Related papers: Protecting Anonymous Speech: A Generative Adversar…
Speaker anonymization aims to conceal a speaker's identity, without considering the linguistic content. In this study, we reveal a weakness of Librispeech, the dataset that is commonly used to evaluate anonymizers: the books read by the…
This paper addresses the problem of manipulating images using natural language description. Our task aims to semantically modify visual attributes of an object in an image according to the text describing the new visual appearance. Although…
The increasing prevalence of computer vision applications necessitates handling vast amounts of visual data, often containing personal information. While this technology offers significant benefits, it should not compromise privacy. Data…
Invisible watermarks safeguard images' copyrights by embedding hidden messages only detectable by owners. They also prevent people from misusing images, especially those generated by AI models. We propose a family of regeneration attacks to…
Social networks have become an indispensable part of our lives, with billions of people producing ever-increasing amounts of text. At such scales, content policies and their enforcement become paramount. To automate moderation, questionable…
Speech is easily leaked imperceptibly, such as being recorded by mobile phones in different situations. Private content in speech may be maliciously extracted through speech enhancement technology. Speech enhancement technology has…
As large language models (LLMs) rapidly advance and integrate into daily life, the privacy risks they pose are attracting increasing attention. We focus on a specific privacy risk where LLMs may help identify the authorship of anonymous…
In speech technologies, speaker's voice representation is used in many applications such as speech recognition, voice conversion, speech synthesis and, obviously, user authentication. Modern vocal representations of the speaker are based on…
The detection of computer-generated text is an area of rapidly increasing significance as nascent generative models allow for efficient creation of compelling human-like text, which may be abused for the purposes of spam, disinformation,…
Speech data on the Internet are proliferating exponentially because of the emergence of social media, and the sharing of such personal data raises obvious security and privacy concerns. One solution to mitigate these concerns involves…
Recent advancements in diffusion models have made generative image editing more accessible, enabling creative edits but raising ethical concerns, particularly regarding malicious edits to human portraits that threaten privacy and identity…
Authorship has entangled style and content inside. Authors frequently write about the same topics in the same style, so when different authors write about the exact same topic the easiest way out to distinguish them is by understanding the…
Recent advancements in adversarial attacks have demonstrated their effectiveness in misleading speaker recognition models, making wrong predictions about speaker identities. On the other hand, defense techniques against speaker-adversarial…
Generative adversarial networks (GANs) have great successes on synthesizing data. However, the existing GANs restrict the discriminator to be a binary classifier, and thus limit their learning capacity for tasks that need to synthesize…
In recent years, Generative Adversarial Networks (GANs) have become a hot topic among researchers and engineers that work with deep learning. It has been a ground-breaking technique which can generate new pieces of content of data in a…
Adversarial examples pose a significant challenge to deep neural networks (DNNs) across both image and text domains, with the intent to degrade model performance through meticulously altered inputs. Adversarial texts, however, are distinct…
In recent years, machine learning - particularly deep learning - has significantly impacted the field of information management. While several strategies have been proposed to restrict models from learning and memorizing sensitive…
While most image captioning aims to generate objective descriptions of images, the last few years have seen work on generating visually grounded image captions which have a specific style (e.g., incorporating positive or negative…
The deployment of Machine-Generated Text (MGT) detection systems necessitates processing sensitive user data, creating a fundamental conflict between authorship verification and privacy preservation. Standard anonymization techniques often…
Interest in automatic people re-identification systems has significantly grown in recent years, mainly for developing surveillance and smart shops software. Due to the variability in person posture, different lighting conditions, and…