Qi Li

Qi Li

Auto-generated profile, based on publicly available information

Qi Li

National University of Singapore

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 November 2022 in Applied Mathematics and Computation
Verified
Journal Article
Closed access
QLQi Li
Qi Li
LCLe Cheng
Le Cheng
WWWei Wang
Wei Wang
XLXianghua Li
Xianghua Li
SLshudong li
shudong li
Peican ZhuPeican Zhu
Peican Zhu

21 October 2023
Verified
Conference Paper
Open access
QLQi Li
Qi Li
XLXingyu Li
Xingyu Li
XCXiaodong Cui
Xiaodong Cui
KTKeke Tang
Keke Tang
Peican ZhuPeican Zhu
Peican Zhu
Exploring adversarial attacks on deep neural networks (DNNs) is crucial for assessing and enhancing their adversarial robustness. Among various attack types, hard-label attacks that rely only on predicted labels offer a practical approach. This paper focuses on the challenging task of hard-label attacks within an extremely limited query budget, which is a significant achievement rarely accomplished by existing methods. To tackle this, we propose an attack framework that leverages geometric information from previous perturbation directions to form triangles and employs a heuristic perpendicular trial to effectively utilize the intermediate directions. Extensive experiments validate the effectiveness of our approach under strict query constraints and demonstrate its superiority to the state-of-the-art methods.

18 August 2022 in IEEE Transactions on Dependable and Secure Computing
Verified
Journal Article
Closed access
YLYunji Liang
Yunji Liang
YQYuchen Qin
Yuchen Qin
QLQi Li
Qi Li
XYXiaokai Yan
Xiaokai Yan
LHLuwen Huangfu
Luwen Huangfu
ZYZhiwen Yu
Zhiwen Yu
With the global prevalence of mobile devices, concerns about mobile devices regarding privacy breaches and data leakage are rising. Although sensor permissions are required for mobile applications to access outputs of built-in sensors, motion sensors (e.g., accelerometer and gyroscope) can be visited directly without permission requirement. Extant studies have shown that motion sensors may cause breaches of confidential information, such as passwords, digits, and voice-based commands, but whether it is possible to synthesize intelligible speech waveforms from low-resolution motion sensors has been understudied. In this paper, we present an escalated side-channel attack of built-in speakers by synthesizing intelligible speech waveforms from low-resolution vibration signals. Opposite to traditional classification problems, we formulate this task as a generative problem and introduce an end-to-end synthesis framework dubbed as AccMyrinx to eavesdrop on the speaker via the low-resolution vibration signals. In AccMyrinx, we introduce the data alignment solution to provide the pair-wise voice-vibration sequences and present wavelet-based MelGAN (WMelGAN) with multi-scale time-frequency domain discriminators to generate intelligible acoustic waveforms. We conducted intensive experiments and demonstrated the feasibility of synthesizing the intelligible acoustic signals from low-resolution solid-borne vibration signals. Compared with existing synthesis solutions, our proposed solution outperforms the baselines in both subject and object metrics with the smoothed word error rate of 42.67% and the Mel-Cepstral distortion of 0.298. In addition, the quality of synthetic speeches could be impacted by several factors, including gender, speech rate, volume, and sampling frequency.

21 November 2024
Verified
Book Chapter
Closed access
PDF file
QLQi Li
Qi Li
RYRunpeng Yu
Runpeng Yu
XWXinchao Wang
Xinchao Wang

18 November 2023 in arXiv
Verified
Preprint
Open access
PDF file
QLQi Li
Qi Li
LLLiangzhi Li
Liangzhi Li
ZJZhouqiang Jiang
Zhouqiang Jiang
BWBowen Wang
Bowen Wang
Visual prompting, an efficient method for transfer learning, has shown its potential in vision tasks. However, previous works focus exclusively on VP from standard source models, it is still unknown how it performs under the scenario of a robust source model: Whether a visual prompt derived from a robust model can inherit the robustness while suffering from the generalization performance decline, albeit for a downstream dataset that is different from the source dataset? In this work, we get an affirmative answer of the above question and give an explanation on the visual representation level. Moreover, we introduce a novel technique named Prompt Boundary Loose (PBL) to effectively mitigates the suboptimal results of visual prompt on standard accuracy without losing (or even significantly improving) its adversarial robustness when using a robust model as source model. Extensive experiments across various datasets show that our findings are universal and demonstrate the significant benefits of our proposed method.

16 July 2024 in arXiv
Verified
Preprint
Open access
PDF file
QLQi Li
Qi Li
RYRunpeng Yu
Runpeng Yu
XWXinchao Wang
Xinchao Wang
This paradigm encapsulates knowledge from various models into a solitary prompt without altering the original models or requiring access to the training data, which enables us to achieve efficient and convenient knowledge transfer in more realistic scenarios. From a practicality standpoint, this paradigm not only for the first time proves the effectiveness of Visual Prompt in data inaccessible contexts, but also solves the problems of low model reusability and high storage resource consumption faced by traditional Data-Free Knowledge Transfer, which means that we can realize the parallel knowledge transfer of multiple models without modifying any source model. Extensive experiments across various datasets and models demonstrate the efficacy of the proposed KiOP knowledge transfer paradigm. Without access to real training data and with rigorous storage capacity constraints, it is also capable of yielding considerable outcomes when dealing with cross-model backbone setups and handling parallel knowledge transfer processing requests with multiple (more than 2) models.