Search

Security monitoring systems detect potentially malicious activities in IT infrastructures, by either looking for known signatures or for anomalous behaviors. Security operators investigate these events to determine whether they pose a threat to their organization. In many cases, a single event may be insufficient to determine whether certain activity is indeed malicious. Therefore, a security operator frequently needs to correlate multiple events to identify if they pose a real threat. Unfortunately, the vast number of events that need to be correlated often overload security operators, forcing them to ignore some events and, thereby, potentially miss attacks. This work studies how to automatically correlate security events and, thus, automate parts of the security operator workload. We design and evaluate DEEPCASE, a system that leverages the context around events to determine which events require further inspection. This approach reduces the number of events that need to be inspected. In addition, the context provides valuable insights into why certain events are classified as malicious. We show that our approach automatically filters 86.72% of the events and reduces the manual workload of security operators by 90.53%, while underestimating the risk of potential threats in less than 0.001% of cases.

Software is continually increasing in size and complexity, and therefore, vulnerability discovery would benefit from techniques that identify potentially vulnerable regions within large code bases, as this allows for easing vulnerability detection by reducing the search space. Previous work has explored the use of conventional code-quality and complexity metrics in highlighting suspicious sections of (source) code. Recently, researchers also proposed to reduce the vulnerability search space by studying code properties with neural networks. However, previous work generally failed in leveraging the rich metadata that is available for long-running, large code repositories. In this paper, we present an approach, named Bran, to reduce the vulnerability search space by combining conventional code metrics with fine-grained repository metadata. Bran locates code sections that are more likely to contain vulnerabilities in large code bases, potentially improving the efficiency of both manual and automatic code audits. In our experiments on four large code bases, Bran successfully highlights potentially vulnerable functions, outperforming several baselines, including state-of-art vulnerability prediction tools. We also assess Bran's effectiveness in assisting automated testing tools. We use Bran to guide syzkaller, a known kernel fuzzer, in fuzzing a recent version of the Linux kernel. The guided fuzzer identifies 26 bugs (10 are zero-day flaws), including arbitrary writes and reads.

Symbolic execution is a powerful technique for exploring programs and generating inputs that drive them into specific states. However, symbolic execution is also known to suffer from severe limitations, which prevent its application to real-world software. For example, symbolically executing programs requires modeling their interactions with the surrounding environment (e.g., libraries, operating systems). Unfortunately, models are usually created manually, introducing considerable approximations of the programs behaviors and significant imprecision in the analysis. In addition, as the complexity of the system under analysis grows, additional models are needed, making this process unsustainable. For these reasons, in this paper we propose a novel technique that allows interleaving symbolic execution with concrete execution, focusing the symbolic exploration only on interesting portions of code. We call this approach interleaved symbolic execution. The key idea of our approach is to re-use the concrete environment to run the input program, and then synchronize the results of the environment interactions with the symbolic execution engine. As a consequence, our approach does not make any assumption about such interactions, and it is agnostic with respect to the concrete environment. We implement a prototype for this technique, SYMBION, and we demonstrate its effectiveness by analyzing real-world malware, showing that it allows us to effectively skip complex portions of code that do not need to be analyzed symbolically.

A recent source of concern for the security of neural networks is the emergence of clean-label dataset poisoning attacks, wherein correctly labeled poison samples are injected into the training dataset. While these poison samples look legitimate to the human observer, they contain malicious characteristics that trigger a targeted misclassification during inference. We propose a scalable and transferable clean-label poisoning attack against transfer learning, which creates poison images with their center close to the target image in the feature space. Our attack, Bullseye Polytope, improves the attack success rate of the current state-of-the-art by 26.75% in end-to-end transfer learning, while increasing attack speed by a factor of 12. We further extend Bullseye Polytope to a more practical attack model by including multiple images of the same object (e.g., from different angles) when crafting the poison samples. We demonstrate that this extension improves attack transferability by over 16% to unseen images (of the same object) without using extra poison samples.

International audience; Machine learning techniques are widely used in addition to signatures and heuristics to increase the detection rate of anti-malware software, as they automate the creation of detection models, making it possible to handle an ever-increasing number of new malware samples. In order to foil the analysis of anti-malware systems and evade detection, malware uses packing and other forms of obfuscation. However, few realize that benign applications use packing and obfuscation as well, to protect intellectual property and prevent license abuse. In this paper, we study how machine learning based on static analysis features operates on packed samples. Malware researchers have often assumed that packing would prevent machine learning techniques from building effective classifiers. However, both industry and academia have published results that show that machine-learning-based classifiers can achieve good detection rates, leading many experts to think that classifiers are simply detecting the fact that a sample is packed, as packing is more prevalent in malicious samples. We show that, different from what is commonly assumed, packers do preserve some information when packing programs that is "useful" for malware classification. However, this information does not necessarily capture the sample's behavior. We demonstrate that the signals extracted from packed executables are not rich enough for machine-learning-based models to (1) generalize their knowledge to operate on unseen packers, and (2) be robust against adversarial examples. We also show that a naïve application of machine learning techniques results in a substantial number of false positives, which, in turn, might have resulted in incorrect labeling of ground-truth data used in past work.

Malware detection plays a vital role in computer security. Modern machine learning approaches have been centered around domain knowledge for extracting malicious features. However, many potential features can be used, and it is time consuming and difficult to manually identify the best features, especially given the diverse nature of malware. In this paper, we propose Neurlux, a neural network for malware detection. Neurlux does not rely on any feature engineering, rather it learns automatically from dynamic analysis reports that detail behavioral information. Our model borrows ideas from the field of document classification, using word sequences present in the reports to predict if a report is from a malicious binary or not. We investigate the learned features of our model and show which components of the reports it tends to give the highest importance. Then, we evaluate our approach on two different datasets and report formats, showing that Neurlux improves on the state of the art and can effectively learn from the dynamic analysis reports. Furthermore, we show that our approach is portable to other malware analysis environments and generalizes to different datasets.

Over the last two years, the Rowhammer bug transformed from a hard-to-exploit DRAM disturbance error into a fully weaponized attack vector. Researchers demonstrated exploits not only against desktop computers, but also used single bit flips to compromise the cloud and mobile devices, all without relying on any software vulnerability. Since hardware-level mitigations cannot be backported, a search for software defenses is pressing. Proposals made by both academia and industry, however, are either impractical to deploy, or insufficient in stopping all attacks: we present rampage, a set of DMA-based Rowhammer attacks against the latest Android OS, consisting of (1) a root exploit, and (2) a series of app-to-app exploit scenarios that bypass all defenses. To mitigate Rowhammer exploitation on ARM, we propose guardion, a lightweight defense that prevents DMA-based attacks—the main attack vector on mobile devices—by isolating DMA buffers with guard rows. We evaluate guardion on 22 benchmark apps and show that it has a negligible memory overhead (2.2 MB on average). We further show that we can improve system performance by re-enabling higher order allocations after Google disabled these as a reaction to previous attacks.

Security research has made extensive use of exhaustive Internet-wide scans over the recent years, as they can provide significant insights into the overall state of security of the Internet, and ZMap made scanning the entire IPv4 address space practical. However, the IPv4 address space is exhausted, and a switch to IPv6, the only accepted long-term solution, is inevitable. In turn, to better understand the security of devices connected to the Internet, including in particular Internet of Things devices, it is imperative to include IPv6 addresses in security evaluations and scans. Unfortunately, it is practically infeasible to iterate through the entire IPv6 address space, as it is 2^96 times larger than the IPv4 address space. Therefore, enumeration of active hosts prior to scanning is necessary. Without it, we will be unable to investigate the overall security of Internet-connected devices in the future. In this paper, we introduce a novel technique to enumerate an active part of the IPv6 address space by walking DNSSEC-signed IPv6 reverse zones. Subsequently, by scanning the enumerated addresses, we uncover significant security problems: the exposure of sensitive data, and incorrectly controlled access to hosts, such as access to routing infrastructure via administrative interfaces, all of which were accessible via IPv6. Furthermore, from our analysis of the differences between accessing dual-stack hosts via IPv6 and IPv4, we hypothesize that the root cause is that machines automatically and by default take on globally routable IPv6 addresses. This is a practice that the affected system administrators appear unaware of, as the respective services are almost always properly protected from unauthorized access via IPv4. Our findings indicate (i) that enumerating active IPv6 hosts is practical without a preferential network position contrary to common belief, (ii) that the security of active IPv6 hosts is currently still lagging behind the security state of IPv4 hosts, and (iii) that unintended IPv6 connectivity is a major security issue for unaware system administrators.

Mobile apps are notorious for collecting a wealth of private information from users. Despite significant effort from the research community in developing privacy leak detection tools based on data flow tracking inside the app or through network traffic analysis, it is still unclear whether apps and ad libraries can hide the fact that they are leaking private information. In fact, all existing analysis tools have limitations: data flow tracking suffers from imprecisions that cause false positives, as well as false negatives when the data flow from a source of private information to a network sink is interrupted; on the other hand, network traffic analysis cannot handle encryption or custom encoding. We propose a new approach to privacy leak detection that is not affected by such limitations, and it is also resilient to obfuscation techniques, such as encoding, formatting, encryption, or any other kind of transformation performed on private information before it is leaked. Our work is based on blackbox differential analysis, and it works in two steps: first, it establishes a baseline of the network behavior of an app; then, it modifies sources of private information, such as the device ID and location, and detects leaks by observing deviations in the resulting network traffic. The basic concept of black-box differential analysis is not novel, but, unfortunately, it is not practical enough to precisely analyze modern mobile apps. In fact, their network traffic contains many sources of non-determinism, such as random identifiers, timestamps, and server-assigned session identifiers, which, when not handled properly, cause too much noise to correlate output changes with input changes. The main contribution of this work is to make black-box differential analysis practical when applied to modern Android apps. In particular, we show that the network-based non-determinism can often be explained and eliminated, and it is thus possible to reliably use variations in the network traffic as a strong signal to detect privacy leaks. We implemented this approach in a tool, called Agrigento, and we evaluated it on more than one thousand Android apps. Our evaluation shows that our approach works well in practice and outperforms current state-of-the-art techniques. We conclude our study by discussing several case studies that show how popular apps and ad libraries currently exfiltrate data by using complex combinations of encoding and encryption mechanisms that other approaches fail to detect. Our results show that these apps and libraries seem to deliberately hide their data leaks from current approaches and clearly demonstrate the need for an obfuscation-resilient approach such as ours.

Recent work shows that the Rowhammer hardware bug can be used to craft powerful attacks and completely subvert a system. However, existing e orts either describe probabilistic (and thus unreliable) attacks or rely on special (and often unavailable) memory management features to place victim objects in vulnerable physical memory locations. Moreover, prior work only targets x86 and researchers have openly wondered whether Rowhammer attacks on other architectures, such as ARM, are even possible. We show that deterministic Rowhammer attacks are feasible on commodity mobile platforms and that they cannot be mitigated by current defenses. Rather than assuming special memory management features, our attack, Drammer, solely relies on the predictable memory reuse patterns of standard physical memory allocators. We implement Drammer on Android/ARM, demonstrating the practicability of our attack, but also discuss a generalization of our approach to other Linux-based platforms. Furthermore, we show that traditional x86-based Rowhammer exploitation techniques no longer work on mobile platforms and address the resulting challenges towards practical mobile Rowhammer attacks. To support our claims, we present the rst Rowhammer-based Android root exploit relying on no software vulnerability, and requiring no user permissions. In addition, we present an analysis of several popular smartphones and nd that many of them are susceptible to our Drammer attack. We conclude by discussing potential mitigation strategies and urging our community to address the concrete threat of faulty DRAM chips in widespread commodity platforms.

Finding and exploiting vulnerabilities in binary code is a challenging task. The lack of high-level, semantically rich information about data structures and control constructs makes the analysis of program properties harder to scale. However, the importance of binary analysis is on the rise. In many situations binary analysis is the only possible way to prove (or disprove) properties about the code that is actually executed. In this paper, we present a binary analysis framework that implements a number of analysis techniques that have been proposed in the past. We present a systematized implementation of these techniques, which allows other researchers to compose them and develop new approaches. In addition, the implementation of these techniques in a unifying framework allows for the direct comparison of these apporaches and the identification of their advantages and disadvantages. The evaluation included in this paper is performed using a recent dataset created by DARPA for evaluating the effectiveness of binary vulnerability analysis techniques. Our framework has been open-sourced and is available to the security community.

Online advertising drives the economy of the World Wide Web. Modern websites of any size and popularity include advertisements to monetize visits from their users. To this end, they assign an area of their web page to an advertising company (so called ad exchange) that will use it to display promotional content. By doing this, the website owner implicitly trusts that the advertising company will offer legitimate content and it will not put the site's visitors at risk of falling victims of malware campaigns and other scams. In this paper, we perform the first large-scale study of the safety of the advertisements that are encountered by the users on the Web. In particular, we analyze to what extent users are exposed to malicious content through advertisements, and investigate what are the sources of this malicious content. Additionally, we show that some ad exchanges are more prone to serving malicious advertisements than others, probably due to their deficient filtering mechanisms. The observations that we make in this paper shed light on a little studied, yet important, aspect of advertisement networks, and can help both advertisement networks and website owners in securing their web pages and in keeping their visitors safe.

Online advertisements (ads) provide a powerful mechanism for advertisers to effectively target Web users. Ads can be customized based on a user's browsing behavior, geographic location, and personal interests. There is currently a multi-billion dollar market for online advertising, which generates the primary revenue for some of the most popular websites on the Internet. In order to meet the immense market demand, and to manage the complex relationships between advertisers and publishers (i.e., the websites hosting the ads), marketplaces known as "ad exchanges" are employed. These exchanges allow publishers (sellers of ad space) and advertisers(buyers of this ad space) to dynamically broker traffic through ad networks to efficiently maximize profits for all parties. Unfortunately, the complexities of these systems invite a considerable amount of abuse from cybercriminals, who profit at the expense of the advertisers.In this paper, we present a detailed view of how one of the largest ad exchanges operates and the associated security issues from the vantage point of a member ad network. More specifically, we analyzed a dataset containing transactions for ingress and egress ad traffic from this ad network. In addition, we examined information collected from a command-and-control server used to operate a botnet that is leveraged to perpetrate ad fraud against the same ad exchange.

Computer security competitions and challenges are a way to foster innovation and educate students in a highly-motivating setting. In recent years, a number of different security competitions and challenges were carried out, each with different characteristics, configurations, and goals. From 2003 to 2007, we carried out a number of live security exercises involving dozens of universities from around the world. These exercises were designed as "traditional" Capture The Flag competitions, where teams both attacked and defended a virtualized host, which provided several vulnerable services. In 2008 and 2009, we introduced two completely new types of competition: a security "treasure hunt" and a botnet-inspired competition. These two competitions, to date, represent the largest live security exercises ever attempted and involved hundreds of students across the globe. In this paper, we describe these two new competition designs, the challenges overcome, and the lessons learned, with the goal of providing useful guidelines to other educators who want to pursue the organization of similar events

Botnets, networks of malware-infected machines that are controlled by an adversary, are the root cause of a large number of security problems on the Internet. A particularly sophisticated and insidious type of bot is Torpig, a malware program that is designed to harvest sensitive information (such as bank account and credit card data) from its victims. In this paper, we report on our efforts to take control of the Torpig botnet and study its operations for a period of ten days. During this time, we observed more than 180 thousand infections and recorded almost 70 GB of data that the bots collected. While botnets have been "hijacked" and studied previously, the Torpig botnet exhibits certain properties that make the analysis of the data particularly interesting. First, it is possible (with reasonable accuracy) to identify unique bot infections and relate that number to the more than 1.2 million IP addresses that contacted our command and control server. Second, the Torpig botnet is large, targets a variety of applications, and gathers a rich and diverse set of data from the infected victims. This data provides a new understanding of the type and amount of personal information that is stolen by botnets.

Nowadays users often possess a variety of electronic devices for communication and entertainment. In particular, smartphones are playing an increasingly central role in users’ lives: Users carry them everywhere they go and often use them to control other devices. This trend provides incentives for the industry to tackle new challenges, such as cross-device authentication, and to develop new monetization schemes. A new technology based on ultrasounds has recently emerged to meet these demands. Ultrasound technology has a number of desirable features: it is easy to deploy, flexible, and inaudible by humans. This technology is already utilized in a number of different real-world applications, such as device pairing, proximity detection, and cross-device tracking. This paper examines the different facets of ultrasound-based technology. Initially, we discuss how it is already used in the real world, and subsequently examine this emerging technology from the privacy and security perspectives. In particular, we first observe that the lack of OS features results in violations of the principle of least privilege: an app that wants to use this technology currently needs to require full access to the device microphone. We then analyse real-world Android apps and find that tracking techniques based on ultrasounds suffer from a number of vulnerabilities and are susceptible to various attacks. For example, we show that ultrasound cross-device tracking deployments can be abused to perform stealthy deanonymization attacks (e.g., to unmask users who browse the Internet through anonymity networks such as Tor), to inject fake or spoofed audio beacons, and to leak a user’s private information. Based on our findings, we introduce several defense mechanisms. We first propose and implement immediately deployable defenses that empower practitioners, researchers, and everyday users to protect their privacy. In particular, we introduce a browser extension and an Android permission that enable the user to selectively suppress frequencies falling within the ultrasonic spectrum. We then argue for the standardization of ultrasound beacons, and we envision a flexible OS-level API that addresses both the effortless deployment of ultrasound-enabled applications, and the prevention of existing privacy and security problems.