Deepfake detection by human crowds, machines, and machine-informed crowds.
Ontology highlight
ABSTRACT:
SUBMITTER: Groh M
PROVIDER: S-EPMC8740705 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:The rapid advancement of 'deepfake' video technology-which uses deep learning artificial intelligence algorithms to create fake videos that look real-has given urgency to the question of how policymakers and technology companies should moderate inauthentic content. We conduct an experiment to measure people's alertness to and ability to detect a high-quality deepfake among a set of videos. First, we find that in a natural setting with no content warnings, individuals who are exposed to a deepfake video of neutral content are no more likely to detect anything out of the ordinary (32.9%) compared to a control group who viewed only authentic videos (34.1%). Second, we find that when individuals are given a warning that at least one video in a set of five is a deepfake, only 21.6% of respondents correctly identify the deepfake as the only inauthentic video, while the remainder erroneously select at least one genuine video as a deepfake.
| S-EPMC10679876 | biostudies-literature
Project description:DeepFake is a forged image or video created using deep learning techniques. The present fake content of the detection technique can detect trivial images such as barefaced fake faces. Moreover, the capability of current methods to detect fake faces is minimal. Many recent types of research have made the fake detection algorithm from rule-based to machine-learning models. However, the emergence of deep learning technology with intelligent improvement motivates this specified research to use deep learning techniques. Thus, it is proposed to have VIOLA Jones's (VJ) algorithm for selecting the best features with Capsule Graph Neural Network (CN). The graph neural network is improved by capsule-based node feature extraction to improve the results of the graph neural network. The experiment is evaluated with CelebDF-FaceForencics++ (c23) datasets, which combines FaceForencies++ (c23) and Celeb-DF. In the end, it is proved that the accuracy of the proposed model has achieved 94.
| S-EPMC10280569 | biostudies-literature
Project description:Recently, deepfake technology has become a popularly used technique for swapping faces in images or videos that create forged data to mislead society. Detecting the originality of the video is a critical process due to the negative pattern of the image. In the detection of forged images or videos, various image processing techniques were implemented. Existing methods are ineffective in detecting new threats or false images. This article has proposed You Only Look Once-Local Binary Pattern Histogram (YOLO-LBPH) to detect fake videos. YOLO is used to detect the face in an image or a frame of a video. The spatial features are extracted from the face image using a EfficientNet-B5 method. Spatial feature extractions are fed as input in the Local Binary Pattern Histogram to extract temporal features. The proposed YOLO-LBPH is implemented using the large scale deepfake forensics (DF) dataset known as CelebDF-FaceForensics++(c23), which is a combination of FaceForensics++(c23) and Celeb-DF. As a result, the precision score is 86.88% in the CelebDF-FaceForensics++(c23) dataset, 88.9% in the DFFD dataset, 91.35% in the CASIA-WebFace data. Similarly, the recall is 92.45% in the Celeb-DF-Face Forensics ++(c23) dataset, 93.76% in the DFFD dataset, and 94.35% in the CASIA-Web Face dataset.
| S-EPMC9575844 | biostudies-literature
Project description:Quantifying sequence-specific protein-ligand interactions is critical for understanding and exploiting numerous cellular processes, including gene expression regulation and signal transduction. Given their importance, next-generation sequencing (NGS) based assays that characterize such recognition with high-throughput are increasingly being used to profile a range of protein classes and interactions. However, these methods do not measure the biophysical parameters that have long been used to uncover the quantitative rules underlying sequence recognition. We developed a highly flexible machine learning framework, called ProBound, to quantify sequence recognition in terms of biophysical parameters based on NGS data. ProBound quantifies transcription factor (TF) behavior with models that accurately predict binding affinity over a range exceeding that of previous resources, captures the impact of DNA modifications and conformational flexibility of multi-TF complexes, and infers specificity directly from \textit{in vivo} data such as ChIP-seq without peak calling. When coupled with a new assay called Kd-seq, it quantifies the absolute affinity of protein-ligand interactions. Its applicability extends beyond thermodynamic equilibrium binding, to the kinetics of kinase-substrate interactions. Altogether, ProBound provides a versatile algorithmic framework for understanding sequence recognition in a wide variety of biological contexts.
2021-06-02 | GSE175942 | GEO
Project description:It is commonly believed that global patterns of motion in flocks, schools and crowds emerge from local interactions between individuals, through a process of self-organization. The key to explaining such collective behaviour thus lies in deciphering these local interactions. We take an experiment-driven approach to modelling collective motion in human crowds. Previously, we observed that a pedestrian aligns their velocity vector (speed and heading direction) with that of a neighbour. Here we investigate the neighbourhood of interaction in a crowd: which neighbours influence a pedestrian's behaviour, how this depends on neighbour position, and how the influences of multiple neighbours are combined. In three experiments, a participant walked in a virtual crowd whose speed and heading were manipulated. We find that neighbour influence is linearly combined and decreases with distance, but not with lateral position (eccentricity). We model the neighbourhood as (i) a circularly symmetric region with (ii) a weighted average of neighbours, (iii) a uni-directional influence, and (iv) weights that decay exponentially to zero by 5 m. The model reproduces the experimental data and predicts individual trajectories in observational data on a human 'swarm'. The results yield the first bottom-up model of collective crowd motion.
| S-EPMC5966612 | biostudies-literature
Project description:The recent advances in language modeling significantly improved the generative capabilities of deep neural models: in 2019 OpenAI released GPT-2, a pre-trained language model that can autonomously generate coherent, non-trivial and human-like text samples. Since then, ever more powerful text generative models have been developed. Adversaries can exploit these tremendous generative capabilities to enhance social bots that will have the ability to write plausible deepfake messages, hoping to contaminate public debate. To prevent this, it is crucial to develop deepfake social media messages detection systems. However, to the best of our knowledge no one has ever addressed the detection of machine-generated texts on social networks like Twitter or Facebook. With the aim of helping the research in this detection field, we collected the first dataset of real deepfake tweets, TweepFake. It is real in the sense that each deepfake tweet was actually posted on Twitter. We collected tweets from a total of 23 bots, imitating 17 human accounts. The bots are based on various generation techniques, i.e., Markov Chains, RNN, RNN+Markov, LSTM, GPT-2. We also randomly selected tweets from the humans imitated by the bots to have an overall balanced dataset of 25,572 tweets (half human and half bots generated). The dataset is publicly available on Kaggle. Lastly, we evaluated 13 deepfake text detection methods (based on various state-of-the-art approaches) to both demonstrate the challenges that Tweepfake poses and create a solid baseline of detection techniques. We hope that TweepFake can offer the opportunity to tackle the deepfake detection on social media messages as well.
| S-EPMC8118345 | biostudies-literature
Project description:Human crowds provide paradigmatic examples of collective behavior emerging through self-organization. Understanding their dynamics is crucial to help manage mass events and daily pedestrian transportation. Although recent findings emphasized that pedestrians' interactions are fundamentally anticipatory in nature, whether and how individual anticipation functionally benefits the group is not well understood. Here, we show the link between individual anticipation and emergent pattern formation through our experiments of lane formation, where unidirectional lanes are spontaneously formed in bidirectional pedestrian flows. Manipulating the anticipatory abilities of some of the pedestrians by distracting them visually delayed the collective pattern formation. Moreover, both the distracted pedestrians and the nondistracted ones had difficulties avoiding collisions while navigating. These results imply that avoidance maneuvers are normally a cooperative process and that mutual anticipation between pedestrians facilitates efficient pattern formation. Our findings may influence various fields, including traffic management, decision-making research, and swarm dynamics.
| S-EPMC7968841 | biostudies-literature
Project description:Provided stimuli are highly distinct, the detection of changes between two briefly separated arrays appears to be achieved by an all-or-none process where either the relevant information is in working memory or observers guess. This observation suggests that it is possible to estimate the average number of items an observer was able to retain across a series of trials, a potentially highly informative cognitive characteristic. For each version of the change detection paradigm, for this estimate to be accurate, it is important to specify how observers use the information available to them. For some instantiations of this task it is possible that observers use knowledge of the contents of working memory even when they are in a guessing state, rather than selecting between the response alternatives at random. Here we test the suggestion that observers may be able to use their knowledge of the number of items in memory to guide guessing in two versions of the change detection task. The four experiments reported here suggest that participants are, in fact, able to use the parameters of the task to update their base expectation of a change occurring to arrive at more informed guessing. (PsycINFO Database Record
| S-EPMC6013305 | biostudies-literature
Project description:Averaging independent numerical judgments can be more accurate than the average individual judgment. This "wisdom of crowds" effect has been shown with large, diverse samples, but the layperson wishing to take advantage of this may only have access to the opinions of a small, more demographically homogeneous "convenience sample." How wise are homogeneous crowds relative to diverse crowds? In simulations and survey studies, we demonstrate three necessary conditions under which small socially diverse crowds can outperform socially homogeneous crowds: Social identity must predict judgment, the effect of social identity on judgment must be at least moderate in size, and the average estimates of the social groups in question must "bracket" the truth being judged. Seven survey studies suggest that these conditions are rarely met in real judgment tasks. Comparisons between the performances of diverse and homogeneous crowds further confirm that social diversity can make crowds wiser but typically by a very small margin.
| S-EPMC5834705 | biostudies-literature
Project description:No anti-cocaine addiction drugs have been approved by the Food and Drug Administration despite decades of effort. The main challenge is the intricate molecular mechanisms of cocaine addiction, involving synergistic interactions among proteins upstream and downstream of the dopamine transporter. However, it is difficult to study so many proteins with traditional experiments, highlighting the need for innovative strategies in the field. We propose a proteome-informed machine learning (ML) platform for discovering nearly optimal anti-cocaine addiction lead compounds. We analyze proteomic protein-protein interaction networks for cocaine dependence to identify 141 involved drug targets and build 32 ML models for cross-target analysis of more than 60,000 drug candidates or experimental drugs for side effects and repurposing potentials. We further predict their ADMET (absorption, distribution, metabolism, excretion, and toxicity) properties. Our platform reveals that essentially all of the existing drug candidates fail in our cross-target and ADMET screenings but identifies several nearly optimal leads for further optimization.
| S-EPMC9357290 | biostudies-literature