Sanitization of Multimedia Content: A Survey of Techniques, Attacks, and Future Directions

• URL: http://arxiv.org/abs/2207.02051v2
• Date: Sun, 14 Sep 2025 20:54:52 GMT
• Title: Sanitization of Multimedia Content: A Survey of Techniques, Attacks, and Future Directions
• Authors: Andrea Ciccotelli, Hanaa Abbas, Roberto Di Pietro,
• Abstract summary: Data sanitization helps to mitigate the severe impact of security risks and privacy violations related to the published data.<n>We present a comprehensive review of technologies designed to protect multimedia content.<n>We identify and elaborate on open research challenges in the crucial domain of multimodal multimedia sanitization.
• Score: 2.1793134762413433
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The exploding rate of data publishing in our networked society has magnified the risk of sensitive information leakage and misuse, pushing the need to secure multimedia content from unintended exposure to potentially untrusted third parties. Data sanitization -- the process of securing multimedia by removing or obfuscating sensitive information such as personally identifiable or confidential data -- helps to mitigate the severe impact of security risks and privacy violations related to the published data. In this paper, we make several contributions. First, we classify data sanitization methods along two main dimensions: the media type (images, audio, text, and video) and the techniques used to sanitize sensitive regions, which we group into obfuscation-based (e.g., distortion, replacement) and removal-based approaches. Building on this categorization, we present a comprehensive review of technologies designed to protect multimedia content. We then broaden the scope by introducing the attacks that specifically target these technologies, followed by a discussion of potential countermeasures. Each aspect is complemented with critical discussions and lessons learned. Finally, we identify and elaborate on open research challenges in the crucial domain of multimodal multimedia sanitization. We argue that the systematization provided in this work -- together with the highlighted challenges and research directions -- offers a valuable blueprint for practitioners, industry, and academia alike, while paving the way for novel research avenues in the field.

Related papers

• Model Inversion Attacks: A Survey of Approaches and Countermeasures [59.986922963781]
  Recently, a new type of privacy attack, the model inversion attacks (MIAs), aims to extract sensitive features of private data for training. Despite the significance, there is a lack of systematic studies that provide a comprehensive overview and deeper insights into MIAs. This survey aims to summarize up-to-date MIA methods in both attacks and defenses.
  arXiv  Detail & Related papers  (2024-11-15T08:09:28Z)
• A Survey of Stance Detection on Social Media: New Directions and Perspectives [50.27382951812502]
  stance detection has emerged as a crucial subfield within affective computing. Recent years have seen a surge of research interest in developing effective stance detection methods. This paper provides a comprehensive survey of stance detection techniques on social media.
  arXiv  Detail & Related papers  (2024-09-24T03:06:25Z)
• Detecting Multimedia Generated by Large AI Models: A Survey [25.97663040910416]
  The aim of this survey is to fill an academic gap and contribute to global AI security efforts.<n>We introduce a novel taxonomy for detection methods, categorized by media modality.<n>We offer a focused analysis from a social media perspective to highlight their broader societal impact.
  arXiv  Detail & Related papers  (2024-01-22T15:08:19Z)
• A Survey on Detection of LLMs-Generated Content [97.87912800179531]
  The ability to detect LLMs-generated content has become of paramount importance. We aim to provide a detailed overview of existing detection strategies and benchmarks. We also posit the necessity for a multi-faceted approach to defend against various attacks.
  arXiv  Detail & Related papers  (2023-10-24T09:10:26Z)
• Fighting Malicious Media Data: A Survey on Tampering Detection and Deepfake Detection [115.83992775004043]
  Recent advances in deep learning, particularly deep generative models, open the doors for producing perceptually convincing images and videos at a low cost. This paper provides a comprehensive review of the current media tampering detection approaches, and discusses the challenges and trends in this field for future research.
  arXiv  Detail & Related papers  (2022-12-12T02:54:08Z)
• Multi-modal Misinformation Detection: Approaches, Challenges and Opportunities [5.4482836906033585]
  Social media platforms are evolving from text-based forums into multi-modal environments. Misinformation spreaders have recently targeted contextual connections between the modalities e.g., text and image. We analyze, categorize and identify existing approaches in addition to challenges and shortcomings they face in order to unearth new research opportunities in the field of multi-modal misinformation detection.
  arXiv  Detail & Related papers  (2022-03-25T19:45:33Z)
• Towards a New Science of Disinformation [3.7305343461339664]
  We discuss how to best address the dangerous impact that deep learning-generated fake audios, photographs, and videos (a.k.a. deepfakes) may have in personal and societal life. We propose that a new Science of Disinformation is needed, one which creates a theoretical framework both for the processes of communication and consumption of false content.
  arXiv  Detail & Related papers  (2022-03-17T19:10:29Z)
• The Deepfake Detection Dilemma: A Multistakeholder Exploration of Adversarial Dynamics in Synthetic Media [0.0]
  Synthetic media detection technologies label media as either synthetic or non-synthetic. As detection practices become more accessible, they become more easily circumvented. This work concludes that there is no "best" approach to navigating the detector dilemma.
  arXiv  Detail & Related papers  (2021-02-11T16:44:09Z)
• Deep Learning Techniques for Future Intelligent Cross-Media Retrieval [58.20547387332133]
  Cross-media retrieval plays a significant role in big data applications. We provide a novel taxonomy according to the challenges faced by multi-modal deep learning approaches. We present some well-known cross-media datasets used for retrieval.
  arXiv  Detail & Related papers  (2020-07-21T09:49:33Z)
• Survey of Network Intrusion Detection Methods from the Perspective of the Knowledge Discovery in Databases Process [63.75363908696257]
  We review the methods that have been applied to network data with the purpose of developing an intrusion detector. We discuss the techniques used for the capture, preparation and transformation of the data, as well as, the data mining and evaluation methods. As a result of this literature review, we investigate some open issues which will need to be considered for further research in the area of network security.
  arXiv  Detail & Related papers  (2020-01-27T11:21:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.