Recent advances in generative AI have led to the development of techniques to
generate visually realistic synthetic video. While a number of techniques have
been developed to detect AI-generated synthetic images, in this paper we show
that synthetic image detectors are unable to detect synthetic videos. We
demonstrate that this is because synthetic video generators introduce
substantially different traces than those left by image generators. Despite
this, we show that synthetic video traces can be learned, and used to perform
reliable synthetic video detection or generator source attribution even after
H.264 re-compression. Furthermore, we demonstrate that while detecting videos
from new generators through zero-shot transferability is challenging, accurate
detection of videos from a new generator can be achieved through few-shot
learning.

生成式人工智能的最新进展已经导致了生成视觉逼真合成视频的技术的发展。本文证明合成图像检测器无法检测合成视频，因为合成视频生成器引入的痕迹与图像生成器留下的痕迹明显不同。尽管如此，我们展示了合成视频痕迹是可以学习的，并且可以在 H.264 重新压缩后用于可靠的合成视频检测或生成器来源归因。此外，我们还证明了通过零样本迁移进行新生成器的视频检测具有挑战性，但可以通过少样本学习实现对新生成器的准确检测。

超越深度伪造图像：检测人工智能生成的视频

Beyond Deepfake Images: Detecting AI-Generated Videos

This paper releases and analyzes two new Huawei cloud serverless traces. The
traces span a period of over 7 months with over 1.4 trillion function
invocations combined. The first trace is derived from Huawei's internal
workloads and contains detailed per-second statistics for 200 functions running
across multiple Huawei cloud data centers. The second trace is a representative
workload from Huawei's public FaaS platform. This trace contains per-minute
arrival rates for over 5000 functions running in a single Huawei data center.
We present the internals of a production FaaS platform by characterizing
resource consumption, cold-start times, programming languages used,
periodicity, per-second versus per-minute burstiness, correlations, and
popularity. Our findings show that there is considerable diversity in how
serverless functions behave: requests vary by up to 9 orders of magnitude
across functions, with some functions executed over 1 billion times per day;
scheduling time, execution time and cold-start distributions vary across 2 to 4
orders of magnitude and have very long tails; and function invocation counts
demonstrate strong periodicity for many individual functions and on an
aggregate level. Our analysis also highlights the need for further research in
estimating resource reservations and time-series prediction to account for the
huge diversity in how serverless functions behave.
Datasets and code available at this https URL

对华为云无服务器服务的行为进行了分析，发现函数的请求和执行方式存在巨大差异，资源消耗和时间分布也存在多样性，需要进一步研究资源预留和时序预测。

生产无服务器工作负载的长期趋势特征

How Does It Function? Characterizing Long-term Trends in Production  Serverless Workloads

We report the current state of the graph isomorphism problem from the
practical point of view. After describing the general principles of the
refinement-individualization paradigm and proving its validity, we explain how
it is implemented in several of the key programs. In particular, we bring the
description of the best known program nauty up to date and describe an
innovative approach called Traces that outperforms the competitors for many
difficult graph classes. Detailed comparisons against saucy, Bliss and conauto
are presented.

本文介绍了图同构问题的研究现状和解决方法，重点讨论了细化 - 个体化范式和其在程序中的实现，以及描述了一个名为 Traces 的创新方法，该方法在许多难解的图类中胜过竞争对手，包括与 saucy，Bliss 和 conauto 的详细比较。