DeepFakes Have No Heart: A Simple rPPG-Based Method to Reveal Fake Videos

Boccignone, Giuseppe; Bursic, Sathya; Cuculo, Vittorio; D’Amelio, Alessandro; Grossi, Giuliano; Lanzarotti, Raffaella; Patania, Sabrina

doi:10.1007/978-3-031-06430-2_16

Cited by 9 publications

(10 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For deepfake detection that used heartbeat, a research paper, [7] that leverages rPPG and heartbeat was reviewed. The suggested deepfake detection method based on the physiological heart rate estimate postulates that when calculating the localized pulse rate from a picture of a genuine head vs. a counterfeit one, rPPG (remote photoplethysmography) approaches should yield noticeably different findings.…”

Section: Heartbeat Detectionmentioning

confidence: 99%

Deepfake Detection using Biological Features: A Survey

Patil¹,

Kale²,

Dhokey³

et al. 2023

Preprint

View full text Add to dashboard Cite

A deep learning-based technique called deepfake has made it easier to change or modify images and videos. In investigations and court, visual evidence is commonly employed. These pieces of evidence may now be a suspect due to technological advancements, particularly Deepfake. Photographs and movies that have been edited are incredibly lifelike and difficult to tell apart from the original. Deepfakes have been utilized to blackmail individuals, plan terrorist attacks, disseminate incorrect facts, defame individuals as well as foment political turmoil. Our study describes the history of the Deepfake to acquire a thorough understanding of the technology. Additionally, the study focuses on the development and detection of Deepfakes and their challenges based on physiological measurements. Here, biological features such as eyebrow recognition, eye blinking detection, eye movement detection, ear and mouth detection, and heartbeat detection are clearly described and a scope in this domain is proposed. A comparison of each biological feature concerning classifiers or techniques along with its key findings is discussed. Generated using the generative adversarial network (GANs) model, Deepfakes are created by iterating an actual data-based generation and verification task through two opposite deep learning models. It was easier to identify deepfakes by humans during the nascent stage of this technology owing to pixel collapse phenomena that generated visible artifacts in skin tone and the general face structure. However, with the technology's advancement, DeepFakes have evolved to be highly indistinguishable from natural images hence it is important to review these detection methods.

show abstract

Section: Heartbeat Detectionmentioning

confidence: 99%

Deepfake Detection using Biological Features: A Survey

Patil¹,

Kale²,

Dhokey³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Approaches to counteract threats like the previously mentioned "deep fakes" include the usage of deep neural networks for the detection of artifacts resulting from the production of such content (for videos see for example [20,53,62,88,115], for images see [27,46,59]). Such artifacts are for example related to image blending, the environment, behavioural anomalies, as well as audiovisual synchronization issues [85].…”

Section: Visual Contentmentioning

confidence: 99%

Moving Beyond Benchmarks and Competitions: Towards Addressing Social Media Challenges in an Educational Context

et al. 2023

View full text Add to dashboard Cite

Natural language processing and other areas of artificial intelligence have seen staggering progress in recent years, yet much of this is reported with reference to somewhat limited benchmark datasets.We see the deployment of these techniques in realistic use cases as the next step in this development. In particular, much progress is still needed in educational settings, which can strongly improve users’ safety on social media. We present our efforts to develop multi-modal machine learning algorithms to be integrated into a social media companion aimed at supporting and educating users in dealing with fake news and other social media threats.Inside the companion environment, such algorithms can automatically assess and enable users to contextualize different aspects of their social media experience. They can estimate and display different characteristics of content in supported users’ feeds, such as ‘fakeness’ and ‘sentiment’, and suggest related alternatives to enrich users’ perspectives. In addition, they can evaluate the opinions, attitudes, and neighbourhoods of the users and of those appearing in their feeds. The aim of the latter process is to raise users’ awareness and resilience to filter bubbles and echo chambers, which are almost unnoticeable and rarely understood phenomena that may affect users’ information intake unconsciously and are unexpectedly widespread.The social media environment is rapidly changing and complex. While our algorithms show state-of-the-art performance, they rely on task-specific datasets, and their reliability may decrease over time and be limited against novel threats. The negative impact of these limits may be exasperated by users’ over-reliance on algorithmic tools.Therefore, companion algorithms and educational activities are meant to increase users’ awareness of social media threats while exposing the limits of such algorithms. This will also provide an educational example of the limits affecting the machine-learning components of social media platforms.We aim to devise, implement and test the impact of the companion and connected educational activities in acquiring and supporting conscientious and autonomous social media usage.

show abstract

“…Remote-PPG measures blood flow changes by analysing the variations of the skin-reflected light captured through a general-purpose RGB-camera placed in front of the person [ 7 ]. While rPPG widens the scope of applications [ 8 , 9 , 10 ], its utility clearly depends on its reliability. As with contact-PPG signals, remotely estimated PPG waveforms carry respiratory-related information; there exists at least three different kinds of Respiratory Induced Variations, RIVs that can be eventually mined from (r)PPG signals: (cfr.…”

Section: Introductionmentioning

confidence: 99%

An Evaluation of Non-Contact Photoplethysmography-Based Methods for Remote Respiratory Rate Estimation

Boccignone

D’Amelio

Ghezzi

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

The respiration rate (RR) is one of the physiological signals deserving monitoring for assessing human health and emotional states. However, traditional devices, such as the respiration belt to be worn around the chest, are not always a feasible solution (e.g., telemedicine, device discomfort). Recently, novel approaches have been proposed aiming at estimating RR in a less invasive yet reliable way, requiring the acquisition and processing of contact or remote Photoplethysmography (contact reference and remote-PPG, respectively). The aim of this paper is to address the lack of systematic evaluation of proposed methods on publicly available datasets, which currently impedes a fair comparison among them. In particular, we evaluate two prominent families of PPG processing methods estimating Respiratory Induced Variations (RIVs): the first encompasses methods based on the direct extraction of morphological features concerning the RR; and the second group includes methods modeling respiratory artifacts adopting, in the most promising cases, single-channel blind source separation. Extensive experiments have been carried out on the public BP4D+ dataset, showing that the morphological estimation of RIVs is more reliable than those produced by a single-channel blind source separation method (both in contact and remote testing phases), as well as in comparison with a representative state-of-the-art Deep Learning-based approach for remote respiratory information estimation.

show abstract

DeepFakes Have No Heart: A Simple rPPG-Based Method to Reveal Fake Videos

Cited by 9 publications

References 50 publications

Deepfake Detection using Biological Features: A Survey

Deepfake Detection using Biological Features: A Survey

Moving Beyond Benchmarks and Competitions: Towards Addressing Social Media Challenges in an Educational Context

An Evaluation of Non-Contact Photoplethysmography-Based Methods for Remote Respiratory Rate Estimation

Contact Info

Product

Resources

About