Auto-Parser: Android Auto and Apple CarPlay Forensics

Mahr, Andrew; Serafin, Robert; Grajeda, Cinthya; Baggili, Ibrahim

doi:10.1007/978-3-031-06365-7_4

Cited by 5 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The development of artificial intelligence has driven the popularity of automatic speech recognition (ASR) systems, which have been integrated into human-computer interaction services such as Amazon Alexa [9], Apple Siri [59], Google Assistant [10], and Microsoft Cortana [23] to transform speech signals into text transcriptions. By sending voice commands, ASR systems free users' hands and make it more convenient to control their smart home devices [34], send messages to their friends [17], or navigate to their destinations [44].…”

Section: Introductionmentioning

confidence: 99%

Compensating Removed Frequency Components: Thwarting Voice Spectrum Reduction Attacks

Wang,

Sun,

2024

Proceedings 2024 Network and Distributed System Security Symposium

View full text Add to dashboard Cite

Automatic speech recognition (ASR) provides diverse audio-to-text services for humans to communicate with machines. However, recent research reveals ASR systems are vulnerable to various malicious audio attacks. In particular, by removing the non-essential frequency components, a new spectrum reduction attack can generate adversarial audios that can be perceived by humans but cannot be correctly interpreted by ASR systems. It raises a new challenge for content moderation solutions to detect harmful content in audio and video available on social media platforms. In this paper, we propose an acoustic compensation system named ACE to counter the spectrum reduction attacks over ASR systems. Our system design is based on two observations, namely, frequency component dependencies and perturbation sensitivity. First, since the Discrete Fourier Transform computation inevitably introduces spectral leakage and aliasing effects to the audio frequency spectrum, the frequency components with similar frequencies will have a high correlation. Thus, considering the intrinsic dependencies between neighboring frequency components, it is possible to recover more of the original audio by compensating for the removed components based on the remaining ones. Second, since the removed components in the spectrum reduction attacks can be regarded as an inverse of adversarial noise, the attack success rate will decrease when the adversarial audio is replayed in an overthe-air scenario. Hence, we can model the acoustic propagation process to add over-the-air perturbations into the attacked audio. We implement a prototype of ACE and the experiments show that ACE can effectively reduce up to 87.9% of ASR inference errors caused by spectrum reduction attacks. Furthermore, by analyzing the residual errors on real audio samples, we summarize six general types of ASR inference errors and investigate the error causes and potential mitigation solutions.

show abstract

Section: Introductionmentioning

confidence: 99%

Compensating Removed Frequency Components: Thwarting Voice Spectrum Reduction Attacks

Wang,

Sun,

2024

Proceedings 2024 Network and Distributed System Security Symposium

View full text Add to dashboard Cite

show abstract

“…With its wireless connection to devices, such as sensors, smartphones, and IoT, a vehicle is exposed to external threats (Hasan 2020). Consequently, vehicles are exposed to a greater cybersecurity attack surface than ever before and the seriousness of this has steadily increased (Mahr 2022). In reality, there have been cases of eavesdropping on IoT devices that operate based on a wireless connection and an attacker has conducted a remotelycontrolled attack on an IoT device (Lakshmanan 2022).…”

Section: Introductionmentioning

confidence: 99%

Digital Forensic Analysis for Vehicle Infotainment Systems based on Packet Fingerprinting

Shin,

Yu,

Shon

2024

Preprint

View full text Add to dashboard Cite

With the increasing number of in-vehicle computing systems and rapid development of technologies, such as autonomous driving technology, various IoT technologies are being incorporated into vehicles. In these scenarios, a vehicle is typically connected to a smartphone or various sensors to exchange information based on wireless communication. While this is convenient for the driver, from a security standpoint, it means exposing the vehicle to a new cyberattack surface: wireless communication attacks. Therefore, active research on security inspection and improvement for wireless communication in vehicular environments is required. Some studies in this regard have raised security issues, but little digital forensic research has been conducted on the issues raised. Against this background, we conducted a case study based on packet fingerprinting to improve the level of security in wireless communication in a vehicular environment (i.e., in-vehicle wireless communications). Packet fingerprinting was applied to 11 in-vehicle infotainment systems. Consequently, devices and services in use were identified from wireless network packets. Images of internal storage data were acquired from three in-vehicle infotainment systems, and a file system-based analysis was performed on the images to derive digital forensic artifacts related to the packets stored in the vehicle systems. Further analysis was conducted by combining the derived artifacts with the packet fingerprinting results. Our findings indicate that the security level of wireless communication in various in-vehicle infotainment system environments can be evaluated and improved. Moreover, we provide various identification information and digital forensic artifacts derived from various in-vehicle infotainment systems.

show abstract