods (e.g., eye-blinking, nodding, etc.), which are widely deployed in mission-critical scenarios like finance and banking applications today, are prone to advanced media-based facial forgery attacks. Sonicumos aims to incorporate the traditional behavior-based method for active liveness detection without introducing extra user burden. By employing ultrasonic signals, Sonicumos capitalizes on the head gestures, significantly raising the security bar. Our approach utilizes the frequency-modulated continuous-wave (FMCW) ultrasonic radar for robust 3D gesture recognition compatible with face authentication. We also propose a new dual-feature fusion network that integrates audio and video features at the feature level to increase detection accuracy and resilience against numerous attacks. Our prototype has been tested on seven off-the-shelf Android/iOS smartphones, achieving an overall detection accuracy of 95.83% at an equal error rate (EER) of 4.96% when dealing with 3D impersonation attacks.