Advances In Recognising Deepfakes

Uploaded on 2024-10-11 in TECHNOLOGY-Key Areas-Artificial Intelligence, FREE TO VIEW

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
Check Point
Cyrin

Real Attacks. Real Tools. Real Scenarios.
Schedule a demo

Sign Up: Cyber Security Intelligence Newsletter

Directory of Suppliers

Directory of Cyber Security Suppliers

Directory of Cyber Security Suppliers

Our Supplier Directory lists 8,000+ specialist cyber security service providers in 128 countries worldwide. IS YOUR ORGANISATION LISTED?

MIRACL

MIRACL

MIRACL provides the world’s only single step Multi-Factor Authentication (MFA) which can replace passwords on 100% of mobiles, desktops or even Smart TVs.

IT Governance

IT Governance

IT Governance is a leading global provider of information security solutions. Download our free guide and find out how ISO 27001 can help protect your organisation's information.

The PC Support Group

The PC Support Group

A partnership with The PC Support Group delivers improved productivity, reduced costs and protects your business through exceptional IT, telecoms and cybersecurity services.

Alvacomm

Alvacomm

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

Titus

Titus

Titus is a global leader in enterprise-grade data protection solutions.

SCIPP International

SCIPP International

SCIPP’s courses are based on internationally recognized best business practices for security awareness, for both technical and non-technical staff and to comply with regulatory mandates.

CIO Dive

CIO Dive

CIO Dive provides news and analysis for IT executives in areas including IT strategy, cloud computing, cyber security, big data, AI, software, infrastructure, dev ops and more.

CERT Tonga

CERT Tonga

CERT Tonga is the national Computer Emergency Response Team for Tonga.

Braintrace

Braintrace

Braintrace’s services include Managed Detection and Response (MDR), Managed SIEM, SIEM-as-a-Service, SOC-as-a-Service, Advisory Services, and Incident Response.

Cysiv

Cysiv

Cysiv SOC-as-a-Service combines all the elements of an advanced, proactive, threat hunting SOC, with a managed security stack for hybrid cloud, network, and endpoint security.

Hunter Strategy

Hunter Strategy

Hunter Strategy focuses on delivering solutions that are concise, scalable, and target our customer’s complex technical challenges.

Char49

Char49

Char49 specialize in Penetration Testing, Red Team Assessment, Social Engineering and Security Research.

Innefu Labs

Innefu Labs

Innefu is an Information Security R&D startup, providing cutting edge Information Security & Data Analytics solutions.

Airiam

Airiam

Airiam provides cybersecurity, managed IT, consulting, incident response, and digital transformation services so you can focus on what matters most.

AdronH

AdronH

AdronH is a company of Cyber Security consultants. We support companies and public institutions with their digital transformation to new and secure business platforms.

VP Techno Labs

VP Techno Labs

VP Techno Labs is an award-winning cybersecurity firm focusing only cybersecurity to develop cutting edge solutions for emerging business.

InfoSight

InfoSight

InfoSight offers proven Cyber Security, Regulatory Compliance, Risk Management and Infrastructure Solutions to protect your business and your customers from cyber crime and fraud.

Prowler

Prowler

Prowler is at the forefront of the Open Cloud Security movement, championing a new era of transparency, customizability, and community-driven security for cloud environments.

Acuvity

Acuvity

Acuvity is the most comprehensive AI security and governance platform for your employees and applications. Secure your GenAI adoption with confidence.

MirrorTab

MirrorTab

MirrorTab is a cyber security company providing advanced web security solutions that defend web applications against cyber threats like hacking and malware.