Slice Your Bug: Debugging Error Detection Mechanisms Using Error Injection Slicing

Schiffel, Ute; Schmitt, André; Süßkraut, Martin; Fetzer, Christof

doi:10.1109/edcc.2010.12

Cited by 10 publications

(2 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To test the resilience of DNN models, we developed a program capable to inject failures into a DNN model. There are many applications or APIs to perform fault injection (FI) [1][2] [3] in programs, but these are not specifically designed to perform the FI in DNN models. Nevertheless, there are other studies that have developed and implemented FI mechanisms to understand the relationship between fault rate and model accuracy, and to test the resilience of DNN models [4] [5][6] [7].…”

Section: Failure Injectionmentioning

confidence: 99%

Evaluando la Resiliencia de Modelos de Deep Learning

Rojas¹,

Nicolae²,

Meneses³

2020

View full text Add to dashboard Cite

Los modelos de Aprendizaje Profundo se han convertido en una valiosa herramienta para resolver problemas complejos en muchas áreas críticas. Es importante proveer confiabilidad en las salidas de la ejecución de estos modelos, aún si se producen fallos durante la ejecución. En este artículo presentamos la evaluación de la confiabilidad de tres modelos de aprendizaje profundo. Usamos un conjunto de datos de ImageNet y desarrollamos un inyector de fallos para realizar las pruebas. Los resultados muestran que entre los modelos hay una diferencia en la sensibilidad a los fallos. Además, hay modelos que a pesar del incremento en la tasa de fallos pueden mantener bajos los valores de error.

show abstract

Section: Failure Injectionmentioning

confidence: 99%

Evaluando la Resiliencia de Modelos de Deep Learning

Rojas¹,

Nicolae²,

Meneses³

2020

View full text Add to dashboard Cite

show abstract

“…For evaluating the error detection capabilities of our encoded programs we used our error injector EIS [12]. It injects the software-level symptoms of possible hardware failures.…”

Section: Discussionmentioning

confidence: 99%

ANB- and ANBDmem-Encoding: Detecting Hardware Errors in Software

Schiffel

Schmitt

Süßkraut

et al. 2010

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. It is expected that commodity hardware is becoming less reliable because of the continuously decreasing feature sizes of integrated circuits. Nevertheless, more and more commodity hardware with insufficient error detection is used in critical applications. One possible solution is to detect hardware errors in software using arithmetic AN-codes. These codes detect hardware errors independent of the actual failure modes of the underlying hardware. However, measurements have shown that AN-codes still exhibit large rates of undetected silent data corruptions (SDC). These high rates of undetected SDCs are caused by the insufficient protection of control and data flow through AN-codes. In contrast, ANB-and ANBD-codes promise much higher error detection rates because they also detect errors in control and data flow. We present our encoding compiler that automatically applies either an AN-, ANBor ANBD-code to an application. Our error injections show that AN-, ANB-, and ANBD-codes successfully detect errors and more important that indeed ANB-and ANBD-codes reduce the SDC rate more effectively than AN-codes. The difference between ANBD-and ANB-codes is also visible but less pronounced.

show abstract