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 »

CyberSecurity Jobsite
Perimeter 81

Directory of Suppliers

Directory of Cyber Security Suppliers

Directory of Cyber Security Suppliers

Our Supplier Directory lists 7,000+ specialist cyber security service providers in 128 countries worldwide. IS YOUR ORGANISATION LISTED?

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.

North Infosec Testing (North IT)

North Infosec Testing (North IT)

North IT (North Infosec Testing) are an award-winning provider of web, software, and application penetration testing.

Alvacomm

Alvacomm

Alvacomm offers holistic VIP cybersecurity services, providing comprehensive protection against cyber threats. Our solutions include risk assessment, threat detection, incident response.

Syxsense

Syxsense

Syxsense brings together endpoint management and security for greater efficiency and collaboration between IT management and security teams.

Tripwire

Tripwire

Tripwire are a leading provider of risk-based security, compliance and vulnerability management solutions.

Pervade Software

Pervade Software

Pervade Software is a global provider of dedicated compliance tracking software with monitoring & reporting capabilities.

Computing Technology Industry Association (CompTIA)

Computing Technology Industry Association (CompTIA)

CompTIA is dedicated to advancing industry growth through its educational programs, market research, networking events, professional certifications, and public policy advocacy.

Intertrust Technologies

Intertrust Technologies

Intertrust Technologies is a software company specializing in trusted computing products and services.

Netlawgic Legal Services

Netlawgic Legal Services

Netlawgic is exclusively focused on delivering cyber law solutions to the industry. We provide our clients with specialized attention and problem solving in all aspects of cyber law.

Newberry Group

Newberry Group

The Newberry Group provides comprehensive IT services and solutions that optimize operations, minimize risk and deliver measurable business value.

RevBits

RevBits

RevBits provides high-performance cybersecurity solutions including email security, endpoint security, deception technology and PAM solution to enterprise companies and public sector organizations.

Tactic Labs

Tactic Labs

Tactic Labs (part of the Avnon Group) delivers a holistic Cyber-Security Management Platform which provides military-grade protection, safeguarding critical infrastructures and mission-critical data.

US Fleet Cyber Command (FLTCYBER)

US Fleet Cyber Command (FLTCYBER)

US Fleet Cyber Command is responsible for Navy information network operations, offensive and defensive cyberspace operations, space operations and signals intelligence.

Purple Knight

Purple Knight

Purple Knight is a free Active Directory security assessment tool built and managed by an elite group of Microsoft identity experts.

CipherStash

CipherStash

CipherStash is a complete data governance and breach prevention platform.

Insurica

Insurica

INSURICA is a full-service insurance agency built upon a tradition of integrity, industry leadership, and excellence.

Token Security

Token Security

Token is the new approach designed for the identity boom era. Introducing Machine-First Identity Security.

Blackmere Consulting

Blackmere Consulting

Blackmere Consulting is a Nationwide Technical and Executive Recruiting firm dedicated to Cyber Security and Information Technology.

Iron EagleX

Iron EagleX

Iron EagleX deliver engineering solutions in cloud computing, big data, cyber, and machine learning technologies to US Government customers.

Soteria LLC

Soteria LLC

Soteria LLC are a client-focused organization providing expert advisory, consulting services, and tailored solutions to prevent, detect, and respond to cybersecurity incidents.