arXiv subjects

Luigi V. Mancini

Publications and source records attributed to Luigi V. Mancini.

26 records · Page 2Linked to original sources

arXiv2019

The Naked Sun: Malicious Cooperation Between Benign-Looking Processes

Recent progress in machine learning has generated promising results in behavioral malware detection. Behavioral modeling identifies malicious processes via features derived by their runtime behavior. Behavioral features hold great promise as they are intrinsically related to the functioning of each malware, and are therefore considered difficult to evade. Indeed, while a significant amount of results exists on evasion of static malware features, evasion of dynamic features has seen limited work. This paper thoroughly examines the robustness of behavioral malware detectors to evasion, focusing particularly on anti-ransomware evasion. We choose ransomware as its behavior tends to differ significantly from that of benign processes, making it a low-hanging fruit for behavioral detection (and a difficult candidate for evasion). Our analysis identifies a set of novel attacks that distribute the overall malware workload across a small set of cooperating processes to avoid the generation of significant behavioral features. Our most effective attack decreases the accuracy of a state-of-the-art classifier from 98.6% to 0% using only 18 cooperating processes. Furthermore, we show our attacks to be effective against commercial ransomware detectors even in a black-box setting.

cs.CR↗

arXiv2018

Have You Stolen My Model? Evasion Attacks Against Deep Neural Network Watermarking Techniques

Deep neural networks have had enormous impact on various domains of computer science, considerably outperforming previous state of the art machine learning techniques. To achieve this performance, neural networks need large quantities of data and huge computational resources, which heavily increases their construction costs. The increased cost of building a good deep neural network model gives rise to a need for protecting this investment from potential copyright infringements. Legitimate owners of a machine learning model want to be able to reliably track and detect a malicious adversary that tries to steal the intellectual property related to the model. Recently, this problem was tackled by introducing in deep neural networks the concept of watermarking, which allows a legitimate owner to embed some secret information(watermark) in a given model. The watermark allows the legitimate owner to detect copyright infringements of his model. This paper focuses on verifying the robustness and reliability of state-of- the-art deep neural network watermarking schemes. We show that, a malicious adversary, even in scenarios where the watermark is difficult to remove, can still evade the verification by the legitimate owners, thus avoiding the detection of model theft.

cs.CR↗

arXiv2016

Know Your Enemy: Stealth Configuration-Information Gathering in SDN

Software Defined Networking (SDN) is a network architecture that aims at providing high flexibility through the separation of the network logic from the forwarding functions. The industry has already widely adopted SDN and researchers thoroughly analyzed its vulnerabilities, proposing solutions to improve its security. However, we believe important security aspects of SDN are still left uninvestigated. In this paper, we raise the concern of the possibility for an attacker to obtain knowledge about an SDN network. In particular, we introduce a novel attack, named Know Your Enemy (KYE), by means of which an attacker can gather vital information about the configuration of the network. This information ranges from the configuration of security tools, such as attack detection thresholds for network scanning, to general network policies like QoS and network virtualization. Additionally, we show that an attacker can perform a KYE attack in a stealthy fashion, i.e., without the risk of being detected. We underline that the vulnerability exploited by the KYE attack is proper of SDN and is not present in legacy networks. To address the KYE attack, we also propose an active defense countermeasure based on network flows obfuscation, which considerably increases the complexity for a successful attack. Our solution offers provable security guarantees that can be tailored to the needs of the specific network under consideration

cs.CR↗

arXiv2015

No Place to Hide that Bytes won't Reveal: Sniffing Location-Based Encrypted Traffic to Track a User's Position

News reports of the last few years indicated that several intelligence agencies are able to monitor large networks or entire portions of the Internet backbone. Such a powerful adversary has only recently been considered by the academic literature. In this paper, we propose a new adversary model for Location Based Services (LBSs). The model takes into account an unauthorized third party, different from the LBS provider itself, that wants to infer the location and monitor the movements of a LBS user. We show that such an adversary can extrapolate the position of a target user by just analyzing the size and the timing of the encrypted traffic exchanged between that user and the LBS provider. We performed a thorough analysis of a widely deployed location based app that comes pre-installed with many Android devices: GoogleNow. The results are encouraging and highlight the importance of devising more effective countermeasures against powerful adversaries to preserve the privacy of LBS users.

cs.CR↗

arXiv2014

Can't you hear me knocking: Identification of user actions on Android apps via traffic analysis

While smartphone usage become more and more pervasive, people start also asking to which extent such devices can be maliciously exploited as "tracking devices". The concern is not only related to an adversary taking physical or remote control of the device (e.g., via a malicious app), but also to what a passive adversary (without the above capabilities) can observe from the device communications. Work in this latter direction aimed, for example, at inferring the apps a user has installed on his device, or identifying the presence of a specific user within a network. In this paper, we move a step forward: we investigate to which extent it is feasible to identify the specific actions that a user is doing on his mobile device, by simply eavesdropping the device's network traffic. In particular, we aim at identifying actions like browsing someone's profile on a social network, posting a message on a friend's wall, or sending an email. We design a system that achieves this goal starting from encrypted TCP/IP packets: it works through identification of network flows and application of machine learning techniques. We did a complete implementation of this system and run a thorough set of experiments, which show that it can achieve accuracy and precision higher than 95%, for most of the considered actions.

cs.CR↗

arXiv2013

Hacking Smart Machines with Smarter Ones: How to Extract Meaningful Data from Machine Learning Classifiers

Machine Learning (ML) algorithms are used to train computers to perform a variety of complex tasks and improve with experience. Computers learn how to recognize patterns, make unintended decisions, or react to a dynamic environment. Certain trained machines may be more effective than others because they are based on more suitable ML algorithms or because they were trained through superior training sets. Although ML algorithms are known and publicly released, training sets may not be reasonably ascertainable and, indeed, may be guarded as trade secrets. While much research has been performed about the privacy of the elements of training sets, in this paper we focus our attention on ML classifiers and on the statistical information that can be unconsciously or maliciously revealed from them. We show that it is possible to infer unexpected but useful information from ML classifiers. In particular, we build a novel meta-classifier and train it to hack other classifiers, obtaining meaningful information about their training sets. This kind of information leakage can be exploited, for example, by a vendor to build more effective classifiers or to simply acquire trade secrets from a competitor's apparatus, potentially violating its intellectual property rights.

cs.CR↗

arXiv2013

Mapping the File Systems Genome: rationales, technique, results and applications

This paper provides evidence of a feature of Hard-Disk Drives (HDDs), that we call File System Genome. Such a feature is originated by the areas where (on the HDD) the file blocks are placed by the operating system during the installation procedure. It appears from our study that the File System Genome is a distinctive and unique feature of each indi- vidual HDD. In particular, our extensive set of experiments shows that the installation of the same operating system on two identical hardware configurations generates two different File System Genomes. Further, the application of sound information theory tools, such as min entropy, show that the differences between two File System Genome are considerably relevant. The results provided in this paper constitute the scientific basis for a number of applications in various fields of information technology, such as forensic identification and security. Finally, this work also paves the way for the application of the highlighted technique to other classes of mass-storage devices (e.g. SSDs, Flash memories).

cs.CR↗

arXiv2009

The Smallville Effect: Social Ties Make Mobile Networks More Secure Against the Node Capture Attack

Mobile Ad Hoc networks, due to the unattended nature of the network itself and the dispersed location of nodes, are subject to several unique security issues. One of the most vexed security threat is node capture. A few solutions have already been proposed to address this problem; however, those solutions are either centralized or focused on theoretical mobility models alone. In the former case the solution does not fit well the distributed nature of the network while, in the latter case, the quality of the solutions obtained for realistic mobility models severely differs from the results obtained for theoretical models. The rationale of this paper is inspired by the observation that re-encounters of mobile nodes do elicit a form of social ties. Leveraging these ties, it is possible to design efficient and distributed algorithms that, with a moderated degree of node cooperation, enforce the emergent property of node capture detection. In particular, in this paper we provide a proof of concept proposing a set of algorithms that leverage, to different extent, node mobility and node cooperation--that is, identifying social ties--to thwart node capture attack. In particular, we test these algorithms on a realistic mobility scenario. Extensive simulations show the quality of the proposed solutions and, more important, the viability of the proposed approach.

cs.CR↗