When the Few Outweigh the Many: Illicit Content Recognition with Few-Shot Learning

• URL: http://arxiv.org/abs/2311.17026v1
• Date: Tue, 28 Nov 2023 18:28:03 GMT
• Title: When the Few Outweigh the Many: Illicit Content Recognition with Few-Shot Learning
• Authors: G. Cascavilla, G. Catolino, M. Conti, D. Mellios, D.A. Tamburri
• Abstract summary: This paper investigates an alternative technique for recognizing illegal activities from images. Siamese neural networks reach 90.9% on 20-Shot experiments over a 10-class dataset.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The anonymity and untraceability benefits of the Dark web account for the exponentially-increased potential of its popularity while creating a suitable womb for many illicit activities, to date. Hence, in collaboration with cybersecurity and law enforcement agencies, research has provided approaches for recognizing and classifying illicit activities with most exploiting textual dark web markets' content recognition; few such approaches use images that originated from dark web content. This paper investigates this alternative technique for recognizing illegal activities from images. In particular, we investigate label-agnostic learning techniques like One-Shot and Few-Shot learning featuring the use Siamese neural networks, a state-of-the-art approach in the field. Our solution manages to handle small-scale datasets with promising accuracy. In particular, Siamese neural networks reach 90.9% on 20-Shot experiments over a 10-class dataset; this leads us to conclude that such models are a promising and cheaper alternative to the definition of automated law-enforcing machinery over the dark web.

Related papers

• Unveiling the Digital Fingerprints: Analysis of Internet attacks based on website fingerprints [0.0]
  We show that using the newest machine learning algorithms an attacker can deanonymize Tor traffic by applying such techniques. We capture network packets across 11 days, while users navigate specific web pages, recording data in.pcapng format through the Wireshark network capture tool.
  arXiv  Detail & Related papers  (2024-09-01T18:44:40Z)
• Deepfake Media Forensics: State of the Art and Challenges Ahead [51.33414186878676]
  AI-generated synthetic media, also called Deepfakes, have influenced so many domains, from entertainment to cybersecurity. Deepfake detection has become a vital area of research, focusing on identifying subtle inconsistencies and artifacts with machine learning techniques. This paper reviews the primary algorithms that address these challenges, examining their advantages, limitations, and future prospects.
  arXiv  Detail & Related papers  (2024-08-01T08:57:47Z)
• Exploring Geometry of Blind Spots in Vision Models [56.47644447201878]
  We study the phenomenon of under-sensitivity in vision models such as CNNs and Transformers. We propose a Level Set Traversal algorithm that iteratively explores regions of high confidence with respect to the input space. We estimate the extent of these connected higher-dimensional regions over which the model maintains a high degree of confidence.
  arXiv  Detail & Related papers  (2023-10-30T18:00:33Z)
• Dark Web Activity Classification Using Deep Learning [0.0]
  We propose a search engine that employs deep learning to detect the titles of activities on the dark web. We focus on five categories of activities, including drug trading, weapon trading, selling stolen bank cards, selling fake IDs, and selling illegal currencies. Our aim is to extract relevant images from websites with a ".onion" extension and identify the titles of websites without images by extracting keywords from the text of the pages.
  arXiv  Detail & Related papers  (2023-05-30T14:39:32Z)
• Harnessing the Power of Text-image Contrastive Models for Automatic Detection of Online Misinformation [50.46219766161111]
  We develop a self-learning model to explore the constrastive learning in the domain of misinformation identification. Our model shows the superior performance of non-matched image-text pair detection when the training data is insufficient.
  arXiv  Detail & Related papers  (2023-04-19T02:53:59Z)
• Deep Learning Algorithm for Threat Detection in Hackers Forum (Deep Web) [0.0]
  We propose a novel approach for detecting cyberthreats using a deep learning algorithm Long Short-Term Memory (LSTM) Our model can be easily deployed by organizations in securing digital communications and detection of vulnerability exposure before cyberattack.
  arXiv  Detail & Related papers  (2022-02-03T07:49:44Z)
• A Crawler Architecture for Harvesting the Clear, Social, and Dark Web for IoT-Related Cyber-Threat Intelligence [1.1661238776379117]
  The clear, social, and dark web have lately been identified as rich sources of valuable cyber-security information. We present a novel crawling architecture for transparently harvesting data from security websites in the clear web, security forums in the social web, and hacker forums/marketplaces in the dark web.
  arXiv  Detail & Related papers  (2021-09-14T19:26:08Z)
• Lighting the Darkness in the Deep Learning Era [118.35081853500411]
  Low-light image enhancement (LLIE) aims at improving the perception or interpretability of an image captured in an environment with poor illumination. Recent advances in this area are dominated by deep learning-based solutions. We provide a comprehensive survey to cover various aspects ranging from algorithm taxonomy to unsolved open issues.
  arXiv  Detail & Related papers  (2021-04-21T19:12:19Z)
• Exploiting Web Images for Fine-Grained Visual Recognition by Eliminating Noisy Samples and Utilizing Hard Ones [60.07027312916081]
  We propose a novel approach for removing irrelevant samples from real-world web images during training. Our approach can alleviate the harmful effects of irrelevant noisy web images and hard examples to achieve better performance.
  arXiv  Detail & Related papers  (2021-01-23T03:58:10Z)
• Improving Object Detection with Selective Self-supervised Self-training [62.792445237541145]
  We study how to leverage Web images to augment human-curated object detection datasets. We retrieve Web images by image-to-image search, which incurs less domain shift from the curated data than other search methods. We propose a novel learning method motivated by two parallel lines of work that explore unlabeled data for image classification.
  arXiv  Detail & Related papers  (2020-07-17T18:05:01Z)
• A General Approach for Using Deep Neural Network for Digital Watermarking [45.15137284053717]
  We propose a general deep neural network (DNN) based watermarking method to fulfill this goal. To the best of our knowledge, we are the first to propose a general way to perform watermarking using DNN.
  arXiv  Detail & Related papers  (2020-03-08T06:22:04Z)

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.