Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Recent work has demonstrated that deep neural networks are vulnerable to adversarial examples---inputs that are almost indistinguishable from natural data and yet classified incorrectly by the network. In fact, some of the latest findings suggest that the existence of adversarial attacks may be an inherent weakness of deep learning models. To address this problem, we study the adversarial robustness of neural networks through the lens of robust optimization. This approach provides us with a broad and unifying view on much of the prior work on this topic. Its principled nature also enables us to identify methods for both training and attacking neural networks that are reliable and, in a certain sense, universal. In particular, they specify a concrete security guarantee that would protect against any adversary. These methods let us train networks with significantly improved resistance to a wide range of adversarial attacks. They also suggest the notion of security against a first-order adversary as a natural and broad security guarantee. We believe that robustness against such well-defined classes of adversaries is an important stepping stone towards fully resistant deep learning models. Code and pre-trained models are available at this https URL and this https URL.

Towards Deep Learning Models Resistant to Adversarial Attacks

Most existing machine learning classifiers are highly vulnerable to adversarial examples. An adversarial example is a sample of input data which has been modified very slightly in a way that is intended to cause a machine learning classifier to misclassify it. In many cases, these modifications can be so subtle that a human observer does not even notice the modification at all, yet the classifier still makes a mistake. Adversarial examples pose security concerns because they could be used to perform an attack on machine learning systems, even if the adversary has no access to the underlying model. Up to now, all previous work have assumed a threat model in which the adversary can feed data directly into the machine learning classifier. This is not always the case for systems operating in the physical world, for example those which are using signals from cameras and other sensors as an input. This paper shows that even in such physical world scenarios, machine learning systems are vulnerable to adversarial examples. We demonstrate this by feeding adversarial images obtained from cell-phone camera to an ImageNet Inception classifier and measuring the classification accuracy of the system. We find that a large fraction of adversarial examples are classified incorrectly even when perceived through the camera.

Adversarial examples in the physical world

Understanding and interpreting classification decisions of automated image classification systems is of high value in many applications, as it allows to verify the reasoning of the system and provides additional information to the human expert. Although machine learning methods are solving very successfully a plethora of tasks, they have in most cases the disadvantage of acting as a black box, not providing any information about what made them arrive at a particular decision. This work proposes a general solution to the problem of understanding classification decisions by pixel-wise decomposition of nonlinear classifiers. We introduce a methodology that allows to visualize the contributions of single pixels to predictions for kernel-based classifiers over Bag of Words features and for multilayered neural networks. These pixel contributions can be visualized as heatmaps and are provided to a human expert who can intuitively not only verify the validity of the classification decision, but also focus further analysis on regions of potential interest. We evaluate our method for classifiers trained on PASCAL VOC 2009 images, synthetic image data containing geometric shapes, the MNIST handwritten digits data set and for the pre-trained ImageNet model available as part of the Caffe open source package.

/pdf/on-pixel-wise-explanations-for-non-linear-classifier-4j59r9tlxm.pdf

On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation.

Whenever machine learning is used to prevent illegal or unsanctioned activity and there is an economic incentive, adversaries will attempt to circumvent the protection provided. Constraints on how adversaries can manipulate training and test data for classifiers used to detect suspicious behavior make problems in this area tractable and interesting. This special issue highlights papers that span many disciplines including email spam detection, computer intrusion detection, and detection of web pages deliberately designed to manipulate the priorities of pages returned by modern search engines. The four papers in this special issue provide a standard taxonomy of the types of attacks that can be expected in an adversarial framework, demonstrate how to design classifiers that are robust to deleted or corrupted features, demonstrate the ability of modern polymorphic engines to rewrite malware so it evades detection by current intrusion detection and antivirus systems, and provide approaches to detect web pages designed to manipulate web page scores returned by search engines. We hope that these papers and this special issue encourages the multidisciplinary cooperation required to address many interesting problems in this relatively new area including predicting the future of the arms races created by adversarial learning, developing effective long-term defensive strategies, and creating algorithms that can process the massive amounts of training and test data available for internet-scale problems.

Machine learning in adversarial environments

Efficient and expressive comparison of sequences is an essential procedure for learning with sequential data. In this article we propose a generic framework for computation of similarity measures for sequences, covering various kernel, distance and non-metric similarity functions. The basis for comparison is embedding of sequences using a formal language, such as a set of natural words, k-grams or all contiguous subsequences. As realizations of the framework we provide linear-time algorithms of different complexity and capabilities using sorted arrays, tries and suffix trees as underlying data structures.

Experiments on data sets from bioinformatics, text processing and computer security illustrate the efficiency of the proposed algorithms---enabling peak performances of up to 106 pairwise comparisons per second. The utility of distances and non-metric similarity measures for sequences as alternatives to string kernels is demonstrated in applications of text categorization, network intrusion detection and transcription site recognition in DNA.

/pdf/linear-time-computation-of-similarity-measures-for-du83l2k4s8.pdf

Linear-Time Computation of Similarity Measures for Sequential Data

The paper presents two useful extensions of the incremental SVM in the context of online learning. An online support vector data description algorithm enables application of the online paradigm to unsupervised learning. Furthermore, online learning can be used in the large-scale classification problems to limit the memory requirements for storage of the kernel matrix. The proposed algorithms are evaluated on the task of online monitoring of EEG data, and on the classification task of learning the USPS dataset with a-priori chosen working set size.

Online SVM learning: from classification to data description and back

In this paper, we propose a method for network intrusion detection based on language models. Our method proceeds by extracting language features such as n-grams and words from connection payloads and applying unsupervised anomaly detection—without prior learning phase or presence of labeled data. The essential part of this procedure is linear-time computation of similarity measures between language models of connection payloads. Particular patterns in these models decisive for differentiation of attacks and normal data can be traced back to attack semantics and utilized for automatic generation of attack signatures. Results of experiments conducted on two datasets of network traffic demonstrate the importance of high-order n-grams and variable-length language models for detection of unknown network attacks. An implementation of our system achieved detection accuracy of over 80% with no false positives on instances of recent remote-to-local attacks in HTTP, FTP and SMTP traffic.

Language models for detection of unknown attacks in network traffic

Detection of Intrusions and Malware, and Vulnerability Assessment: 19th International Conference, DIMVA 2022, Cagliari, Italy, June 29 –July 1, 2022, Proceedings

Pavel Laskov

Papers

Machine learning in adversarial environments

Linear-Time Computation of Similarity Measures for Sequential Data

Online SVM learning: from classification to data description and back

Language models for detection of unknown attacks in network traffic

Detection of Intrusions and Malware, and Vulnerability Assessment: 19th International Conference, DIMVA 2022, Cagliari, Italy, June 29 –July 1, 2022, Proceedings