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

Software vulnerabilities have had a devastating effect on the Internet. Worms such as CodeRed and Slammer can compromise hundreds of thousands of hosts within hours or even minutes, and cause millions of dollars of damage [26, 43]. To successfully combat these fast automatic Internet attacks, we need fast automatic attack detection and filtering mechanisms. In this paper we propose dynamic taint analysis for automatic detection of overwrite attacks, which include most types of exploits. This approach does not need source code or special compilation for the monitored program, and hence works on commodity software. To demonstrate this idea, we have implemented TaintCheck, a mechanism that can perform dynamic taint analysis by performing binary rewriting at run time. We show that TaintCheck reliably detects most types of exploits. We found that TaintCheck produced no false positives for any of the many different programs that we tested. Further, we describe how TaintCheck could improve automatic signature generation in

/pdf/dynamic-taint-analysis-for-automatic-detection-analysis-and-2bodbjb0mi.pdf

Dynamic Taint Analysis for Automatic Detection, Analysis, and Signature Generation of Exploits on Commodity Software

Network anomaly detection is an important and dynamic research area. Many network intrusion detection methods and systems (NIDS) have been proposed in the literature. In this paper, we provide a structured and comprehensive overview of various facets of network anomaly detection so that a researcher can become quickly familiar with every aspect of network anomaly detection. We present attacks normally encountered by network intrusion detection systems. We categorize existing network anomaly detection methods and systems based on the underlying computational techniques used. Within this framework, we briefly describe and compare a large number of network anomaly detection methods and systems. In addition, we also discuss tools that can be used by network defenders and datasets that researchers in network anomaly detection can use. We also highlight research directions in network anomaly detection.

Network Anomaly Detection: Methods, Systems and Tools

In this paper (expanded from an invited talk at AISEC 2010), we discuss an emerging field of study: adversarial machine learning---the study of effective machine learning techniques against an adversarial opponent. In this paper, we: give a taxonomy for classifying attacks against online machine learning algorithms; discuss application-specific factors that limit an adversary's capabilities; introduce two models for modeling an adversary's capabilities; explore the limits of an adversary's knowledge about the algorithm, feature space, training, and input data; explore vulnerabilities in machine learning algorithms; discuss countermeasures against attacks; introduce the evasion challenge; and discuss privacy-preserving learning techniques.

/pdf/adversarial-machine-learning-56wpx170q1.pdf

Adversarial machine learning

This paper describes GenProg, an automated method for repairing defects in off-the-shelf, legacy programs without formal specifications, program annotations, or special coding practices. GenProg uses an extended form of genetic programming to evolve a program variant that retains required functionality but is not susceptible to a given defect, using existing test suites to encode both the defect and required functionality. Structural differencing algorithms and delta debugging reduce the difference between this variant and the original program to a minimal repair. We describe the algorithm and report experimental results of its success on 16 programs totaling 1.25 M lines of C code and 120K lines of module code, spanning eight classes of defects, in 357 seconds, on average. We analyze the generated repairs qualitatively and quantitatively to demonstrate that the process efficiently produces evolved programs that repair the defect, are not fragile input memorizations, and do not lead to serious degradation in functionality.

GenProg: A Generic Method for Automatic Software Repair

We present a payload-based anomaly detector, we call PAYL, for intrusion detection. PAYL models the normal application payload of network traffic in a fully automatic, unsupervised and very effecient fashion. We first compute during a training phase a profile byte frequency distribution and their standard deviation of the application payload flowing to a single host and port. We then use Mahalanobis distance during the detection phase to calculate the similarity of new data against the pre-computed profile. The detector compares this measure against a threshold and generates an alert when the distance of the new input exceeds this threshold. We demonstrate the surprising effectiveness of the method on the 1999 DARPA IDS dataset and a live dataset we collected on the Columbia CS department network. In once case nearly 100% accuracy is achieved with 0.1% false positive rate for port 80 traffic.

/pdf/anomalous-payload-based-network-intrusion-detection-olwhsg8m8h.pdf

Anomalous Payload-Based Network Intrusion Detection

In this paper, we present Anagram, a content anomaly detector that models a mixture ofhigh-order n-grams (n > 1) designed to detect anomalous and “suspicious” network packet payloads. By using higher-order n-grams, Anagram can detect significant anomalous byte sequences and generate robust signatures of validated malicious packet content. The Anagram content models are implemented using highly efficient Bloom filters, reducing space requirements and enabling privacy-preserving cross-site correlation. The sensor models the distinct content flow of a network or host using a semi-supervised training regimen. Previously known exploits, extracted from the signatures of an IDS, are likewise modeled in a Bloom filter and are used during training as well as detection time. We demonstrate that Anagram can identify anomalous traffic with high accuracy and low false positive rates. Anagram's high-order n-gram analysis technique is also resilient against simple mimicry attacks that blend exploits with “normal” appearing byte padding, such as the blended polymorphic attack recently demonstrated in [1]. We discuss randomized n-gram models, which further raises the bar and makes it more difficult for attackers to build precise packet structures to evade Anagram even if they know the distribution of the local site content flow. Finally, Anagram's speed and high detection rate makes it valuable not only as a standalone sensor, but also as a network anomaly flow classifier in an instrumented fault-tolerant host-based environment; this enables significant cost amortization and the possibility of a “symbiotic” feedback loop that can improve accuracy and reduce false positive rates over time.

/pdf/anagram-a-content-anomaly-detector-resistant-to-mimicry-3ee2h1phs3.pdf

Anagram: a content anomaly detector resistant to mimicry attack

We propose a method to analyze files to categorize their type using efficient 1-gram analysis of their binary contents. Our aim is to be able to accurately identify the true type of an arbitrary file using statistical analysis of their binary contents without parsing. Consequently, we may determine the type of a file if its name does not announce its true type. The method represents each file type by a compact representation we call a fileprint, effectively a simple means of representing all members of the same file type by a set of statistical 1-gram models. The method is designed to be highly efficient so that files can be inspected with little or no buffering, and on a network appliance operating in high bandwidth environment or when streaming the file from or to disk.

/pdf/fileprints-identifying-file-types-by-n-gram-analysis-5fp1cdq8j5.pdf

Fileprints: identifying file types by n-gram analysis

New features of the PAYL anomalous payload detection sensor are demonstrated to accurately detect and generate signatures for zero-day worms. Experimental evidence demonstrates that site-specific packet content models are capable of detecting new worms with high accuracy in a collaborative security system. A new approach is proposed that correlates ingress/egress payload alerts to identify the worm's initial propagation. The method also enables automatic signature generation that can be deployed immediately to network firewalls and content filters to proactively protect other hosts. We also propose a collaborative privacy-preserving security strategy whereby different hosts can exchange PAYL signatures to increase accuracy and mitigate against false positives. The important principle demonstrated is that correlating multiple alerts identifies true positives from the set of anomaly alerts and reduces incorrect decisions producing accurate mitigation.

Anomalous payload-based worm detection and signature generation

A method, apparatus and medium are provided for detecting anomalous payloads transmitted through a network. The system receives payloads within the network and determines a length for data contained in each payload. A statistical distribution is generated for data contained in each payload received within the network, and compared to a selected model distribution representative of normal payloads transmitted through the network. The model payload can be selected such that it has a predetermined length range that encompasses the length for data contained in the received payload. Anomalous payloads are then identified based on differences detected between the statistical distribution of received payloads and the model distribution. The system can also provide for automatic training and incremental updating of models.

Ke Wang

Papers

Anomalous Payload-Based Network Intrusion Detection

Anagram: a content anomaly detector resistant to mimicry attack

Fileprints: identifying file types by n-gram analysis

Anomalous payload-based worm detection and signature generation

Apparatus method and medium for detecting payload anomaly using n-gram distribution of normal data