During the deployment of deep neural networks (DNNs) on edge devices, many research efforts are devoted to the limited hardware resource. However, little attention is paid to the influence of dynamic power management. As edge devices typically only have a budget of energy with batteries (rather than almost unlimited energy support on servers or workstations), their dynamic power management often changes the execution frequency as in the widely-used dynamic voltage and frequency scaling (DVFS) technique. This leads to highly unstable inference speed performance, especially for computation-intensive DNN models, which can harm user experience and waste hardware resources. We firstly identify this problem and then propose All-in-One, a highly representative pruning framework to work with dynamic power management using DVFS. The framework can use only one set of model weights and soft masks (together with other auxiliary parameters of negligible storage) to represent multiple models of various pruning ratios. By re-configuring the model to the corresponding pruning ratio for a specific execution frequency (and voltage), we are able to achieve stable inference speed, i.e., keeping the difference in speed performance under various execution frequencies as small as possible. Our experiments demonstrate that our method not only achieves high accuracy for multiple models of different pruning ratios, but also reduces their variance of inference latency for various frequencies, with minimal memory consumption of only one model and one soft mask.

Robust prediction of citywide traffic flows at different time periods plays a crucial role in intelligent transportation systems. While previous work has made great efforts to model spatio-temporal correlations, existing methods still suffer from two key limitations: i) Most models collectively predict all regions' flows without accounting for spatial heterogeneity, i.e., different regions may have skewed traffic flow distributions. ii) These models fail to capture the temporal heterogeneity induced by time-varying traffic patterns, as they typically model temporal correlations with a shared parameterized space for all time periods. To tackle these challenges, we propose a novel Spatio-Temporal Self-Supervised Learning (ST-SSL) traffic prediction framework which enhances the traffic pattern representations to be reflective of both spatial and temporal heterogeneity, with auxiliary self-supervised learning paradigms. Specifically, our ST-SSL is built over an integrated module with temporal and spatial convolutions for encoding the information across space and time. To achieve the adaptive spatio-temporal self-supervised learning, our ST-SSL first performs the adaptive augmentation over the traffic flow graph data at both attribute- and structure-levels. On top of the augmented traffic graph, two SSL auxiliary tasks are constructed to supplement the main traffic prediction task with spatial and temporal heterogeneity-aware augmentation. Experiments on four benchmark datasets demonstrate that ST-SSL consistently outperforms various state-of-the-art baselines. Since spatio-temporal heterogeneity widely exists in practical datasets, the proposed framework may also cast light on other spatial-temporal applications. Model implementation is available at https://github.com/Echo-Ji/ST-SSL.

The security of artificial intelligence (AI) is an important research area towards safe, reliable, and trustworthy AI systems. To accelerate the research on AI security, the Artificial Intelligence Security Competition (AISC) was organized by the Zhongguancun Laboratory, China Industrial Control Systems Cyber Emergency Response Team, Institute for Artificial Intelligence, Tsinghua University, and RealAI as part of the Zhongguancun International Frontier Technology Innovation Competition (https://www.zgc-aisc.com/en). The competition consists of three tracks, including Deepfake Security Competition, Autonomous Driving Security Competition, and Face Recognition Security Competition. This report will introduce the competition rules of these three tracks and the solutions of top-ranking teams in each track.

Speech representation learning has improved both speech understanding and speech synthesis tasks for single language. However, its ability in cross-lingual scenarios has not been explored. In this paper, we extend the pretraining method for cross-lingual multi-speaker speech synthesis tasks, including cross-lingual multi-speaker voice cloning and cross-lingual multi-speaker speech editing. We propose a speech-text joint pretraining framework, where we randomly mask the spectrogram and the phonemes given a speech example and its transcription. By learning to reconstruct the masked parts of the input in different languages, our model shows great improvements over speaker-embedding-based multi-speaker TTS methods. Moreover, our framework is end-to-end for both the training and the inference without any finetuning effort. In cross-lingual multi-speaker voice cloning and cross-lingual multi-speaker speech editing tasks, our experiments show that our model outperforms speaker-embedding-based multi-speaker TTS methods. The code and model are publicly available at PaddleSpeech.

Network traffic classification is the basis of many network security applications and has attracted enough attention in the field of cyberspace security. Existing network traffic classification based on convolutional neural networks (CNNs) often emphasizes local patterns of traffic data while ignoring global information associations. In this paper, we propose a MLP-Mixer based multi-view multi-label neural network for network traffic classification. Compared with the existing CNN-based methods, our method adopts the MLP-Mixer structure, which is more in line with the structure of the packet than the conventional convolution operation. In our method, the packet is divided into the packet header and the packet body, together with the flow features of the packet as input from different views. We utilize a multi-label setting to learn different scenarios simultaneously to improve the classification performance by exploiting the correlations between different scenarios. Taking advantage of the above characteristics, we propose an end-to-end network traffic classification method. We conduct experiments on three public datasets, and the experimental results show that our method can achieve superior performance.

由于其稀疏和细长的性质，估算3D空间中准确的车道线仍然具有挑战性。在这项工作中，我们提出了M^2-3dlanenet，这是一个有效3D车道检测的多模式框架。旨在集成来自多传感器的互补信息，M^2-3dlanenet首先将多模式特征提取具有模态特异性骨架，然后将它们融合在统一的鸟眼视图（BEV）空间中。具体而言，我们的方法由两个核心组成部分组成。 1）要获得准确的2D-3D映射，我们提出了自上而下的BEV生成。其中，使用线条限制的变形（LRDA）模块可用于以自上而下的方式有效地增强图像特征，从而充分捕获车道的细长特征。之后，它使用深度感知的举重将2D锥体特征投入到3D空间中，并通过枕形生成BEV特征。 2）我们进一步提出了自下而上的BEV融合，该融合通过多尺度的级联注意力汇总了多模式特征，从而集成了来自摄像头和激光雷达传感器的互补信息。足够的实验证明了M^2-3dlanenet的有效性，该实验的有效性超过了先前的最先进方法，即在OpenLane数据集上提高了12.1％的F1-SCORE改善。

特洛伊木马攻击对AI系统构成了严重威胁。有关变压器模型的最新著作获得了爆炸性的流行，并且自我展示是无可争议的。这提出了一个核心问题：我们可以通过伯特和VIT中的注意力机制揭示特洛伊木马吗？在本文中，我们调查了特洛伊木马AIS中的注意力劫持模式，当存在特定的触发器时，触发令牌``绑架''的注意力重量。我们观察到来自自然语言处理（NLP）和计算机视觉（CV）域的Trojan变形金刚中劫持模式的一致性劫持模式。这种有趣的财产有助于我们了解伯特和VIT中的特洛伊木马机制。我们还提出了一个关注的特洛伊木马检测器（AHTD），以将特洛伊木马与干净的AI区分开。

随着相机和激光雷达传感器捕获用于自主驾驶的互补信息，已经做出了巨大的努力，通过多模式数据融合来开发语义分割算法。但是，基于融合的方法需要配对的数据，即具有严格的点对像素映射的激光点云和相机图像，因为培训和推理的输入都严重阻碍了在实际情况下的应用。因此，在这项工作中，我们建议通过充分利用具有丰富外观的2D图像来提高对点云上的代表性学习的2D先验辅助语义分割（2DPass），以增强对点云的表示。实际上，通过利用辅助模态融合和多尺度融合到单个知识蒸馏（MSFSKD），2DAPS从多模式数据中获取更丰富的语义和结构信息，然后在线蒸馏到纯3D网络。结果，配备了2DAPS，我们的基线仅使用点云输入显示出显着的改进。具体而言，它在两个大规模的基准（即Semantickitti和Nuscenes）上实现了最先进的方法，其中包括TOP-1的semantickitti的单扫描和多次扫描竞赛。

实时投标（RTB）是现代在线广告系统中的重要机制。广告商在RTB中采用投标策略来优化其广告效果，但根据各种财务要求，其中广泛采用的是投资回报（ROI）约束。在顺序招标过程中，ROI在非单调的情况下变化，通常在约束满意度和客观优化之间具有透视作用。通常在静态或轻微变化的市场中建立了约束 - 目标权衡解决方案。但是，由于无法适应不同的动态和部分可观察性，这些方法在非平稳广告市场中大大失败。在这项工作中，我们专门研究非机构市场的ROI限制招标。基于部分可观察到的马尔可夫决策过程，我们提出了第一个容纳非单调约束的硬屏障解决方案。我们的方法利用了无参数指标的奖励功能，并开发了课程指导的贝叶斯强化学习（CBRL）框架，以适应在非平稳广告市场中的约束目标权衡。在具有两个问题设置的大规模工业数据集上进行的广泛实验表明，CBRL在分布和分发数据制度方面都很好地概括了，并且具有出色的稳定性。

特洛伊木马攻击引起了严重的安全问题。在本文中，我们研究了Trojaned Bert模型的潜在机制。我们观察到木马模型的注意力焦点漂移行为，即，在遇到中毒输入时，触发令牌劫持了注意力的焦点，无论上下文如何。我们对这种现象提供了彻底的定性和定量分析，揭示了对特洛伊木马机制的见解。基于观察结果，我们提出了一个基于注意力的特洛伊木马检测器，以将木马模型与干净的模型区分开。据我们所知，这是第一篇分析特洛伊木马机制并根据变压器的注意力开发特洛伊木马检测器的论文。