Fuzzing is a commonly used technique designed to test software by automatically crafting program inputs. Currently, the most successful fuzzing algorithms emphasize simple, low-overhead strategies with the ability to efficiently monitor program state during execution. Through compile-time instrumentation, these approaches have access to numerous aspects of program state including coverage, data flow, and heterogeneous fault detection and classification. However, existing approaches utilize blind random mutation strategies when generating test inputs. We present a different approach that uses this state information to optimize mutation operators using reinforcement learning (RL). By integrating OpenAI Gym with libFuzzer we are able to simultaneously leverage advancements in reinforcement learning as well as fuzzing to achieve deeper coverage across several varied benchmarks. Our technique connects the rich, efficient program monitors provided by LLVM Santizers with a deep neural net to learn mutation selection strategies directly from the input data. The cross-language, asynchronous architecture we developed enables us to apply any OpenAI Gym compatible deep reinforcement learning algorithm to any fuzzing problem with minimal slowdown.

Since the early days of machine learning, artificial intelligence scenarios have faced with two big challenges in order to experience mainstream adoption. First, we have the data efficiency problem that requires machine or deep learning models to be trained using large and accurate datasets which, as we know, are really expensive to build and maintain. Secondly, we have the generalization problem which AI agents face in order to build new knowledge that is different from the training data. Humans, by contrast, are incredibly efficient learning with minimum supervision and rapidly generalizing knowledge from a few data examples. Generative models are one of the deep learning disciplines that focuses on addressing the two challenges mentioned above.

Many deep models have been recently proposed for anomaly detection. This paper presents comparison of selected generative deep models and classical anomaly detection methods on an extensive number of non--image benchmark datasets. We provide statistical comparison of the selected models, in many configurations, architectures and hyperparamaters. We arrive to conclusion that performance of the generative models is determined by the process of selection of their hyperparameters. Specifically, performance of the deep generative models deteriorates with decreasing amount of anomalous samples used in hyperparameter selection. In practical scenarios of anomaly detection, none of the deep generative models systematically outperforms the kNN.

We introduce a deep generative model for functions. Our model provides a joint distribution p(f, z) over functions f and latent variables z which lets us efficiently sample from the marginal p(f) and maximize a variational lower bound on the entropy H(f). We can thus maximize objectives of the form E_{f~p(f)}[R(f)] + c*H(f), where R(f) denotes, e.g., a data log-likelihood term or an expected reward. Such objectives encompass Bayesian deep learning in function space, rather than parameter space, and Bayesian deep RL with representations of uncertainty that offer benefits over bootstrapping and parameter noise. In this short paper we describe our model, situate it in the context of prior work, and present proof-of-concept experiments for regression and RL.

We introduce Glow, a reversible generative model which uses invertible 1x1 convolutions. It extends previous work on reversible generative models and simplifies the architecture. Our model can generate realistic high resolution images, supports efficient sampling, and discovers features that can be used to manipulate attributes of data. We're releasing code for the model and an online visualization tool so people can explore and build on these results. The model isn't given attribute labels at training time, yet it learns a latent space where certain directions correspond to changes in attributes like beard density, age, hair color, and so on.

On Monday, non-profit AI research company OpenAI published a blog post about OpenAI Five, a group of five neural networks designed to work as a team while playing the real-time computer strategy game called Dota 2. According to the post, OpenAI Five can now beat a team of five human amateur players at the game, albeit with specific restrictions placed on gameplay. In August, it will attempt to beat a team of professional Dota 2 players at The International (TI), an annual Dota 2 tournament hosted by the game's developer, Valve Corporation.

On Monday, non-profit AI research company OpenAI published a blog post about OpenAI Five, a group of five neural networks designed to work as a team while playing the real-time computer strategy game called Dota 2. According to the post, OpenAI Five can now beat a team of five human amateur players at the game, albeit with specific restrictions placed on gameplay. In August, it will attempt to beat a team of professional Dota 2 players at The International (TI), an annual Dota 2 tournament hosted by the game's developer, Valve Corporation.

In this paper, we demonstrate the potential of applying Variational Autoencoder (VAE) [10] for anomaly detection in skin disease images. VAE is a class of deep generative models which is trained by maximizing the evidence lower bound of data distribution [10]. When trained on only normal data, the resulting model is able to perform efficient inference and to determine if a test image is normal or not. We perform experiments on ISIC2018 Challenge Disease Classification dataset (Task 3) and compare different methods to use VAE to detect anomaly. The model is able to detect all diseases with 0.779 AUCROC. If we focus on specific diseases, the model is able to detect melanoma with 0.864 AUCROC and detect actinic keratosis with 0.872 AUCROC, even if it only sees the images of nevus. To the best of our knowledge, this is the first applied work of deep generative models for anomaly detection in dermatology.

Gary Numan once asked: are friends electric? Well, if you're a robot -- the answer is a resounding "affirmative". In a landmark event, AI has beaten humans in a teamwork related video game called Dota 2. Bill Gates calls the event "a big deal, because their victory required teamwork and collaboration – a huge milestone in advancing artificial intelligence." The AI team, comprised of five neural networks and collectively called OpenAI Five (itself part of the larger OpenAI) is funded by Elon Musk. These five separate neural networks played 180 years worth of Dota 2 against itself every day for about two months.

Five different AI algorithms have teamed up to kick human butt in Dota 2, a popular strategy computer game. Researchers at OpenAI, a nonprofit based in California, developed the algorithmic A team, which they call the OpenAI Five. Each algorithm uses a neural network to learn not only how to play the game, but also how to cooperate with its AI teammates. It has started defeating amateur Dota 2 players in testing, OpenAI says. This is an important and novel direction for AI, since algorithms typically operate independently.