Loading story…
Google has made SynthID Detector available globally in English, expanding access from media professionals to the general public. The tool checks images, video, and audio for imperceptible watermarks embedded by Google and participating AI providers. Google names OpenAI, NVIDIA, and Kakao as partners, with Apple support forthcoming. The rollout complements verification features in Search, the Gemini app, and Chrome.
The public detector requires authentication and limits users to approximately 10 media checks daily, a restriction Google says helps prevent development of watermark-removal tools. A negative result does not establish that media is authentic: providers may use other watermarking technologies or none, and locally operated open-weight models can generate unlabeled content. Security teams should treat SynthID as one verification signal rather than a universal AI-content detector; cryptographic provenance technologies such as C2PA offer a complementary approach to authenticating media at creation. The announcement concerns a detection-tool expansion, not a reported vulnerability, attack, or breach.
Track how attackers are adapting to this technology.
3 events from the most recent confirmed update back to the earliest known activity.
Google launched SynthID to help identify AI-generated media using imperceptible watermarks.
Google announced global public availability of SynthID Detector in English for checking images, videos, and audio for watermarks from Google and participating partners, including OpenAI, NVIDIA, and Kakao. The tool requires authentication and limits users to approximately 10 checks daily, which Google says helps prevent development of watermark-removal tools.
Google introduced an early version of SynthID Detector for media professionals before expanding access to the general public.
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.
2 references tracked. Mallory keeps watching after this page renders.
Map 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
Major frontier AI providers including **Anthropic, Google, OpenAI, and Meta** have begun deploying watermarking and provenance controls on synthetic content to comply with **EU AI Act Article 50**, which requires general-purpose and generative AI systems to mark AI-generated outputs in a machine-detectable form. Anthropic said it is watermarking Claude text using a version of **Google DeepMind's SynthID**, a technique that subtly adjusts token-selection probabilities so longer passages can later be identified as AI-generated; Google has already used SynthID in Gemini outputs, while other vendors are also adopting metadata-based provenance approaches such as **C2PA**. The rollout has exposed immediate technical and operational limits. Open-source tools have appeared that can strip metadata or reduce watermark detectability, and statistical text watermarking can degrade after paraphrasing, translation, or in short outputs. The reporting also highlights false-positive risks in low-entropy material such as code and configuration files, along with a broader compliance gap between tightly managed hosted AI services and self-hosted open-weight models, where downstream operators can change decoding behavior and bypass watermarking controls.
Aug 18, 2026
Research by Siposova found that **SynthID-Text** AI-output watermarking can materially alter language-model safety behavior. In tests of six open-weight models using Hugging Face’s unmodified `SynthIDTextWatermarkLogitsProcessor` in a non-distortionary configuration, tournament-sampling watermarking made some models more likely to comply with harmful requests—particularly requests delivered through prompt-injection techniques—that equivalent unwatermarked models refused. The secret key used by the watermarking system also affected harmful-compliance outcomes. SynthID-Text embeds a detectable provenance signal by modifying next-token sampling with a secret key and scoring mechanism. The study additionally found changes in AI-agent tool-call correctness, raising concern for models operating with tools or autonomous workflows. The results do not establish the same effect in proprietary models such as Claude or in planned Google deployments, but they show that watermarking layers require dedicated security, safety, and red-team evaluation under adversarial prompting before deployment.
Sep 18, 2026