Deepfake Detection
for Investigating Fraud
Fraud is one of the most pressing threat vectors enabled by synthetic media. Individuals and organized crime groups use deepfakes in sophisticated social engineering attacks to impersonate trusted figures, fake identities, or fabricate evidence to gain access to systems with the intention of extracting money or data.
Deepfake-Driven Fraud Attacks
Sympathy Scams
Synthetic protagonists – from people with Down syndrome, to the elderly, to cancer patients – convince viewers to donate to their cause or buy their handmade products. These scams typically push a pity narrative fragmented over multiple short form deepfaked videos intended to emotionally manipulate the target.
Crypto Scams
Deepfake celebrity endorsement videos are used to promote malicious crypto schemes and scam investment opportunities. Influential figures such as Elon Musk and Martin Lewis have been deepfaked to push fake investment opportunities. Another common version of this scam uses synthetic influencers to convince targets to install malicious software capable of draining crypto wallets and exfiltrating data from the victim’s computer.
Romance Scams
Romance scams take various forms, from deepfaked celebrities, to hyper-realistic synthetic avatars with deepfaked voices, enabling scammers to interact with victims in real-time. Also known as “pig-butchering” scams because victims are “fattened” before being “led to slaughter”.
Trusted Authority Scams
A variant on the above sometimes referred to as ‘vishing’, convincing deepfakes of authority figures or senior executives are used to pressure consumers or employees into transferring funds to accounts owned by the scammers. Successful scams have been carried out to the tune of tens of millions of dollars. In 2024, engineering firm Arup was the victim of a sophisticated deepfake scam over $25m. Fraudsters used hyper-realistic video and audio deepfakes of senior company executives during a conference call, convincing an employee to execute multiple transfers.
The prime minister of Singapore, Lawrence Wong, and several senior aides were also deepfaked on a conference call where scammers requested a temporary investment from a target who lost over $3.8m.
Deepfake fraud challenges
Deepfake-driven fraud is a significant challenge for law enforcement due to the scale at which attacks can be deployed with little resources or technical knowledge. An additional problem is the ease with which highly customized attacks can be created to target specific individuals. Convincing avatar clones can be generated from authentic videos and images of real people found online, while a clone of someone’s voice can be produced from just a few seconds of recorded audio.
Cyberfraud gangs are already well familiar with the potential of face and voice manipulation for the purposes of impersonation, ID theft, and fooling KYC (Know Your Customer) processes.
Crime-as-a-Service (CaaS) is also a major trend in the criminal ecosystem, automating and scaling many aspects of criminal activity, as well as lowering the barrier to entry for newcomers and established criminals seeking to expand operations with pre-packaged tools and services available on criminal forums and the dark web.
Forensic-grade evidence analysis for investigating fraud
Scalable, automated and multilayer analysis with court-ready reports
Every result includes explainability, provenance metadata, and visual evidence supporting the conclusion. Reports are automatically generated in 30+ languages, enabling cross-border collaboration and ensuring admissibility in court.
Get actionable results in seconds, not hours
With standardized reporting, multilingual support, and strict chain-of-custody controls, Sensity AI transforms deepfake detection into actionable, certifiable intelligence. Investigators can export structured evidence packages for prosecutors, international partners, or judicial authorities.
Stay on top of the caseload
With millions of deepfakes in circulation, digital forensic investigators are under increasing pressure to work through large case loads. Sensity AI integrates synthetic media and deepfake detection at the earliest stage of evidence ingestion, so every extracted media file can be automatically screened for signs of manipulation before it enters the investigative record, speeding up time to evidence.
Cutting edge digital forensics
Specialist digital forensic analysis tools have always existed, but they are not equipped for detecting sophisticated AI-generated falsifications at scale. Sensity AI analyzes video, images, and audio within a single interface, automatically detecting audio in video, and provides relevant and contextual analysis within the same dashboard in real-time.
