[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

McPherson et al., 2016 - Google Patents

Defeating image obfuscation with deep learning

McPherson et al., 2016

View PDF
Document ID
10687407709476928806
Author
McPherson R
Shokri R
Shmatikov V
Publication year
Publication venue
arXiv preprint arXiv:1609.00408

External Links

Snippet

We demonstrate that modern image recognition methods based on artificial neural networks can recover hidden information from images protected by various forms of obfuscation. The obfuscation techniques considered in this paper are mosaicing (also known as pixelation) …
Continue reading at arxiv.org (PDF) (other versions)

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00—Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/36—Image preprocessing, i.e. processing the image information without deciding about the identity of the image
    • G06K9/46—Extraction of features or characteristics of the image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00—Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/20—Image acquisition
    • G06K9/32—Aligning or centering of the image pick-up or image-field
    • G06K9/3233—Determination of region of interest
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00—Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/00221—Acquiring or recognising human faces, facial parts, facial sketches, facial expressions
    • G06K9/00288—Classification, e.g. identification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00—Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/20—Image acquisition
    • G06K9/2018—Identifying/ignoring parts by sensing at different wavelengths
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00—Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/00221—Acquiring or recognising human faces, facial parts, facial sketches, facial expressions
    • G06K9/00268—Feature extraction; Face representation
    • G06K9/00275—Holistic features and representations, i.e. based on the facial image taken as a whole
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00—Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/00221—Acquiring or recognising human faces, facial parts, facial sketches, facial expressions
    • G06K9/00268—Feature extraction; Face representation
    • G06K9/00281—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00—Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/62—Methods or arrangements for recognition using electronic means
    • G06K9/6288—Fusion techniques, i.e. combining data from various sources, e.g. sensor fusion
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00—Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/00624—Recognising scenes, i.e. recognition of a whole field of perception; recognising scene-specific objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00—Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/00597—Acquiring or recognising eyes, e.g. iris verification

Similar Documents

Publication Publication Date Title
McPherson et al. Defeating image obfuscation with deep learning
Yang et al. A study of face obfuscation in imagenet
Meden et al. Privacy–enhancing face biometrics: A comprehensive survey
Yu et al. Attributing fake images to gans: Learning and analyzing gan fingerprints
Yang et al. Neural network inversion in adversarial setting via background knowledge alignment
Goel et al. Dual branch convolutional neural network for copy move forgery detection
Wang et al. Data hiding with deep learning: A survey unifying digital watermarking and steganography
Liu et al. A survey on security threats and defensive techniques of machine learning: A data driven view
Raval et al. Protecting visual secrets using adversarial nets
Chen et al. Detecting visually similar web pages: Application to phishing detection
US11687623B2 (en) Anti-piracy framework for deep neural networks
Li et al. Deepobfuscator: Obfuscating intermediate representations with privacy-preserving adversarial learning on smartphones
Fan et al. Integration of statistical detector and Gaussian noise injection detector for adversarial example detection in deep neural networks
Barni et al. Iris deidentification with high visual realism for privacy protection on websites and social networks
Raynal et al. Image obfuscation for privacy-preserving machine learning
Ma et al. TransCAB: Transferable clean-annotation backdoor to object detection with natural trigger in real-world
Tasneem et al. Learning phase mask for privacy-preserving passive depth estimation
Ye et al. Privacy-preserving age estimation for content rating
Thaler et al. Deep learning in information security
Ara et al. An efficient privacy-preserving user authentication scheme using image processing and blockchain technologies
Li et al. Hierarchical Perceptual Noise Injection for Social Media Fingerprint Privacy Protection
Liu et al. Radap: A robust and adaptive defense against diverse adversarial patches on face recognition
Wu et al. Giid-net: Generalizable image inpainting detection network
Ye et al. Label-only model inversion attack: The attack that requires the least information
CN114638356A (en) Static weight guided deep neural network back door detection method and system