<p dir="ltr">Several incidents report misuse of synthetic speech for impersonation attacks, spreading misinformation, and supporting financial frauds. To counter such misuse, this dissertation focuses on developing methods for speech forensics. First, we present a method to detect compressed synthetic speech. The method uses comparatively 33 times less information from compressed bit stream than used by existing methods and achieve high performance. Second, we present a transformer neural network method that uses 2D spectral representation of speech signals to detect synthetic speech. The method shows high performance on detecting both compressed and uncompressed synthetic speech. Third, we present a method using an interpretable machine learning approach known as disentangled representation learning for synthetic speech detection. Fourth, we present a method for synthetic speech attribution. It identifies the source of a speech signal. If the speech is spoken by a human, we classify it as authentic/bona fide. If the speech signal is synthetic, we identify the generation method used to create it. We examine both closed-set and open-set attribution scenarios. In a closed-set scenario, we evaluate our approach only on the speech generation methods present in the training set. In an open-set scenario, we also evaluate on methods which are not present in the training set. Fifth, we propose a multi-domain method for synthetic speech localization. It processes multi-domain features obtained from a transformer using a ResNet-style MLP. We show that with relatively less number of parameters, the proposed method performs better than existing methods. Finally, we present a new direction of research in speech forensics <i>i.e.</i>, bias and fairness of synthetic speech detectors. By bias, we refer to an action in which a detector unfairly targets a specific demographic group of individuals and falsely labels their bona fide speech as synthetic. We show that existing synthetic speech detectors are gender, age and accent biased. They also have bias against bona fide speech from people with speech impairments such as stuttering. We propose a set of augmentations that simulate stuttering in speech. We show that synthetic speech detectors trained with proposed augmentation have less bias relative to detector trained without it.</p>

<p dir="ltr">High quality synthetic speech can now be generated and used maliciously. There is a need of speech forensic tools to detect synthetic speech. Besides detection, it is important to identify the synthesizer that was used for generating a given speech. This is known as synthetic speech attribution. Speech editing tools can be used to create partially synthetic speech in which only parts of speech are synthetic. Detecting these synthetic parts is known as synthetic speech localization.</p><p dir="ltr">We first propose a method for synthetic speech attribution known as the Patchout Spectrogram Attribution Transformer (PSAT). PSAT can distinguish unseen speech synthesis methods (<i>unknown </i>synthesizers) from the methods that were seen during its training (<i>known </i>synthesizers). It achieves more than 95% attribution accuracy. Second, we propose a method known as Fine-Grain Synthetic Speech Attribution Transformer (FGSSAT) that can assign different labels to different <i>unknown </i>synthesizers. Existing methods including PSAT cannot distinguish between different <i>unknown </i>synthesizers. FGSSAT improves on existing work by doing a fine-grain synthetic speech attribution analysis. Third, we propose Synthetic Speech Localization Convolutional Transformer (SSLCT) and achieve less than 10% Equal Error Rate (EER) for synthetic speech localization. Fourth, we demonstrate that existing methods do not perform well for recent diffusion-based synthesizers. We propose the Diffusion-Based Synthetic Speech Dataset (DiffSSD) consisting of about 200 hours of speech, including synthetic speech from 8 diffusion-based open-source and 2 commercial generators. We train speech forensic methods on this dataset and show its importance with respect to recent open-source and commercial generators.</p>

The practice of spamming (sending unsolicited electronic communications) has been dubbed “the scourge of the 21st century” affecting different stakeholders. This practice is also credited for not only disrupting electronic communications but also, it overloads electronic systems and creates unnecessary costs for those affected than the ones responsible for sending such communications. In trying to address this issue nations have implemented anti-spam laws to combat the scourge. South Africa not lagging behind, has put in place anti-spam provisions to deal with the scourge. The anti-spam provisions are scattered in pieces of legislation dealing with diverse issues including: consumer protection; direct marketing; credit laws; and electronic transactions and communications. In addition to these provisions, an Amendment Bill to one of these laws and two Bills covering cybercrimes and cyber-security issues have been published. In this thesis, a question is asked on whether the current fragmented anti-spam provisions are adequate in protecting consumers. Whether the overlaps between these pieces of legislation are competent to deal with the ever increasing threats on electronic communications at large. Finally, the question as to whether a multi-faceted approach, which includes a Model Law on spam would be a suitable starting point setting out requirements for the sending of unsolicited electronic communications can be sufficient in protecting consumers. And as spam is not only a national but also a global problem, South Africa needs to look at the option of entering into mutual agreements with other countries and organisations in order to combat spam at a global level. / Mercantile Law / LL. D.

This thesis deals with the introduction to the security mechanism.The procedure explains the basic concepts, principles of cryptography and security of modern protocols and basic principles that are used for information transmission network. The work also describes the most common types of attacks targeting the eavesdropping of communication. The result is a design of the eavesdropping and the implementation of an attack on the secure communication of the SSL protocol..The attacker uses a false certificate and attacks based on poisoning the ARP and DNS tables for this purpose. The thesis discusses the principles of the SSL protocol and methodology of attacks on the ARP and DNS tables.