We present a multi-scale predictive coding model for future video frames prediction. Drawing inspiration on the ``Predictive Coding" theories in cognitive science, it is updated by a combination of bottom-up and top-down information flows, which can enhance the interaction between different network levels. However, traditional predictive coding models only predict what is happening hierarchically rather than predicting the future. To address the problem, our model employs a multi-scale approach (Coarse to Fine), where the higher level neurons generate coarser predictions (lower resolution), while the lower level generate finer predictions (higher resolution). In terms of network architecture, we directly incorporate the encoder-decoder network within the LSTM module and share the final encoded high-level semantic information across different network levels. This enables comprehensive interaction between the current input and the historical states of LSTM compared with the traditional Encoder-LSTM-Decoder architecture, thus learning more believable temporal and spatial dependencies. Furthermore, to tackle the instability in adversarial training and mitigate the accumulation of prediction errors in long-term prediction, we propose several improvements to the training strategy. Our approach achieves good performance on datasets such as KTH, Moving MNIST and Caltech Pedestrian. Code is available at https://github.com/Ling-CF/MSPN.

As we move towards a future where we lean on cybersecurity much more in our daily lives, it's important to be aware of the differences in the types of AI being used for network security. Over the last decade, Machine Learning has made huge progress in technology with Supervised and Reinforcement learning, in everything from photo recognition to self-driving cars. However, Supervised Learning is limited in its network security abilities like finding threats because it only looks for specifics that it has seen or labeled before, whereas Unsupervised Learning is constantly searching the network to find anomalies. Machine Learning comes in a few forms: Supervised, Reinforcement, Unsupervised and Semi-Supervised (also known as Active Learning). Supervised Learning relies on a process of labeling in order to "understand" information.

As we move towards a future where we lean on cybersecurity much more in our daily lives, it's important to be aware of the differences in the types of AI being used for network security. Over the last decade, Machine Learning has made huge progress in technology with Supervised and Reinforcement learning, in everything from photo recognition to self-driving cars. However, Supervised Learning is limited in its network security abilities like finding threats because it only looks for specifics that it has seen or labeled before, whereas Unsupervised Learning is constantly searching the network to find anomalies. Machine Learning comes in a few forms: Supervised, Reinforcement, Unsupervised and Semi-Supervised (also known as Active Learning). Supervised Learning relies on a process of labeling in order to "understand" information.

For the last few years, internet security has been based on a combination of anti-virus software, isolation techniques and encryption software. Government bodies and security companies would track traffic on the internet and look for suspicious materials based upon their signature. These techniques focused on running anti-malware software after the facts. They enabled the segregation between good data and malware. But if malware was undetected, it could lurk in the background of systems for months or even years and become active later in time. The consumer world is rapidly changing.

Not all Artificial Intelligence is created equal. As we move towards a future where we lean on cybersecurity much more in our daily lives, it's important to be aware of the differences in the types of AI being used for network security. Dr. Igor, Chief Scientist and CTO at MixMode explains: Over the last decade, Machine Learning has made huge progress in technology with Supervised and Reinforcement learning, in everything from photo recognition to self-driving cars. However, Supervised Learning is limited in its network security abilities like finding threats because it only looks for specifics that it has seen or labeled before, whereas Unsupervised Learning is constantly searching the network to find anomalies. Machine Learning comes in a few forms: Supervised, Reinforcement, Unsupervised and Semi-Supervised (also known as Active Learning).

The objective of this article is to optimize the overall traffic flow on freeways using multiple ramp metering controls plus its complementary Dynamic Speed Limits (DSLs). An optimal freeway operation can be reached when minimizing the difference between the freeway density and the critical ratio for maximum traffic flow. In this article, a Multi-Agent Reinforcement Learning for Freeways Control (MARL-FWC) system for ramps metering and DSLs is proposed. MARL-FWC introduces a new microscopic framework at the network level based on collaborative Markov Decision Process modeling (Markov game) and an associated cooperative Q-learning algorithm. The technique incorporates payoff propagation (Max-Plus algorithm) under the coordination graphs framework, particularly suited for optimal control purposes. MARL-FWC provides three control designs: fully independent, fully distributed, and centralized; suited for different network architectures. MARL-FWC was extensively tested in order to assess the proposed model of the joint payoff, as well as the global payoff. Experiments are conducted with heavy traffic flow under the renowned VISSIM traffic simulator to evaluate MARL-FWC. The experimental results show a significant decrease in the total travel time and an increase in the average speed (when compared with the base case) while maintaining an optimal traffic flow.

The following is a guest article from Dr. Sven Krasser, chief scientist at CrowdStrike. Without a doubt, machine learning is one of the hottest topics in cybersecurity at the moment, and most vendors boast their newest machine learning additions as the panacea that liberates you from all security woes. Machine learning allows security products to do vastly better in various areas. However, it is best understood as a set of techniques that dramatically optimize detection techniques. It does not allow sidestepping inherent limitations e.g.

Compared to common DoS/DDoS attacks that are destructive and generate massive traffic, the application layer DoS attacks can be slow-and-low which means they occur at a slow rate and do not generate a massive amount of traffic. These attacks appear legitimate in terms of the protocol rules and rates. These characteristics make the detection of these attacks difficult. In this paper, we study the RUDY (R-U-Dead- Yet) attack which is one of the slow-and-low application layer attack types. RUDY attacks can bring down a server by creating long POST HTTP form submissions to the server at a very slow rate which results in application threads at the server side becoming stuck. The mitigation methods against RUDY attacks are mostly host-based. In this paper, we use a machine learning approach for the detection of RUDY attacks as well as determining the important features for their detection at the network level. The network level detection is scalable and it provides detection for hosts that do not have their own detection mechanism.We extract features from bi-directional instances of the network traffic.We then use an ensemble feature selection approach containing 10 different feature ranker methods in order to extract the most important features for the detection of RUDY attacks at the network level.