Deterministic and Statistical Strategies to Protect ANNs against Fault Injection Attacks

Artificial neural networks are currently used for many tasks, including safety critical ones such as automated driving. Hence, it is very important to protect them against faults and fault attacks. In this work, we propose two fault injection attack detection mechanisms: one based on using output labels for a reference input, and the other on...

Combining Fault Analysis Technologies for ISO26262 Functional Safety Verification

The development of Integrated Circuits for the Automotive sector imposes on complex challenges. ISO26262 Functional Safety requirements entail extensive Fault Injection campaigns and complex analysis for the evaluation of deployed Software Tools. This paper proposes a methodology to improve Fault Analysis Tools Confidence Level (TCL) by...

Determined-Safe Faults Identification: A step towards ISO26262 hardware compliant designs

The development of Integrated Circuits for the Automotive sector imposes on major challenges. ISO26262 compliance, as part of this process, entails complex analysis for the evaluation of potential random hardware faults. This paper proposes a systematic approach to identify faults that do not disrupt safety-critical functionalities and...

On the Analysis of Real-time Operating System Reliability in Embedded Systems

Nowadays, the reliability has become one of the main issues for safety-critical embedded systems, like automotive, aerospace and avionic. In an embedded system, the full system stack usually includes, between the hardware layer and the software/application layer, a middle layer composed by the Operating System (OS) and the middleware. Most of...

Use of Formal Methods for verification and optimization of Fault Lists in the scope of ISO26262

This work aims at an alternative method to verify the correctness of Fault Lists generated by fault simulators tools in context of safety verification. The lists generated by simulation tools are verified against lists from formal tools. The consistency evaluation between the lists supports the Tool Confidence Level (TCL) assessment, defined in...