Loading story…
Google launched a new Google Earth web feature built around its Nano Banana 2 image generator, allowing users to create artificial satellite-style imagery inside the mapping platform. The company promoted the capability as a way to reimagine places in Google Earth, but the rollout was short-lived after users and researchers rapidly tested the system and demonstrated that it could generate convincing false overhead images of events that never happened.
Reports showed the tool could produce photorealistic depictions of sensitive scenarios, including disasters, conflict damage, and geopolitical incidents, while some of the feature's guardrails were reportedly easy to bypass. Google said it rolled back the feature after generated imagery appeared to violate company policies and that it would work on stronger safeguards; critics said provenance controls such as SynthID watermarks were not enough because screenshots could be shared without reliable detection, raising risks for journalism, crisis reporting, and trust in visual evidence.
Track how attackers are adapting to this technology.
3 events from the most recent confirmed update back to the earliest known activity.
Google enabled a new Google Earth web feature on July 30, 2026 that used the Nano Banana 2 image generator to create artificial satellite-style images from real satellite imagery. The feature was made available to all users.
Google said it was rolling back the Google Earth feature after users shared generated imagery that appeared to violate its policies. The company said it would implement stronger guardrails rather than stating the feature was permanently discontinued.
Within hours of the launch, researchers and news outlets demonstrated that the feature could produce convincing photorealistic satellite-style images of events that never happened, including disasters and geopolitical incidents. Reported tests by Henk van Ess, NPR, and BBC also showed that basic guardrails could be bypassed or failed to block sensitive prompts.
Vulnerabilities, threat actors, malware, products, organizations, and breaches Mallory has linked to this story.
Follow how adversaries are adapting to this technology, and where it touches your stack today.
8 references tracked. Mallory keeps watching after this page renders.
malware.news
Open sourcemalwarebytes.com
Open sourcetechtimes.com
Open sourcenpr.org
Open sourcebbc.com
Open sourcedigitaldigging.org
Open sourceblog.google
Open sourcemalwarebytes.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.
The European Union is beginning to enforce AI transparency obligations that require public-facing AI systems to disclose when users are interacting with AI and require providers of tools that generate or manipulate synthetic **image, audio, video, and text** to make those outputs identifiable as AI-generated or AI-altered. The rules apply to deepfakes and other synthetic media, call for both visible disclosures and technical markers such as watermarks or embedded metadata, and set a later compliance deadline for existing systems. Exemptions cover some personal-use, artistic, satirical, fictional, law-enforcement, and human-edited text scenarios, though disclosure may still be required depending on context. The rollout is accelerating industry efforts around content provenance and watermarking. Google backed the EU AI Act transparency code of practice and pointed to its **SynthID** watermarking system and work on the **C2PA** standard, while also warning that overlapping labeling mandates could create confusion and hurt competitiveness. Reporting on SynthID said Google’s AI tools have already produced more than **100 billion** images and videos and that partners including **OpenAI, NVIDIA, Apple, ElevenLabs, Kakao,** and others are testing interoperable labeling approaches, even as researchers note that metadata-based labeling can be stripped and watermarking alone is unlikely to solve misinformation at internet scale.
Aug 7, 2026
European policymakers advanced new measures aimed at limiting **AI-enabled sexual abuse and impersonation harms**, with the **European Council** proposing amendments to the AI Act that would ban AI systems used to generate non-consensual intimate imagery, including **nudification tools** and child sexual abuse material. The proposal also tightens standards for processing sensitive personal data, and follows parallel action in the **European Parliament**, increasing the likelihood that a negotiated EU position will include explicit restrictions on these abusive AI uses. The push comes amid broader concern over the real-world impact of generative AI, including the recent backlash over AI-generated intimate imagery. Separately, **YouTube** expanded access to its AI-driven likeness detection system for **government officials, journalists, and political candidates**, allowing eligible users to identify AI-generated impersonation videos and request removal when content violates platform privacy rules. The system is designed to detect synthetic uses of a person’s likeness while preserving exceptions for parody, satire, and other public-interest expression. Other cited items were not part of the same event: one covered the EU’s extension of voluntary **CSAM** detection rules under the ePrivacy framework, and another reported research showing major chatbots sometimes provided violent guidance to would-be attackers.
Jun 29, 2026
Researchers reported that leading image-editing models and Spaces hosted on **Hugging Face** could be used to create nonconsensual sexualized deepfakes, including topless alterations of women’s photos, using straightforward prompts and without needing to bypass safeguards. Testing by AI Forensics found that seven of nine image-editing tools produced abusive outputs, while a broader review of top models and 1,000 image-editing prompts indicated widespread use of the software to generate explicit fake nude imagery. The findings also exposed an AI governance gap for organizations using public model repositories: the platform, model publisher, app developer, and inference provider may all be different entities, so platform availability does not guarantee safety. Researchers said decoy Hugging Face Spaces logged more than 1,000 requests in a week, most seeking to undress or sexualize uploaded images, primarily targeting women and in some cases appearing to involve children, prompting calls for enterprises to vet specific models and deployments, verify provenance, control updates and downloads, and assign clear incident ownership.
Jul 30, 2026