arXiv subjects

Yuval Elovici

Publications and source records attributed to Yuval Elovici.

At least 145 records · Page 8Linked to original sources

arXiv2018

PIDS - A Behavioral Framework for Analysis and Detection of Network Printer Attacks

Nowadays, every organization might be attacked through its network printers. The malicious exploitation of printing protocols is a dangerous and underestimated threat against every printer today, as highlighted by recent published researches. This article presents PIDS (Printers' IDS), an intrusion detection system for detecting attacks on printing protocols. PIDS continuously captures various features and events obtained from traffic produced by printing protocols in order to detect attacks. As part of this research we conducted thousands of automatic and manual printing protocol attacks on various printers and recorded thousands of the printers' benign network sessions. Then we applied various supervised machine learning (ML) algorithms to classify the collected data as normal (benign) or abnormal (malicious). We evaluated several detection algorithms, feature selection methods, and the features needed in order to obtain the best detection results for protocol traffic of printers. Our empirical results suggest that the proposed framework is effective in detecting printing protocol attacks, providing an accuracy of 99.9 with negligible fall-positive rate.

cs.CR↗

arXiv2018

Generic Black-Box End-to-End Attack Against State of the Art API Call Based Malware Classifiers

In this paper, we present a black-box attack against API call based machine learning malware classifiers, focusing on generating adversarial sequences combining API calls and static features (e.g., printable strings) that will be misclassified by the classifier without affecting the malware functionality. We show that this attack is effective against many classifiers due to the transferability principle between RNN variants, feed forward DNNs, and traditional machine learning classifiers such as SVM. We also implement GADGET, a software framework to convert any malware binary to a binary undetected by malware classifiers, using the proposed attack, without access to the malware source code.

cs.CR↗

arXiv2018

Kitsune: An Ensemble of Autoencoders for Online Network Intrusion Detection

Neural networks have become an increasingly popular solution for network intrusion detection systems (NIDS). Their capability of learning complex patterns and behaviors make them a suitable solution for differentiating between normal traffic and network attacks. However, a drawback of neural networks is the amount of resources needed to train them. Many network gateways and routers devices, which could potentially host an NIDS, simply do not have the memory or processing power to train and sometimes even execute such models. More importantly, the existing neural network solutions are trained in a supervised manner. Meaning that an expert must label the network traffic and update the model manually from time to time. In this paper, we present Kitsune: a plug and play NIDS which can learn to detect attacks on the local network, without supervision, and in an efficient online manner. Kitsune's core algorithm (KitNET) uses an ensemble of neural networks called autoencoders to collectively differentiate between normal and abnormal traffic patterns. KitNET is supported by a feature extraction framework which efficiently tracks the patterns of every network channel. Our evaluations show that Kitsune can detect various attacks with a performance comparable to offline anomaly detectors, even on a Raspberry PI. This demonstrates that Kitsune can be a practical and economic NIDS.

cs.CR↗

arXiv2018

N-BaIoT: Network-based Detection of IoT Botnet Attacks Using Deep Autoencoders

The proliferation of IoT devices which can be more easily compromised than desktop computers has led to an increase in the occurrence of IoT based botnet attacks. In order to mitigate this new threat there is a need to develop new methods for detecting attacks launched from compromised IoT devices and differentiate between hour and millisecond long IoTbased attacks. In this paper we propose and empirically evaluate a novel network based anomaly detection method which extracts behavior snapshots of the network and uses deep autoencoders to detect anomalous network traffic emanating from compromised IoT devices. To evaluate our method, we infected nine commercial IoT devices in our lab with two of the most widely known IoT based botnets, Mirai and BASHLITE. Our evaluation results demonstrated our proposed method's ability to accurately and instantly detect the attacks as they were being launched from the compromised IoT devices which were part of a botnet.

cs.CR↗

arXiv2018

PowerHammer: Exfiltrating Data from Air-Gapped Computers through Power Lines

In this paper we provide an implementation, evaluation, and analysis of PowerHammer, a malware (bridgeware [1]) that uses power lines to exfiltrate data from air-gapped computers. In this case, a malicious code running on a compromised computer can control the power consumption of the system by intentionally regulating the CPU utilization. Data is modulated, encoded, and transmitted on top of the current flow fluctuations, and then it is conducted and propagated through the power lines. This phenomena is known as a 'conducted emission'. We present two versions of the attack. Line level powerhammering: In this attack, the attacker taps the in-home power lines1 that are directly attached to the electrical outlet. Phase level power-hammering: In this attack, the attacker taps the power lines at the phase level, in the main electrical service panel. In both versions of the attack, the attacker measures the emission conducted and then decodes the exfiltrated data. We describe the adversarial attack model and present modulations and encoding schemes along with a transmission protocol. We evaluate the covert channel in different scenarios and discuss signal-to-noise (SNR), signal processing, and forms of interference. We also present a set of defensive countermeasures. Our results show that binary data can be covertly exfiltrated from air-gapped computers through the power lines at bit rates of 1000 bit/sec for the line level power-hammering attack and 10 bit/sec for the phase level power-hammering attack.

cs.CR↗

arXiv2018

CIoTA: Collaborative IoT Anomaly Detection via Blockchain

Due to their rapid growth and deployment, Internet of things (IoT) devices have become a central aspect of our daily lives. However, they tend to have many vulnerabilities which can be exploited by an attacker. Unsupervised techniques, such as anomaly detection, can help us secure the IoT devices. However, an anomaly detection model must be trained for a long time in order to capture all benign behaviors. This approach is vulnerable to adversarial attacks since all observations are assumed to be benign while training the anomaly detection model. In this paper, we propose CIoTA, a lightweight framework that utilizes the blockchain concept to perform distributed and collaborative anomaly detection for devices with limited resources. CIoTA uses blockchain to incrementally update a trusted anomaly detection model via self-attestation and consensus among IoT devices. We evaluate CIoTA on our own distributed IoT simulation platform, which consists of 48 Raspberry Pis, to demonstrate CIoTA's ability to enhance the security of each device and the security of the network as a whole.

cs.CY↗

arXiv2018

MOSQUITO: Covert Ultrasonic Transmissions between Two Air-Gapped Computers using Speaker-to-Speaker Communication

In this paper we show how two (or more) airgapped computers in the same room, equipped with passive speakers, headphones, or earphones can covertly exchange data via ultrasonic waves. Microphones are not required. Our method is based on the capability of a malware to exploit a specific audio chip feature in order to reverse the connected speakers from output devices into input devices - unobtrusively rendering them microphones. We discuss the attack model and provide technical background and implementation details. We show that although the reversed speakers/headphones/earphones were not originally designed to perform as microphones, they still respond well to the near-ultrasonic range (18kHz to 24kHz). We evaluate the communication channel with different equipment, and at various distances and transmission speeds, and also discuss some practical considerations. Our results show that the speaker-to-speaker communication can be used to covertly transmit data between two air-gapped computers positioned a maximum of nine meters away from one another. Moreover, we show that two (microphone-less) headphones can exchange data from a distance of three meters apart. This enables 'headphones-to-headphones' covert communication, which is discussed for the first time in this paper.

cs.CR↗

arXiv2018

Vesper: Using Echo-Analysis to Detect Man-in-the-Middle Attacks in LANs

The Man-in-the-Middle (MitM) attack is a cyber-attack in which an attacker intercepts traffic, thus harming the confidentiality, integrity, and availability of the network. It remains a popular attack vector due to its simplicity. However, existing solutions are either not portable, suffer from a high false positive rate, or are simply not generic. In this paper, we propose Vesper: a novel plug-and-play MitM detector for local area networks. Vesper uses a technique inspired from impulse response analysis used in the domain of acoustic signal processing. Analogous to how echoes in a cave capture the shape and construction of the environment, so to can a short and intense pulse of ICMP echo requests model the link between two network hosts. Vesper uses neural networks called autoencoders to model the normal patterns of the echoed pulses, and detect when the environment changes. Using this technique, Vesper is able to detect MitM attacks with high accuracy while incurring minimal network overhead. We evaluate Vesper on LANs consisting of video surveillance cameras, servers, and PC workstations. We also investigate several possible adversarial attacks against Vesper, and demonstrate how Vesper mitigates these attacks.

cs.CR↗

arXiv2018

Know Your Enemy: Characteristics of Cyber-Attacks on Medical Imaging Devices

Purpose: Used extensively in the diagnosis, treatment, and prevention of disease, Medical Imaging Devices (MIDs), such as Magnetic Resonance Imaging (MRI) or Computed Tomography (CT) machines, play an important role in medicine today. MIDs are increasingly connected to hospital networks, making them vulnerable to sophisticated cyber-attacks targeting the devices' infrastructure and components, which can disrupt digital patient records, and potentially jeopardize patients' health. Attacks on MIDs are likely to increase, as attackers' skills improve and the number of unpatched devices with known vulnerabilities that can be easily exploited grows. Attackers may also block access to MIDs or disable them, as part of ransomware attacks, which have been shown to be successful against hospitals. Method and Materials: We conducted a comprehensive risk analysis survey at the Malware-Lab, based on the Confidentiality, Integrity, and Availability (CIA) model, in collaboration with our country's largest health maintenance organization, to define the characteristics of cyber-attacks on MIDs. The survey includes a range of vulnerabilities and potential attacks aimed at MIDs, medical and imaging information systems, and medical protocols and standards such as DICOM and HL7. Results: Based on our survey, we found that CT devices face the greatest risk of cyber-attack, due to their pivotal role in acute care imaging. Thus, we identified several possible attack vectors that target the infrastructure and functionality of CT devices, which can cause: 1. Disruption of the parameters' values used in the scanning protocols within the CT devices (e.g., tampering with the radiation exposure levels); 2. Mechanical disruption of the CT device (e.g., changing the pitch); 3. Disruption of the tomography scan signals constructing the digital images; and 4. Denial-of-Service attacks against the CT device.

cs.CR↗

arXiv2018

ODINI : Escaping Sensitive Data from Faraday-Caged, Air-Gapped Computers via Magnetic Fields

Air-gapped computers are computers which are kept isolated from the Internet, because they store and process sensitive information. When highly sensitive data is involved, an air-gapped computer might also be kept secluded in a Faraday cage. The Faraday cage prevents the leakage of electromagnetic signals emanating from various computer parts, which may be picked up by an eavesdropping adversary remotely. The air-gap separation, coupled with the Faraday shield, provides a high level of isolation, preventing the potential leakage of sensitive data from the system. In this paper, we show how attackers can bypass Faraday cages and air-gaps in order to leak data from highly secure computers. Our method is based on an exploitation of the magnetic field generated by the computer CPU. Unlike electromagnetic radiation (EMR), low frequency magnetic radiation propagates though the air, penetrating metal shielding such as Faraday cages (e.g., compass still works inside Faraday cages). We introduce a malware code-named ODINI that can control the low frequency magnetic fields emitted from the infected computer by regulating the load of the CPU cores. Arbitrary data can be modulated and transmitted on top of the magnetic emission and received by a magnetic receiver (bug) placed nearby. We provide technical background and examine the characteristics of the magnetic fields. We implement a malware prototype and discuss the design considerations along with the implementation details. We also show that the malicious code does not require special privileges (e.g., root) and can successfully operate from within isolated virtual machines (VMs) as well.

cs.CR↗

arXiv2018

MAGNETO: Covert Channel between Air-Gapped Systems and Nearby Smartphones via CPU-Generated Magnetic Fields

In this paper, we show that attackers can leak data from isolated, air-gapped computers to nearby smartphones via covert magnetic signals. The proposed covert channel works even if a smartphone is kept inside a Faraday shielding case, which aims to block any type of inbound and outbound wireless communication (Wi-Fi, cellular, Bluetooth, etc.). The channel also works if the smartphone is set in airplane mode in order to block any communication with the device. We implement a malware that controls the magnetic fields emanating from the computer by regulating workloads on the CPU cores. Sensitive data such as encryption keys, passwords, or keylogging data is encoded and transmitted over the magnetic signals. A smartphone located near the computer receives the covert signals with its magnetic sensor. We present technical background, and discuss signal generation, data encoding, and signal reception. We show that the proposed covert channel works from a user-level process, without requiring special privileges, and can successfully operate from within an isolated virtual machine (VM).

cs.CR↗

arXiv2018

PALE: Partially Asynchronous Agile Leader Election

Many tasks executed in dynamic distributed systems, such as sensor networks or enterprise environments with bring-your-own-device policy, require central coordination by a leader node. In the past it has been proven that distributed leader election in dynamic environments with constant changes and asynchronous communication is not possible. Thus, state-of-the-art leader election algorithms are not applicable in asynchronous environments with constant network changes. Some algorithms converge only after the network stabilizes (an unrealistic requirement in many dynamic environments). Other algorithms reach consensus in the presence of network changes but require a global clock or some level of communication synchronization. Determining the weakest assumptions, under which leader election is possible, remains an unresolved problem. In this study we present a leader election algorithm that operates in the presence of changes and under weak (realistic) assumptions regarding message delays and regarding the clock drifts of the distributed nodes. The proposed algorithm is self-sufficient, easy to implement and can be extended to support multiple regions, self-stabilization, and wireless ad-hoc networks. We prove the algorithm's correctness and provide a complexity analysis of the time, space, and number of messages required to elect a leader.

cs.DC↗

arXiv2018

Game of Drones - Detecting Streamed POI from Encrypted FPV Channel

Drones have created a new threat to people's privacy. We are now in an era in which anyone with a drone equipped with a video camera can use it to invade a subject's privacy by streaming the subject in his/her private space over an encrypted first person view (FPV) channel. Although many methods have been suggested to detect nearby drones, they all suffer from the same shortcoming: they cannot identify exactly what is being captured, and therefore they fail to distinguish between the legitimate use of a drone (for example, to use a drone to film a selfie from the air) and illegitimate use that invades someone's privacy (when the same operator uses the drone to stream the view into the window of his neighbor's apartment), a distinction that in some cases depends on the orientation of the drone's video camera rather than on the drone's location. In this paper we shatter the commonly held belief that the use of encryption to secure an FPV channel prevents an interceptor from extracting the POI that is being streamed. We show methods that leverage physical stimuli to detect whether the drone's camera is directed towards a target in real time. We investigate the influence of changing pixels on the FPV channel (in a lab setup). Based on our observations we demonstrate how an interceptor can perform a side-channel attack to detect whether a target is being streamed by analyzing the encrypted FPV channel that is transmitted from a real drone (DJI Mavic) in two use cases: when the target is a private house and when the target is a subject.

cs.CR↗

arXiv2017

aIR-Jumper: Covert Air-Gap Exfiltration/Infiltration via Security Cameras & Infrared (IR)

Infrared (IR) light is invisible to humans, but cameras are optically sensitive to this type of light. In this paper, we show how attackers can use surveillance cameras and infrared light to establish bi-directional covert communication between the internal networks of organizations and remote attackers. We present two scenarios: exfiltration (leaking data out of the network) and infiltration (sending data into the network). Exfiltration. Surveillance and security cameras are equipped with IR LEDs, which are used for night vision. In the exfiltration scenario, malware within the organization access the surveillance cameras across the local network and controls the IR illumination. Sensitive data such as PIN codes, passwords, and encryption keys are then modulated, encoded, and transmitted over the IR signals. Infiltration. In an infiltration scenario, an attacker standing in a public area (e.g., in the street) uses IR LEDs to transmit hidden signals to the surveillance camera(s). Binary data such as command and control (C&C) and beacon messages are encoded on top of the IR signals. The exfiltration and infiltration can be combined to establish bidirectional, 'air-gap' communication between the compromised network and the attacker. We discuss related work and provide scientific background about this optical channel. We implement a malware prototype and present data modulation schemas and a basic transmission protocol. Our evaluation of the covert channel shows that data can be covertly exfiltrated from an organization at a rate of 20 bit/sec per surveillance camera to a distance of tens of meters away. Data can be covertly infiltrated into an organization at a rate of over 100 bit/sec per surveillance camera from a distance of hundreds of meters to kilometers away.

cs.CR↗

arXiv2017

Detection of Unauthorized IoT Devices Using Machine Learning Techniques

Security experts have demonstrated numerous risks imposed by Internet of Things (IoT) devices on organizations. Due to the widespread adoption of such devices, their diversity, standardization obstacles, and inherent mobility, organizations require an intelligent mechanism capable of automatically detecting suspicious IoT devices connected to their networks. In particular, devices not included in a white list of trustworthy IoT device types (allowed to be used within the organizational premises) should be detected. In this research, Random Forest, a supervised machine learning algorithm, was applied to features extracted from network traffic data with the aim of accurately identifying IoT device types from the white list. To train and evaluate multi-class classifiers, we collected and manually labeled network traffic data from 17 distinct IoT devices, representing nine types of IoT devices. Based on the classification of 20 consecutive sessions and the use of majority rule, IoT device types that are not on the white list were correctly detected as unknown in 96% of test cases (on average), and white listed device types were correctly classified by their actual types in 99% of cases. Some IoT device types were identified quicker than others (e.g., sockets and thermostats were successfully detected within five TCP sessions of connecting to the network). Perfect detection of unauthorized IoT device types was achieved upon analyzing 110 consecutive sessions; perfect classification of white listed types required 346 consecutive sessions, 110 of which resulted in 99.49% accuracy. Further experiments demonstrated the successful applicability of classifiers trained in one location and tested on another. In addition, a discussion is provided regarding the resilience of our machine learning-based IoT white listing method to adversarial attacks.

cs.CR↗

arXiv2017

Temporal Pattern Discovery for Accurate Sepsis Diagnosis in ICU Patients

Sepsis is a condition caused by the body's overwhelming and life-threatening response to infection, which can lead to tissue damage, organ failure, and finally death. Common signs and symptoms include fever, increased heart rate, increased breathing rate, and confusion. Sepsis is difficult to predict, diagnose, and treat. Patients who develop sepsis have an increased risk of complications and death and face higher health care costs and longer hospitalization. Today, sepsis is one of the leading causes of mortality among populations in intensive care units (ICUs). In this paper, we look at the problem of early detection of sepsis by using temporal data mining. We focus on the use of knowledge-based temporal abstraction to create meaningful interval-based abstractions, and on time-interval mining to discover frequent interval-based patterns. We used 2,560 cases derived from the MIMIC-III database. We found that the distribution of the temporal patterns whose frequency is above 10% discovered in the records of septic patients during the last 6 and 12 hours before onset of sepsis is significantly different from that distribution within a similar period, during an equivalent time window during hospitalization, in the records of non-septic patients. This discovery is encouraging for the purpose of performing an early diagnosis of sepsis using the discovered patterns as constructed features.

cs.LG↗

arXiv2017

Power Consumption-based Detection of Sabotage Attacks in Additive Manufacturing

Additive Manufacturing (AM), a.k.a. 3D Printing, is increasingly used to manufacture functional parts of safety-critical systems. AM's dependence on computerization raises the concern that the AM process can be tampered with, and a part's mechanical properties sabotaged. This can lead to the destruction of a system employing the sabotaged part, causing loss of life, financial damage, and reputation loss. To address this threat, we propose a novel approach for detecting sabotage attacks. Our approach is based on continuous monitoring of the current delivered to all actuators during the manufacturing process and detection of deviations from a provable benign process. The proposed approach has numerous advantages: (i) it is non-invasive in a time-critical process, (ii) it can be retrofitted in legacy systems, and (iii) it is airgapped from the computerized components of the AM process, preventing simultaneous compromise. Evaluation on a desktop 3D Printer detects all attacks involving a modification of X or Y motor movement, with false positives at 0%.

cs.CR↗

arXiv2017

Protecting Military Avionics Platforms from Attacks on MIL-STD-1553 Communication Bus

MIL-STD-1553 is a military standard that defines the physical and logical layers, and a command/response time division multiplexing of a communication bus used in military and aerospace avionic platforms for more than 40 years. As a legacy platform, MIL-STD-1553 was designed for high level of fault tolerance while less attention was taken with regard to security. Recent studies already addressed the impact of successful cyber attacks on aerospace vehicles that are implementing MIL-STD-1553. In this study we present a security analysis of MIL-STD-1553. In addition, we present a method for anomaly detection in MIL-STD-1553 communication bus and its performance in the presence of several attack scenarios implemented in a testbed, as well as results on real system data. Moreover, we propose a general approach towards an intrusion detection system (IDS) for a MIL-STD-1553 communication bus.

cs.CR↗