arXiv subjects

Hany Farid

Publications and source records attributed to Hany Farid.

24 records · Page 2Linked to original sources

arXiv2022

A Toolbox for the Radial and Angular Marginalization of Bivariate Normal Distributions

Bivariate normal distributions are often used to describe the joint probability density of a pair of random variables. These distributions arise across many domains, from telecommunications, to meteorology, ballistics, and computational neuroscience. In these applications, it is often useful to radially and angularly marginalize (i.e.,~under a polar transformation) the joint probability distribution relative to the coordinate system's origin. This marginalization is trivial for a zero-mean, isotropic distribution, but is non-trivial for the most general case of a non-zero-mean, anisotropic distribution with a non-diagonal covariance matrix. Across domains, a range of solutions with varying degrees of generality have been derived. Here, we provide a concise summary of analytic solutions for the polar marginalization of bivariate normal distributions. This report accompanies a Matlab (Mathworks, Inc.) and R toolbox that provides closed-form and numeric implementations for the marginalizations described herein.

stat.ME↗

arXiv2021

Mutual Hyperlinking Among Misinformation Peddlers

The internet promised to democratize access to knowledge and make the world more open and understanding. The reality of today's internet, however, is far from this ideal. Misinformation, lies, and conspiracies dominate many social media platforms. This toxic online world has had real-world implications ranging from genocide to, election interference, and threats to global public health. A frustrated public and impatient government regulators are calling for a more vigorous response to mis- and disinformation campaigns designed to sow civil unrest and inspire violence against individuals, societies, and democracies. We describe a large-scale, domain-level analysis that reveals seemingly coordinated efforts between multiple domains to spread and amplify misinformation. We also describe how the hyperlinks shared by certain Twitter users can be used to surface problematic domains. These analyses can be used by search engines and social media recommendation algorithms to systematically discover and demote misinformation peddlers.

cs.SI↗

arXiv2021

Examining the Global Spread of COVID-19 Misinformation

The global COVID-19 pandemic has led to the online proliferation of health-, political-, and conspiratorial-based misinformation. Understanding the reach and belief in this misinformation is vital to managing this crisis, as well as future crises. The results from our global survey finds a troubling reach of and belief in COVID-related misinformation, as well as a correlation with those that primarily consume news from social media, and, in the United States, a strong correlation with political leaning.

cs.SI↗

arXiv2020

Detecting Deep-Fake Videos from Appearance and Behavior

Synthetically-generated audios and videos -- so-called deep fakes -- continue to capture the imagination of the computer-graphics and computer-vision communities. At the same time, the democratization of access to technology that can create sophisticated manipulated video of anybody saying anything continues to be of concern because of its power to disrupt democratic elections, commit small to large-scale fraud, fuel dis-information campaigns, and create non-consensual pornography. We describe a biometric-based forensic technique for detecting face-swap deep fakes. This technique combines a static biometric based on facial recognition with a temporal, behavioral biometric based on facial expressions and head movements, where the behavioral embedding is learned using a CNN with a metric-learning objective function. We show the efficacy of this approach across several large-scale video datasets, as well as in-the-wild deep fakes.

cs.CV↗

arXiv2020

Evading Deepfake-Image Detectors with White- and Black-Box Attacks

It is now possible to synthesize highly realistic images of people who don't exist. Such content has, for example, been implicated in the creation of fraudulent social-media profiles responsible for dis-information campaigns. Significant efforts are, therefore, being deployed to detect synthetically-generated content. One popular forensic approach trains a neural network to distinguish real from synthetic content. We show that such forensic classifiers are vulnerable to a range of attacks that reduce the classifier to near-0% accuracy. We develop five attack case studies on a state-of-the-art classifier that achieves an area under the ROC curve (AUC) of 0.95 on almost all existing image generators, when only trained on one generator. With full access to the classifier, we can flip the lowest bit of each pixel in an image to reduce the classifier's AUC to 0.0005; perturb 1% of the image area to reduce the classifier's AUC to 0.08; or add a single noise pattern in the synthesizer's latent space to reduce the classifier's AUC to 0.17. We also develop a black-box attack that, with no access to the target classifier, reduces the AUC to 0.22. These attacks reveal significant vulnerabilities of certain image-forensic classifiers.

cs.CV↗

arXiv2020

A Longitudinal Analysis of YouTube's Promotion of Conspiracy Videos

Conspiracy theories have flourished on social media, raising concerns that such content is fueling the spread of disinformation, supporting extremist ideologies, and in some cases, leading to violence. Under increased scrutiny and pressure from legislators and the public, YouTube announced efforts to change their recommendation algorithms so that the most egregious conspiracy videos are demoted and demonetized. To verify this claim, we have developed a classifier for automatically determining if a video is conspiratorial (e.g., the moon landing was faked, the pyramids of Giza were built by aliens, end of the world prophecies, etc.). We coupled this classifier with an emulation of YouTube's watch-next algorithm on more than a thousand popular informational channels to obtain a year-long picture of the videos actively promoted by YouTube. We also obtained trends of the so-called filter-bubble effect for conspiracy theories.

cs.CY↗