arXiv subjects

Tianming Zhao

Publications and source records attributed to Tianming Zhao.

6 recordsLinked to original sources

arXiv2024

Act in Collusion: Distributed Multi-Target Backdoor Attacks in Federated Learning

Federated learning (FL) is widely used in Internet-of-Things (IoT) systems, but its distributed training process also exposes it to backdoor attacks. Existing studies mainly consider single-target or centralized multi-target settings, while coordinated distributed multi-target attacks remain underexplored. In practical IoT scenarios, one adversarial entity may control multiple distributed malicious clients and assign each client distinct triggers and target labels. Under this setting, existing distributed backdoor methods often fail to preserve the effectiveness of all backdoors because malicious updates conflict during aggregation. To address this issue, we propose a Distributed Multi-Target Backdoor Attack (DMBA) for FL. DMBA introduces a Backdoor Replay (BR) mechanism to reduce discrepancies among malicious gradients and a Channel-Frequency Composite Trigger (CFCT) strategy to improve trigger distinguishability and alleviate local interference. Experiments on multiple datasets show that DMBA ensures attack success rates above 80% for all implanted backdoors, whereas some baseline backdoors fall below 50% and may even approach 0.

cs.CV↗

arXiv2022

EarSpy: Spying Caller Speech and Identity through Tiny Vibrations of Smartphone Ear Speakers

Eavesdropping from the user's smartphone is a well-known threat to the user's safety and privacy. Existing studies show that loudspeaker reverberation can inject speech into motion sensor readings, leading to speech eavesdropping. While more devastating attacks on ear speakers, which produce much smaller scale vibrations, were believed impossible to eavesdrop with zero-permission motion sensors. In this work, we revisit this important line of reach. We explore recent trends in smartphone manufacturers that include extra/powerful speakers in place of small ear speakers, and demonstrate the feasibility of using motion sensors to capture such tiny speech vibrations. We investigate the impacts of these new ear speakers on built-in motion sensors and examine the potential to elicit private speech information from the minute vibrations. Our designed system EarSpy can successfully detect word regions, time, and frequency domain features and generate a spectrogram for each word region. We train and test the extracted data using classical machine learning algorithms and convolutional neural networks. We found up to 98.66% accuracy in gender detection, 92.6% detection in speaker detection, and 56.42% detection in digit detection (which is 5X more significant than the random selection (10%)). Our result unveils the potential threat of eavesdropping on phone conversations from ear speakers using motion sensors.

cs.SD↗

arXiv2022

A Survey on Biometrics Authentication

Nowadays, traditional authentication methods are vulnerable to face attacks that are often based on inherent security issues. Professional attackers leverage adversarial offenses on the security holes. Biometrics has intrinsic advantages to overcome the traditional authentication methods on security, success rates, efficiency, and accessibility. Biometrics has wide prospects to implement various applications in fields. Whether in authentication security or clinical medicine, biometrics is one of the mainstream studies. In this paper, we surveyed and reviewed some related studies of biometrics, which are outstanding and significant in driving the development and popularization of biometrics. Although they still have some inherent disadvantages to restrict popularization, these obstacles could not conceal the promising future of biometrics. Multi-factors continuous biometrics authentication has become the mainstream trend of development. We reflect the findings as well as the challenges of the studies in the survey paper.

cs.CR↗

arXiv2022

RIBAC: Towards Robust and Imperceptible Backdoor Attack against Compact DNN

Recently backdoor attack has become an emerging threat to the security of deep neural network (DNN) models. To date, most of the existing studies focus on backdoor attack against the uncompressed model; while the vulnerability of compressed DNNs, which are widely used in the practical applications, is little exploited yet. In this paper, we propose to study and develop Robust and Imperceptible Backdoor Attack against Compact DNN models (RIBAC). By performing systematic analysis and exploration on the important design knobs, we propose a framework that can learn the proper trigger patterns, model parameters and pruning masks in an efficient way. Thereby achieving high trigger stealthiness, high attack success rate and high model efficiency simultaneously. Extensive evaluations across different datasets, including the test against the state-of-the-art defense mechanisms, demonstrate the high robustness, stealthiness and model efficiency of RIBAC. Code is available at https://github.com/huyvnphan/ECCV2022-RIBAC

cs.CR↗

arXiv2021

GUIGAN: Learning to Generate GUI Designs Using Generative Adversarial Networks

Graphical User Interface (GUI) is ubiquitous in almost all modern desktop software, mobile applications, and online websites. A good GUI design is crucial to the success of the software in the market, but designing a good GUI which requires much innovation and creativity is difficult even to well-trained designers. Besides, the requirement of the rapid development of GUI design also aggravates designers' working load. So, the availability of various automated generated GUIs can help enhance the design personalization and specialization as they can cater to the taste of different designers. To assist designers, we develop a model GUIGAN to automatically generate GUI designs. Different from conventional image generation models based on image pixels, our GUIGAN is to reuse GUI components collected from existing mobile app GUIs for composing a new design that is similar to natural-language generation. Our GUIGAN is based on SeqGAN by modeling the GUI component style compatibility and GUI structure. The evaluation demonstrates that our model significantly outperforms the best of the baseline methods by 30.77% in Frechet Inception distance (FID) and 12.35% in 1-Nearest Neighbor Accuracy (1-NNA). Through a pilot user study, we provide initial evidence of the usefulness of our approach for generating acceptable brand new GUI designs.

cs.HC↗

arXiv2020

A highly efficient integrated source of twisted single-photons

Photons with a helical phase front (twisted photons) can carry a discrete, in principle, unbounded amount of orbital angular momentum (OAM). Twisted single-photons have been demonstrated as a high-dimensional quantum system with information processing ability far beyond the widely used two-level qubits. To date, the generations of single-photons carrying OAM merely rely on the non-linear process in bulk crystals, e.g., spontaneous parametric down-conversion (SPDC), which unavoidably limits both the efficiency and the scalability of the source. Therefore, an on-demand OAM quantum light source on a semiconductor chip is yet illusive and highly desirable for integrated photonic quantum technologies. Here we demonstrate highly-efficient emission of twisted single-photons from solid-state quantum emitters embedded in a microring with angular gratings. The cavity QED effect allows the generations of single-photons and encoding OAM in the same nanostructure and therefore enables the realization of devices with very small footprints and great scalability. The OAM states of singe-photons are clearly identified via quantum interference of single-photons with themselves. Our device may boost the development of integrated quantum photonic devices with potential applications towards high-dimensional quantum information processing.

physics.optics↗