Loading story…
AI-generated deepfakes are increasingly used to manipulate public opinion, interfere in elections, and incite real-world violence. Recent incidents include viral fake audio clips during Slovakia’s election and deepfake videos in conflicts such as Ukraine and the Middle East. The proliferation of deepfakes poses significant risks to democratic processes and societal stability.
Mallory correlates global threat intelligence with your attack surface — know if you’re exposed before adversaries strike.
6 events from the most recent confirmed update back to the earliest known activity.
Following Nicolás Maduro's capture, social media saw a wave of altered and misleading images, including AI-generated visuals, tied to the event. The incident marked another distinct real-world case of synthetic media amplifying confusion around a major breaking-news development.
After a major earthquake struck northern Japan on 2025-12-08, social media platforms were flooded with false and misleading content, including AI-generated tsunami footage, fabricated reporter videos, and pseudoscientific earthquake claims. Japanese officials warned that the misinformation could disrupt disaster response and urged the public to rely on government sources and trusted media.
Initial story creation
DFRLab published analysis describing how AI tools were being used in disinformation related to the war in Ukraine. The report marked a separate documented case of generative AI being applied to influence operations outside the election and disaster-response contexts already in the timeline.
Technology companies announced a commitment to fight deceptive AI-generated election content, marking an industry response to growing concerns about deepfakes in democratic processes. This represents a policy and platform-governance development distinct from the later misinformation surge after the Japan earthquake.
A political attack ad tied to Ron DeSantis used AI-generated images depicting Donald Trump embracing Anthony Fauci, drawing attention to the use of synthetic media in U.S. campaign messaging. The incident became an early high-profile example of generative AI being used in electoral political content.
11 references tracked. Mallory keeps watching after this page renders.
cybercenter.space
Open sourcewww3.nhk.or.jp
Open sourcecbsnews.com
Open sourceblog.knowbe4.com
Open sourcenextgov.com
Open sourcecyberscoop.com
Open sourceapnews.com
Open sourcetheverge.com
Open sourceMap indicators from this story to your assets and identify affected systems in minutes.
Every observed campaign, victim, and pivot linked to actors named in this story.
Malware, exploits, and IOCs connected to the activity described here.
YARA, Sigma, and Snort rules deployed to your SIEM as soon as they’re published.
Get matching new stories delivered to your team as they break — not the next morning.
Ask questions about this story and take action on the answers.
Other stories Mallory is tracking that overlap on entities, sources, or topic labels.
Artificial intelligence is increasingly being leveraged by both cybercriminals and law enforcement, fundamentally transforming the landscape of cybercrime and digital forensics. AI-powered tools are now capable of detecting cyber threats by recognizing malicious activity patterns and supporting digital forensic investigations, making it easier for specialists to identify relevant evidence such as images and chat logs while minimizing exposure to unrelated or distressing material. However, the same AI technologies are also being exploited by threat actors to create highly realistic deepfakes—synthetic images, videos, and voices—that are difficult to distinguish from genuine content. These deepfakes are used in a variety of malicious campaigns, including misinformation, fraud, identity theft, and sophisticated social engineering attacks. State-sponsored groups from countries like Iran, China, North Korea, and Russia have been documented using AI-generated media for phishing, reconnaissance, and information warfare, with specific examples including Iranian actors impersonating officials and North Korean hackers using fake job interviews to infiltrate organizations. The rapid evolution of deepfake technology has led to the development of advanced AI-powered detection tools that utilize machine learning, computer vision, and biometric analysis to identify manipulated content before it can cause harm. Despite these advances, challenges remain: AI models can struggle with altered media, such as deepfakes, and require constant retraining with supervised, high-quality data to avoid errors and hallucinations. Public concern over the misuse of deepfakes is growing, with surveys indicating that half of young people in the UK fear non-consensual deepfake nudes, and a significant portion of the population worries about financial losses, scams, and unauthorized access to sensitive information facilitated by AI-generated content. The emotional and psychological risks associated with malicious deepfakes are substantial, particularly when individuals or their families are targeted. There is also a notable gap in public understanding of deepfake threats, with a portion of the population unable to identify deepfake calls, underscoring the need for greater education and awareness. Organizations are increasingly adopting AI-powered security awareness training to help employees recognize and respond to evolving social engineering tactics. The dual use of AI in both cybercrime and its detection highlights the urgent need for ongoing collaboration, improved training, and the responsible development of AI technologies to mitigate risks while enhancing digital forensics capabilities. As AI continues to advance, both the sophistication of attacks and the tools to counter them are expected to grow, making vigilance and adaptability essential for cybersecurity professionals and the public alike.
Jun 29, 2026
Criminals are leveraging AI tools to manipulate publicly available images and videos from social media, creating convincing fake 'proof of life' media for use in virtual kidnapping and extortion scams. The FBI has warned that these scams involve contacting victims with claims of having kidnapped a loved one, often accompanied by doctored images or videos to increase credibility and pressure for ransom payment. The ease of accessing personal media online and the sophistication of AI-driven image and video manipulation have made these scams more convincing and difficult to detect, with the FBI noting a rise in such emergency scams and significant financial losses for victims. The proliferation of AI-generated media has also led to broader concerns about the spread of deepfakes and nonconsensual explicit imagery. Security researchers have uncovered exposed databases from AI image generator startups containing millions of manipulated images, including nonconsensual 'nudified' photos of real people and even children. These developments highlight the growing risks posed by AI-powered media manipulation, both for targeted extortion schemes and for the privacy and safety of individuals whose images are scraped and abused online.
Jun 29, 2026
Gartner found that AI-enabled deepfake impersonation is making social-engineering attacks more convincing across phone calls, video conferences, email, and text messages. Of 297 senior cybersecurity leaders surveyed, **41%** reported a deepfake-related employee audio-call incident and **36%** reported a video-call incident in the preceding 12 months; **79%** encountered phishing, spear-phishing, or business-email-compromise activity. A prominent example was the 2024 fraud against engineering firm Arup, where video-call impersonations of colleagues persuaded an employee to transfer more than **$25 million** to criminal-controlled accounts. Gartner urged organizations to replace training focused on spotting fakes with mandatory, out-of-band verification for sensitive requests. CISOs should apply phishing-resistant and risk-based identity controls to high-value workflows, correlate suspicious communications with identity, device, privilege, and payment activity, and extend incident-response plans to cover multimodal impersonation and compromised AI agents.
Sep 25, 2026