AI 模型和平台
软件包发布 AI 图像和视频检测的两个模型
在 Google 上的首选来源中添加 Unite.AI
2026年11月4日的Pangram 宣布两种计算机视觉模型：用于检测AI生成的图像的Pangram Image 1.0和用于按帧分析AI视频帧的较小，更快的Pangram Image Flash 1.0. 发行时还发布了推出热映射输出，本土视频上传，Chrome扩展集成和API支持图像和视频。
图像1.0的热映射是为了将合成材料定位在图像中，如原为真实照片中的AI生成元素。 在X上的一个官方的发布帖子中，Pangram 称模型识别出99.2%的AI生成的图像，同时保持0.27%的假阳性率。
图片和视频测试
为其图像评价，Pangram用12个图像生成器创建了100张真实照片的合成镜像。 提示紧密匹配每张原始照片，产生1,200张合成图像；Pangram报告该公司制作的图像1.0的准确度为99.96%。 该图描述了这种将真实的和合成的图像进行定点配对的性能，而不是对在网上遇到的每个图像的普遍精确率。
视频比较采用了类似的合成-镜像原理。 Pangram开始使用129个真实的社会媒体视频，并使用14个视频发电机，每台发电机创建100个合成视频，从真实集中抽取，共计1,529个视频。 每个生成器都收到了真实的视频第一帧和视觉语言模型对动作的描述。 由于每个真实的视频及其合成的对应器都共享一个场景和主题，设计测试一个探测器是否能够区分出相似的片段而不奖励将特定内容与AI联系在一起的捷径。
DF26 视频基准测试
Pangram评价了Flash 1.0与DF26，一个在2026年9月7日提交的预印本中描述的基准测试。 基准测试包含271个真实视频和2,420个合成视频，由7个现代视频模型制作，侧重于一人在直接对相机录音，官方声明和工作室采访中发言。 其作者报告说，人们和最先进深假探测器都进行了接近随机机会的检测，并主张进行明确测试强性的评价，以测试从现代发电机到分配的转变。
Pangram 称 Image Flash 1.0在DF26上得分98.7%，比次佳探测器高29分。 原生视频上传将模型放入仪表板：Flash分析每个帧，并识别上传视频的哪些部分返回AI检测。
研究预览以外的部署
2026年7月29日的研究预览只接受512到512像素或更大的图像，并将深假和面值互换列为无法自信地检测的案例。 Pangram 称版本1.0改进了深假，低分辨率图像和前沿生成模型上的性能。 现在最小的输入值为256乘以256像素，但低于512像素的图像会产生一种降低信心的解说。
Pangram 称它训练新的模型来检测压缩，缩小尺度，模糊和噪音等变换，无论是社交平台的推出还是试图逃避检测的演员。 自预览以来，访问范围也有所扩大，当时图像API访问仅为邀请，仪表板视频输入和Chrome集成被列为未来工作。 Image 1.0被整合到Chrome扩展，以旗下AI生成的跨社交媒体，购物和出租网站的材料，而更新的API支持图像和视频检测。
发行的实际意义是新模式与这些接入点的结合：检测可以在浏览器的种子中运行，在上传的视频中运行或通过API集成运行。 对较小图像的不信任的否定仍然是关键条件，表明更广泛的输入支持和更广泛的分布并不等于每个图像具有统一的信任。
本文由 AI图鉴自动抓取并翻译，版权归原作者所有；如需查看原文请点下方链接。
AI Models & Platforms
Pangram Launches Two Models for AI Image and Video Detection
Add Unite.AI to your preferred sources on Google
Pangram announced two computer-vision models on November 4, 2026: Pangram Image 1.0 for detecting AI-generated images and the smaller, faster Pangram Image Flash 1.0 for analyzing AI video frame by frame. The release also introduces heatmap output, native video uploads, Chrome extension integration and API support for images and video.
Image 1.0’s heatmap is intended to localize synthetic material within an image, such as an AI-generated element inside an otherwise real photograph. In an official launch post on X, Pangram said the model identifies 99.2% of AI-generated images while maintaining a 0.27% false-positive rate.
Paired Image and Video Tests
For its image evaluation, Pangram created synthetic mirrors of 100 real photographs with 12 image generators. Prompts closely matched each original photo, producing 1,200 synthetic images; Pangram reports 99.96% accuracy for Image 1.0 on that company-created set. The figure describes performance on this targeted pairing of real and synthetic images, rather than a universal accuracy rate for every image encountered online.
The video comparison applied a similar synthetic-mirror principle. Pangram started with 129 real social-media videos and used 14 video generators to create 100 synthetic videos per generator, sampled from the real set, for 1,529 videos in total. Each generator received the real video’s first frame and a vision-language model’s description of the action. Because each real video and its synthetic counterpart share a scene and subject, the design tests whether a detector can distinguish similar clips without rewarding a shortcut that associates particular content with AI.
The DF26 Video Benchmark
Pangram evaluated Flash 1.0 with DF26, a benchmark described in a preprint submitted on September 7, 2026. The benchmark contains 271 real and 2,420 synthetic videos produced by seven modern video models, focused on one person speaking in direct-to-camera recordings, official statements and studio interviews. Its authors report that both people and state-of-the-art deepfake detectors performed close to random chance, and argue for evaluations that explicitly test robustness to distribution shifts from modern generators.
Pangram says Image Flash 1.0 scores 98.7% on DF26, 29 points above the next-best detector. Native video uploads put that model into the dashboard: Flash analyzes each frame and identifies which portions of an uploaded video return an AI detection.
Deployment Beyond the Research Preview
The July 29, 2026 research preview accepted images only at 512 by 512 pixels or larger and listed deepfakes and face swaps as cases it could not confidently detect. Pangram says version 1.0 improves performance on deepfakes, low-resolution images and frontier generation models. The minimum input is now 256 by 256 pixels, but images below 512 pixels produce a reduced-confidence disclaimer.
Pangram says it trains the new model to detect transformations such as compression, downscaling, blur and noise, whether introduced by social platforms or by actors attempting to evade detection. Access has also widened since the preview, when image API access was invitation-only and dashboard video input and Chrome integration were listed as future work. Image 1.0 is integrated into the Chrome extension to flag AI-generated material across social media, shopping and rental sites, while the updated API supports both image and video detection.
The release’s practical significance is the combination of the new models with those access points: detection can run in a browser feed, on an uploaded video or through an API integration. The reduced-confidence disclaimer for smaller images remains the key qualification, showing that broader input support and wider distribution do not amount to uniform confidence across every image.
Auto-fetched and translated by AI Atlas. All rights belong to the original author.