Tianfang Zhang

Tianfang Zhang

Auto-generated profile, based on publicly available information

Tianfang Zhang

Rutgers University, New Brunswick, NJ, USA

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
14 October 2022
Verified
Conference Paper
Open access
CSCong Shi
Cong Shi
TZTianfang Zhang
Tianfang Zhang
ZLZhuohang Li
Zhuohang Li
HPHuy Phan
Huy Phan
TZTianming Zhao
Tianming Zhao
YCYingying Chen
Yingying Chen
Deep learning models have become key enablers of voice user interfaces. With the growing trend of adopting outsourced training of these models, backdoor attacks, stealthy yet effective training-phase attacks, have gained increasing attention. They inject hidden trigger patterns through training set poisoning and overwrite the model's predictions in the inference phase. Research in backdoor attacks has been focusing on image classification tasks, while there have been few studies in the audio domain. In this work, we explore the severity of audio-domain backdoor attacks and demonstrate their feasibility under practical scenarios of voice user interfaces, where an adversary injects (plays) an unnoticeable audio trigger into live speech to launch the attack. To realize such attacks, we consider jointly optimizing the audio trigger and the target model in the training phase, deriving a position-independent, unnoticeable, and robust audio trigger. We design new data poisoning techniques and penalty-based algorithms that inject the trigger into randomly generated temporal positions in the audio input during training, rendering the trigger resilient to any temporal position variations. We further design an environmental sound mimicking technique to make the trigger resemble unnoticeable situational sounds and simulate played over-the-air distortions to improve the trigger's robustness during the joint optimization process. Extensive experiments on two important applications (i.e., speech command recognition and speaker recognition) demonstrate that our attack can achieve an average success rate of over 99% under both digital and physical attack settings.

15 November 2023
Verified
Conference Paper
Open access
TZTianfang Zhang
Tianfang Zhang
ZYZhengkun Ye
Zhengkun Ye
AMAhmed Tanvir Mahdad
Ahmed Tanvir Mahdad
MAMojibur Rahman Redoy Akanda
Mojibur Rahman Redoy Akanda
CSCong Shi
Cong Shi
YCYingying Chen
Yingying Chen
The market size of augmented reality and virtual reality (AR/VR) has been expanding rapidly in recent years, with the use of face-mounted headsets extending beyond gaming to various application sectors, such as education, healthcare, and the military. Despite the rapid growth, the understanding of information leakage through sensor-rich headsets remains in its infancy. Some of the headset's built-in sensors do not require users' permission to access, and any apps and websites can acquire their readings. While theseunrestricted sensors are generally considered free of privacy risks, we find that an adversary could uncover private information by scrutinizing sensor readings, making existing AR/VR apps and websites potential eavesdroppers. In this work, we investigate a novel, unobtrusive privacy attack called FaceReader, which reconstructs high-quality vital sign signals (breathing and heartbeat patterns) based on unrestricted AR/VR motion sensors. FaceReader is built on the key insight that the headset is closely mounted on the user's face, allowing the motion sensors to detect subtle facial vibrations produced by users' breathing and heartbeats. Based on the reconstructed vital signs, we further investigate three more advanced attacks, including gender recognition, user re-identification, and body fat ratio estimation. Such attacks pose severe privacy concerns, as an adversary may obtain users' sensitive demographic/physiological traits and potentially uncover their real-world identities. Compared to prior privacy attacks relying on speeches and activities, FaceReader targets spontaneous breathing and heartbeat activities that are naturally produced by the human body and are unobtrusive to victims. In particular, we design an adaptive filter to dynamically mitigate the impacts of body motions. We further employ advanced deep-learning techniques to reconstruct vital sign signals, achieving signal qualities comparable to those of dedicated medical instruments, as well as deriving sensitive gender, identity, and body fat information. We conduct extensive experiments involving 35 users on three types of mainstream AR/VR headsets across 3 months. The results reveal that FaceReader can reconstruct vital signs with low mean errors and accurately detect gender (over 93.33%). The attack can also link/re-identify users across different apps, websites, and longitudinal sessions with over 97.83% accuracy. Furthermore, we present the first successful attempt at revealing body fat information from motion sensor data, achieving a remarkably low estimation error of 4.43%.

22 May 2024 in IEEE Transactions on Mobile Computing
Verified
Journal Article
Closed access
ZTZijie Tang
Zijie Tang
TZTianming Zhao
Tianming Zhao
TZTianfang Zhang
Tianfang Zhang
HPHuy Phan
Huy Phan
YWYan Wang
Yan Wang
YCYingying Chen
Yingying Chen
Deep learning (DL) has recently become a key technology supporting radio frequency (RF) signal classification applications. Given the heavy DL training requirement, adopting outsourced training is a practical option for RF application developers. However, the outsourcing process exposes a security vulnerability that enables a backdoor attack. While backdoor attacks have been explored in the vision domain, it is rarely explored in the RF domain. In this work, we present a stealthy backdoor attack that targets DL-based RF signal classification. To realize such an attack, we extensively explore the characteristics of the RF data in different applications, which include RF modulation classification and RF fingerprint-based device identification. Then, we design a training-based backdoor trigger generation approach with different optimization procedures for two backdoor attack scenarios (i.e., poison-label and clean-label). Extensive experiments on two RF signal classification datasets show that the attack success rate is over 99.2%, while its classification accuracy for the clean data remains high (i.e., less than a 0.6% drop compared to the clean model). The low NMSE (less than 0.091) indicates the stealthiness of the attack. Additionally, we demonstrate that our attack can bypass existing defense strategies, such as Neural Cleanse and STRIP.

2 December 2024
Verified
Conference Paper
Open access
TZTianfang Zhang
Tianfang Zhang
QJQiufan Ji
Qiufan Ji
ZYZhengkun Ye
Zhengkun Ye
MAMojibur Rahman Redoy Akanda
Mojibur Rahman Redoy Akanda
AMAhmed Tanvir Mahdad
Ahmed Tanvir Mahdad
YCYingying Chen
Yingying Chen
In AR/VR devices, the voice interface, serving as one of the primary AR/VR control mechanisms, enables users to interact naturally using speeches (voice commands) for accessing data, controlling applications, and engaging in remote communication/meetings. Voice authentication can be adopted to protect against unauthorized speech inputs. However, existing voice authentication mechanisms are usually susceptible to voice spoofing attacks and are unreliable under the variations of phonetic content. In this work, we propose SAFARI, a spoofing-resistant and text-independent speech authentication system that can be seamlessly integrated into AR/VR voice interfaces. The key idea is to elicit phonetic-invariant biometrics from the facial muscle vibrations upon the headset. During speech production, a user's facial muscles are deformed for articulating phoneme sounds. The facial deformations associated with the phonemes are referred to as visemes. They carry rich biometrics of the wearer's muscles, tissue, and bones, which can propagate through the head and vibrate the headset. SAFARI aims to derive reliable facial biometrics from the viseme-associated facial vibrations captured by the AR/VR motion sensors. Particularly, it identifies the vibration data segments that contain rich viseme patterns (prominent visemes) less susceptible to phonetic variations. Based on the prominent visemes, SAFARI learns on the correlations among facial vibrations of different frequencies to extract biometric representations invariant to the phonetic context. The key advantages of SAFARI are that it is suitable for commodity AR/VR headsets (no additional sensors) and is resistant to voice spoofing attacks as the conductive property of the facial vibrations prevents biometric disclosure via the air media or the audio channel. To mitigate the impacts of body motions in AR/VR scenarios, we also design a generative diffusion model trained to reconstruct the viseme patterns from the data distorted by motion artifacts. We conduct extensive experiments with two representative AR/VR headsets and 35 users under various usage and attack settings. We demonstrate that SAFARI can achieve over 96% true positive rate on verifying legitimate users while successfully rejecting different kinds of spoofing attacks with over 97% true negative rates.

18 June 2023
Verified
Conference Paper
Open access
TZTianfang Zhang
Tianfang Zhang
CSCong Shi
Cong Shi
PWPayton Walker
Payton Walker
ZYZhengkun Ye
Zhengkun Ye
YWYan Wang
Yan Wang
YCYingying Chen
Yingying Chen
Vital signs (e.g., breathing and heart rates) and personal identities are essential information for personalized medicine and healthcare. The popularity of augmented reality/virtual reality (AR/VR) provides an excellent opportunity for enabling long-term health monitoring in a broad range of scenarios, including virtual entertainment, education, and telemedicine. However, commercial-off-the-shelf AR/VR devices do not have dedicated biosensors for providing vital signs and personal identities. In this work, we propose a novel framework that can generate fine-grained vital sign signals and other personalized health information of an AR/VR user through passive sensing on AR/VR devices. In particular, we find that the user's minute facial vibrations induced by breathing and heart beating can impact the readily available motion sensors on AR/VR headsets, which encode rich vital sign patterns and unique biometrics. The proposed framework further estimates the breathing and heartbeat rates, detects the gender and identity, and derives the body fat percentage of the user. To mitigate the impacts of body movement, we design an adaptive filtering scheme to cancel the spontaneous and non-spontaneous motion artifacts. We also develop unique facial vibration features and deep learning techniques to facilitate vital sign signal reconstruction and user identification. Extensive experiments demonstrate that our framework can achieve a low error of vital sign signal reconstruction and rate measurement, along with 95.51% and 93.33% accuracy on identity and gender recognition.

15 November 2023
Verified
Conference Paper
Open access
CSCong Shi
Cong Shi
TZTianfang Zhang
Tianfang Zhang
ZXZhaoyi Xu
Zhaoyi Xu
SLShuping Li
Shuping Li
DGDonglin Gao
Donglin Gao
YCYingying Chen
Yingying Chen
Speech eavesdropping has long been an important threat to the privacy of individuals and enterprises. Recent research has shown the possibility of deriving private speech information from sound-induced vibrations. Acoustic signals transmitted through a solid medium or air may induce vibrations upon solid surfaces, which can be picked up by various sensors (e.g., motion sensors, high-speed cameras and lasers), without using a microphone. To date, these threats are limited to scenarios where the sensor is in contact with the vibration surface or at least in the visual line-of-sight. In this paper, we revisit this important line of research and show that a remote, long-distance, and even thru-the-wall speech eavesdropping attack is possible. We discover a new form of speech eavesdropping attack that remotely elicits speech from minute surface vibrations upon common room objects (e.g., paper bags, plastic storage bin) via mmWave sensing, signal processing, and advanced deep learning techniques. While mmWave signals have high sensitivity for vibrations, they have limited sensing distance and normally do not penetrate through walls. We overcome this key challenge through designing and implementing a high-resolution software-defined phased-MIMO radar that integrates transmit beamforming, virtual array, and receive beamforming. The proposed system enhances sensing directivity by focusing all the mmWave beams toward a target room object, allowing mmWave signals to pick up minute speech-induced vibrations from a long distance and even through walls. To realize the attack, we design an object identification technique that scans objects in a room and identifies a prominent object that is most sensitive to speech vibrations for vibration feature extraction. We successfully demonstrate speech privacy leakage using speech-induced vibrations via the development of a deep learning framework. Our framework can leverage domain adaptation techniques to infer speech content based only on the unlabeled vibration data of a victim. We validate the proof-of-concept attack on digit recognition through extensive experiments, involving 40 speakers, five common room objects, and attack scenarios with mmWave devices inside and outside the room. Our phased-MIMO-based attack can achieve success rates of 88% ~ 98% and 64% ~ 86% with and without using speech labels for training. The success rates are 81% ~ 94% and 58% ~ 74% for thru-the-wall attacks. Furthermore, we discuss possible defense methods to mitigate this unprecedented security threat.