> For the complete documentation index, see [llms.txt](https://docs.adsecure.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.adsecure.com/features/content-classification.md). # Content Classification Classify the content of your ads and landing pages by identifying labels, logos, and unsafe content ## What is Content Classification? AdSecure started a comprehensive update focusing on the classification of content. In this first phase, ad creatives are analysed and the classification of content is reported in various dashboards in the AdSecure application. This new functionality will be powered by a combination of Google API and our own built-in machine learning tools. We understand that content classification and detection may not be relevant for all of our partners, so we operate on a voluntary, opt-in basis. Please let us know in case you would like to have 1 or more modules for content classification enabled on your account. ## Modules ### Unsafe Content The first module is Unsafe Content and uses five categories (***adult, spoof, medical, violence, and racy***) which will be flagged when it is likely that a given ad creative or landing page contains such content. Analytical results can be viewed in the dashboard *Unsafe Content* in the Analytics menu of your AdSecure application. ![](https://1597915041-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FPFKZe65DxLiZWt9eUQJw%2Fuploads%2FKWixPTllbQhFEonl9BZE%2Fae9f6841b6b2.png?alt=media\&token=f2aee3ed-2604-491a-ad4b-e29e3ba96dc7) ![](https://1597915041-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FPFKZe65DxLiZWt9eUQJw%2Fuploads%2FwFIu5nuuMXrKRNEh5izr%2F2734b2bca6b5.png?alt=media\&token=c336d788-a054-464c-a21d-6667ce0b7b43) In addition to the dashboard, there are 5 corresponding *Unsafe Content* violations introduced which will each be displayed in AdSecure reports when detected, just like you are used to from other violations in AdSecure. Please note that we can disable one or more detections if desired. * Unsafe content: Adult- Unsafe content: Spoof * Unsafe content: Medical * Unsafe content: Violence * Unsafe content: Racy ### Ad Labels The second module is Ad Labels, which reports information about entities in an ad image, across a broad group of categories. Labels can identify general objects, locations, activities, animal species, products, and more. Ad Labels has its own dedicated dashboard under the Analytics menu and can give you great insight into what exactly is appearing in your ad images, particularly if you have concerns about certain products, industries, etc. ![](https://1597915041-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FPFKZe65DxLiZWt9eUQJw%2Fuploads%2FzVG3vuzoaAFY8SznbGXh%2F3624699a812f.png?alt=media\&token=bb9edb76-f5a8-4c4e-a6fc-893f85e59cec) ![](https://1597915041-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FPFKZe65DxLiZWt9eUQJw%2Fuploads%2FErR9CUyyONDa3IPM6NaK%2F2394a4ea5a4c.png?alt=media\&token=3cbc0f0e-074f-4d72-8b79-0169c91b2f0c) ![](https://1597915041-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FPFKZe65DxLiZWt9eUQJw%2Fuploads%2FCHl742rsp5rG2wdM8599%2F0368794c89e5.png?alt=media\&token=8deea7cf-d82b-424d-af16-97fd82285e03) ### Logo Detection The third module is Logo Detection, which provides information about logos that are detected on ad images. Logo Detection has its own dedicated dashboard under the Analytics menu and can give great insight into which brands are involved with your ad campaigns. ![](https://1597915041-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FPFKZe65DxLiZWt9eUQJw%2Fuploads%2FgLANPW90HW80vOyZ6Qa1%2F3eaee67b4efb.png?alt=media\&token=43f34dd1-a8ec-4c50-9437-b3417fd67903) ![](https://1597915041-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FPFKZe65DxLiZWt9eUQJw%2Fuploads%2FTAL7RN0p84hsXP4KhXub%2F9db1b5a5f5cb.png?alt=media\&token=5d0045de-f40f-4d99-8865-cec7b699f6a5) ![](https://1597915041-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FPFKZe65DxLiZWt9eUQJw%2Fuploads%2FI89PzgeOzgTF6KZqaHDM%2F8ae53f4b0d1d.png?alt=media\&token=eb90801a-1a0f-4e3a-a8df-81cee1708f2f) --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.adsecure.com/features/content-classification.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.