Advances In Recognising Deepfakes

As Artificial Intelligence (AI) continues to advance, distinguishing between real and AI-generated content is becoming increasingly difficult. This challenge could have significant implications, such as not being able to say if certain evidence is real or not.

It seems that AI itself might be our best defence against AI fakery after an algorithm has identified giveaway signs of AI videos with over 98% accuracy. 

Now,  a new study by Carnegie Mellon University and École Centrale Nantes addresses this issue by exploring the limitations of deepfake detection in environmental sounds.

Deepfake Technology

Deepfake technology leverages AI and machine learning algorithms to create hyper-realistic videos or audio recordings. This technology can manipulate facial features, voice, and body movements, making it challenging to distinguish between real and fabricated content. While there are benign applications, such as in the entertainment industry, the potential for malicious use in fraud and identity theft is a significant concern.

Research Work

The researchers at Carnegie Mellon and Ecole Centrale Nantes developed a deep neural network detector designed to automatically classify environmental sounds (anything that is not speech or music) in recordings as either real or AI-generated. According to TechXplore, the detector currently recognises seven categories of environmental sounds and demonstrated high accuracy during testing, with around 100 errors out of approximately 6,000 sounds. Theses the errors were categorised into two types: the detector mistakenly labelled AI-generated sounds as real or real sounds as AI-generated.To further investigate, the study involved 20 human participants who listened to the same sets of sounds identified incorrectly by the detector. Participants were asked to distinguish between real and AI-generated sounds.

The results revealed that humans were only about 50% accurate in identifying the fake sounds that the detector classified as real, suggesting that these sounds might have subtle characteristics that both the detector and participants struggled to recognise. In contrast, participants correctly identified real sounds labelled as fake by the detector about 71% of the time, indicating a possible cue in these sounds that humans can detect, which the current detector fails to recognise.

Carnegie Mellon University professor of psychology, Dr. Laurie Heller, concluded that if this cue can be identified, it could improve the accuracy of AI sound detectors. The research points to the potential for developing more sophisticated AI detection tools capable of analysing both speech and environmental sounds.

Heller emphasised the importance of staying ahead of rapidly advancing AI technologies, warning that a future where AI-generated content is indistinguishable from reality could lead to significant societal challenges.

I-HIS     |     Eurasip     |     Live Science     |     Drexel News     |     Reuters     |     Onfido

Image: Makhbubakhon Ismatova

You Might Also Read:

Progress In Deepfake Detection:


If you like this website and use the comprehensive 7,000-plus service supplier Directory, you can get unrestricted access, including the exclusive in-depth Directors Report series, by signing up for a Premium Subscription.

  • Individual £5 per month or £50 per year. Sign Up
  • Multi-User, Corporate & Library Accounts Available on Request

Cyber Security Intelligence: Captured Organised & Accessible


 

« Surge In DDoS Attacks On Financial Services
Cyber Insurance: What Businesses Need To Know »

Infosecurity Europe
CyberSecurity Jobsite
Perimeter 81

Directory of Suppliers

DigitalStakeout

DigitalStakeout

DigitalStakeout enables cyber security professionals to reduce cyber risk to their organization with proactive security solutions, providing immediate improvement in security posture and ROI.

Jooble

Jooble

Jooble is a job search aggregator operating in 71 countries worldwide. We simplify the job search process by displaying active job ads from major job boards and career sites across the internet.

TÜV SÜD Academy UK

TÜV SÜD Academy UK

TÜV SÜD offers expert-led cybersecurity training to help organisations safeguard their operations and data.

Authentic8

Authentic8

Authentic8 transforms how organizations secure and control the use of the web with Silo, its patented cloud browser.

CSI Consulting Services

CSI Consulting Services

Get Advice From The Experts: * Training * Penetration Testing * Data Governance * GDPR Compliance. Connecting you to the best in the business.

Information Security Group (ISG) - Royal Holloway

Information Security Group (ISG) - Royal Holloway

The Information Security Group, Royal Holloway, University of London, is an Academic Centres of Excellence in Cyber Security Research.

GigaOm

GigaOm

GigaOm's mission is to provide enterprises with information and analysis to help them make better decisions about technology.

American International Group (AIG)

American International Group (AIG)

AIG, is an American multinational insurance corporation. Commercial services include cyber risk insurance.

Optimum Insurance

Optimum Insurance

Optimum's Cyber Risk & Data Protection Insurance policies are designed to protect against cyber exposures that arise when a company’s data and customer information is breached or stolen.

Viasat

Viasat

Viasat is a provider of high-speed satellite broadband services and secure networking systems covering military and commercial markets.

Awake Security

Awake Security

Awake Security offer a security solution built on an AI platform that acts like the human brain to sense, detect, and respond to threats you may not even know exist.

Synelixis Solutions

Synelixis Solutions

Synelixis Solutions is a high-tech company founded to provide complete telecommunications, networking, security, control and automation solutions.

Verafin

Verafin

Verafin is one of the North American leaders in fraud detection and AML software.

Datrix

Datrix

Datrix is a leading Smart Infrastructure and Cyber Security solutions provider. We deliver critical networking, communications and cyber security solutions to public and private sector organisations.

CertNexus

CertNexus

CertNexus is a vendor-neutral certification body, providing emerging technology certifications and micro-credentials for business, data, developer, IT, and security professionals.

Telesign

Telesign

Telesign connect, protect, and defend online experiences with sophisticated digital identity and programmable communications solutions.

Vercara

Vercara

Vercara offers a purpose-built, global cloud security platform that provides layers of protection to safeguard businesses’ online presence, no matter where an attack comes from or where it is aimed.

ThreatER

ThreatER

ThreateER (formerly ThreatBlockr / Bandura Cyber) is a cybersecurity platform that provides active network defense by automating the discovery, enforcement, and analysis of cyber threats at scale.

PDI Technologies

PDI Technologies

PDI Technologies helps convenience retail and petroleum wholesale businesses around the globe increase efficiency and profitability by securely connecting their data and operations.

Sansec Technology

Sansec Technology

Sansec Technology is dedicated to the research and development of cryptographic products and solutions for cyber security.

Federal Office for the Protection of the Constitution (BfV)

Federal Office for the Protection of the Constitution (BfV)

The Federal Office for the Protection of the Constitution (Bundesamt für Verfassungsschutz - BfV) is the domestic intelligence services of the federal government of Germany.