Detecting digital audio forgeries by checking frame offsets

Yang, Rui; Qu, Zhenhua; Huang, Jiwu

doi:10.1145/1411328.1411334

Cited by 70 publications

(40 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yang et al [19] presented an interesting approach for detecting digital audio forgeries mainly in MP3. Using a passive approach, they are able to detect doctored MP3 audio by checking frame offsets.…”

Section: Related Workmentioning

confidence: 99%

“…Using an unsupervised SOM to reduce the dimensionality of PC values, we introduce an offset rule similar to that presented in [19] to detect compromised programs. Thus using machine learning techniques [22] we are able to determine whether two PC values are similar to each other, with the use of the program binaries [21] and no prior knowledge of the source code.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Exploring ICMetrics to detect abnormal program behaviour on embedded devices

Zhai

Appiah

Ehsan

et al. 2015

Journal of Systems Architecture

View full text Add to dashboard Cite

Abstract-Execution of unknown or malicious software on an embedded system may trigger harmful system behaviour targeted at stealing sensitive data and/or causing damage to the system. It is thus considered a potential and significant threat to the security of embedded systems. Generally, the resource constrained nature of Commercial offthe-shelf (COTS) embedded devices, such as embedded medical equipment, does not allow computationally expensive protection solutions to be deployed on these devices, rendering them vulnerable. A Self-Organising Map (SOM) based and Fuzzy C-means based approaches are proposed in this paper for detecting abnormal program behaviour to boost embedded system security. The presented technique extracts features derived from processor's Program Counter (PC) and Cycles per Instruction (CPI), and then utilises the features to identify abnormal behaviour using the SOM. Results achieved in our experiment show that the proposed SOM based and Fuzzy C-means based methods can identify unknown program behaviours not included in the training set with 90.9% and 98.7% accuracy.Index Terms-Embedded system security, abnormal behaviour detection, intrusion detection, Self-Organising Map.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Exploring ICMetrics to detect abnormal program behaviour on embedded devices

Zhai

Appiah

Ehsan

et al. 2015

Journal of Systems Architecture

View full text Add to dashboard Cite

show abstract

“…A set of statistical features of zero MDCT coefficients and nonzero MDCT coefficients from the frequency range as well as individual scale bands are adopted. In [5,6], a forgery detection method for MP3 audio files is proposed. Based on the observation that forgeries break the original frame segmentation, frame offsets are used to locate forgeries automatically, allowing to detect most common forgeries, such http://jis.eurasipjournals.com/content/2014/1/10 as deletion, insertion, substitution, and splicing.…”

Section: Introductionmentioning

confidence: 99%

Detection and localization of double compression in MP3 audio tracks

Bianchi

Rosa

Fontani

et al. 2014

EURASIP J. on Info. Security

View full text Add to dashboard Cite

In this work, by exploiting the traces left by double compression in the statistics of quantized modified discrete cosine transform coefficients, a single measure has been derived that allows to decide whether an MP3 file is singly or doubly compressed and, in the last case, to devise also the bit-rate of the first compression. Moreover, the proposed method as well as two state-of-the-art methods have been applied to analyze short temporal windows of the track, allowing the localization of possible tampered portions in the MP3 file under analysis. Experiments confirm the good performance of the proposed scheme and demonstrate that current detection methods are useful for tampering localization, thus offering a new tool for the forensic analysis of MP3 audio tracks.

show abstract

“…4. Time-domain analysis based methods [25][26][27][28][29] have also been proposed to determine authenticity of digital audio recordings by capturing traces of lossy compression using encoder frame offsets in time domain [25][26][27] or detecting traces of "butt-splicing" in the digital recording using higher-order time-differences and correlation analysis [28]. http://www.security-informatics.com/content/3/1/11…”

Section: Introductionmentioning

confidence: 99%

Acoustic environment identification using unsupervised learning

Malik

Mahmood

2014

Secur Inform

View full text Add to dashboard Cite

Acoustic environment leaves its characteristic signature in the audio recording captured in it. The acoustic environment signature can be modeled using acoustic reverberations and background noise. Acoustic reverberation depends on the geometry and composition of the recording location. The proposed scheme uses similarity in the estimated acoustic signature for acoustic environment identification (AEI). We describe a parametric model to realize acoustic reverberation, and a statistical framework based on maximum likelihood estimation is used to estimate the model parameters. The density-based clustering is used for automatic AEI using estimated acoustic parameters. Performance of the proposed framework is evaluated for two data sets consisting of hand-clapping and speech recordings made in a diverse set of acoustic environments using three microphones. Impact of the microphone type variation, frequency, and clustering accuracy and efficiency on the performance of the proposed method is investigated. Performance of the proposed method is also compared with the existing state-of-the-art (SoA) for AEI.

show abstract

Detecting digital audio forgeries by checking frame offsets

Cited by 70 publications

References 7 publications

Exploring ICMetrics to detect abnormal program behaviour on embedded devices

Exploring ICMetrics to detect abnormal program behaviour on embedded devices

Detection and localization of double compression in MP3 audio tracks

Acoustic environment identification using unsupervised learning

Contact Info

Product

Resources

About