Bernhard Fischer

Daniel Dorfmeister, Flavio Ferrarotti, Bernhard Fischer et al.

More and more companies' Intellectual Property (IP) is being integrated into Neural Network (NN) models. This IP has considerable value for companies and, therefore, requires adequate protection. For example, an attacker might replicate a production machines' hardware and subsequently simply copy associated software and NN models onto the cloned hardware. To make copying NN models onto cloned hardware infeasible, we present an approach to bind NN models - and thus also the IP contained within them - to their underlying hardware. For this purpose, we link an NN model's weights, which are crucial for its operation, to unique and unclonable hardware properties by leveraging Physically Unclonable Functions (PUFs). By doing so, sufficient accuracy can only be achieved using the target hardware to restore the original weights, rendering proper execution of the NN model on cloned hardware impossible. We demonstrate that our approach accomplishes the desired degradation of accuracy on various NN models and outline possible future improvements.

Bernhard Fischer, Daniel Dorfmeister, Flavio Ferrarotti et al.

Embedded software used in industrial systems frequently relies on data that ensures the correct and efficient operation of these systems. Thus, companies invest considerable resources in fine-tuning this data, making it their valuable intellectual property (IP). We present a novel protection mechanism for this IP that combines hardware fingerprints with Boolean logic. Unlike usual copy-protection approaches, unauthorised copies of the software still run on cloned devices but suboptimally. According to our security evaluation, only a complex dynamic analysis of the protected software running on the genuine target device can reveal the secret data. This makes the protection offered by our method more difficult to bypass. Notably, our approach does not require additional hardware, relying only on relatively simple updates to the software. We evaluate our protection mechanism by binding the parameters of a PID controller to a microcontroller unit (MCU) by using a physically unclonable function (PUF) based on its SRAM.

Daniel Dorfmeister, Flavio Ferrarotti, Bernhard Fischer et al.

We introduce a novel copy-protection method for industrial control software. With our method, a program executes correctly only on its target hardware and behaves differently on other machines. The hardware-software binding is based on Physically Unclonable Functions (PUFs). We use symbolic execution to guarantee the preservation of safety properties if the software is executed on a different machine, or if there is a problem with the PUF response. Moreover, we show that the protection method is also secure against reverse engineering.

Bernhard Fischer

The embedded systems engineering industry faces increasing demands for more functionality, rapidly evolving components, and shrinking schedules. Abilities to quickly adapt to changes, develop products with safe design, minimize project costs, and deliver timely are needed. Model-based development (MBD) follows a separation of concerns by abstracting systems with an appropriate intensity. MBD promises higher comprehension by modeling on several abstraction-levels, formal verification, and automated code generation. This thesis demonstrates MBD with the Scicos/SynDEx framework on a distributed embedded system. Scicos is a modeling and simulation environment for hybrid systems. SynDEx is a rapid prototyping integrated development environment for distributed systems. Performed examples implement well-known control algorithms on a target system containing several networked microcontrollers, sensors, and actuators. The addressed research question tackles the feasibility of MBD for medium-sized embedded systems. In the case of single-processor applications experiments show that the comforts of tool-provided simulation, verification, and code-generation have to be weighed against an additional memory consumption in dynamic and static memory compared to a hand-written approach. Establishing a near-seamless modeling-framework with Scicos/SynDEx is expensive. An increased development effort indicates a high price for developing single applications, but might pay off for product families. A further drawback was that the distributed code generated with SynDEx could not be adapted to microcontrollers without a significant alteration of the scheduling tables. The Scicos/SynDEx framework forms a valuable tool set that, however, still needs many improvements. Therefore, its usage is only recommended for experimental purposes.