Detecting malware with autonomous side channel monitoring

Description

Master thesis: Detecting malware with autonomous side-channel monitoring

About this opportunity

Side-channel emission is defined as a non-intended information channel from electronic equipment, such as a mobile phone or a computer. A side-channel can consist of e.g., power consumption, electromagnetic (EM) emissions, timing, thermal signatures, sound and optical emissions. The side-channel emission can be used maliciously, for example, to extract a cryptographic key from the electronic equipment. However, side-channel emissions can also be used to monitor a device's health, for example, to ensure that the expected software is running on electronic equipment; this is called side-channel monitoring.

In an ever-increasingly connected world, it is important to be able to detect attacks on, and malfunctions in, electronic equipment. Monitors inside the equipment are one way of ensuring this, but they can also be targeted by attacks and be the cause of failures.

To complement built-in monitors, external monitors are needed. The external monitoring should preferably be performed without the need for hardware upgrades, hence requiring the monitor to be mobile.

The master thesis project will focus on evaluating the feasibility of autonomous side-channel monitoring, where electronic equipment will be monitored by a movable monitor without any human interaction.

You will be required to:

Review existing literature that explore side-channel monitoring, with emphasis on electromagnetic side-channel monitoring. Become acquainted with the Chipwhisperer platform and understand the basics of practical side-channel monitoring. Program a movable monitor, in this thesis work represented by a robotic arm, to continuously move the electromagnetic sensor in position to perform side-channel monitor on several pieces of electronic equipment. Feed the collected data to monitoring process, for example, a pre-trained machine learning model, to determine if the electronic equipment behaves as intended. Provide a proof-of-concept demo, thesis paper and presentation. If time permits, the project may also include any of: Improved detection of the state of the electronic equipment Choosing machine learning models depending on measurements Adapting the monitor to find the optimal measuring point.

The master thesis will be performed on-premises at Ericsson in Lund.

What you will do

We are looking for one or two students studying master program in computer science, electronics, information & communication, machine learning or equivalent.

The student(s) should be familiar with programming and working with hardware, for example, Arduino. Knowledge in security and machine learning is considered as a merit.

The project is expected to be performed in Lund with one or two master thesis student(s), starting in 2024 Q3 and lasting approximately 20 weeks.

You will bring

Applications should include a brief personal letter and CV. Relevant experience is highly valued so please describe accomplished projects and your role in the respect project if there is any one you consider relevant for this position. Candidates are encouraged to send in their application as soon as possible. Suitable applicants will be interviewed as applications are received.

Why join Ericsson?

At Ericsson, you´ll have an outstanding opportunity. The chance to use your skills and imagination to push the boundaries of what´s possible. To build solutions never seen before to some of the world’s toughest problems. You´ll be challenged, but you won’t be alone. You´ll be joining a team of diverse innovators, all driven to go beyond the status quo to craft what comes next.
 

---