Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313171097> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W4313171097 abstract "As machine learning (ML) has become more preva-lent across many critical domains, so has the need to understand ML applications' resilience. While prior work like TensorFI [1], MindFI [2], and PyTorchFI [3] has focused on building ML fault injectors for specific ML frameworks, there has been little work on performing fault injection (FI) for ML applications written in multiple frameworks. We present LLTFI, a framework-agnostic fault injection tool for ML applications, allowing users to run FI experiments on ML applications at the LLVM IR level. LLTFI provides users with finer FI granularity at the level of instructions, and a better understanding of how faults manifest and propagate between different ML components. We evaluate LLTFI on six ML programs and compare it with TensorFI. We found significant differences in the Silent Data Corruption (SDC) rates for similar faults between the two tools. Finally, we use LLTFI to evaluate the efficacy of selective instruction duplication - an error mitigation technique - for ML programs." @default.
- W4313171097 created "2023-01-06" @default.
- W4313171097 creator A5070061214 @default.
- W4313171097 creator A5073641368 @default.
- W4313171097 creator A5091644091 @default.
- W4313171097 date "2022-10-01" @default.
- W4313171097 modified "2023-10-14" @default.
- W4313171097 title "LLTFI: Framework Agnostic Fault Injection for Machine Learning Applications (Tools and Artifact Track)" @default.
- W4313171097 cites W1619770058 @default.
- W4313171097 cites W2013280342 @default.
- W4313171097 cites W2130189691 @default.
- W4313171097 cites W2148313391 @default.
- W4313171097 cites W2152833323 @default.
- W4313171097 cites W2402686027 @default.
- W4313171097 cites W241117969 @default.
- W4313171097 cites W2612733213 @default.
- W4313171097 cites W2767260595 @default.
- W4313171097 cites W2809188712 @default.
- W4313171097 cites W2902203584 @default.
- W4313171097 cites W2903175372 @default.
- W4313171097 cites W2983012040 @default.
- W4313171097 cites W3000371584 @default.
- W4313171097 cites W3036979375 @default.
- W4313171097 cites W3046764219 @default.
- W4313171097 cites W3104284241 @default.
- W4313171097 cites W3122286897 @default.
- W4313171097 cites W3134690320 @default.
- W4313171097 cites W3185323353 @default.
- W4313171097 cites W3187862527 @default.
- W4313171097 cites W4213283227 @default.
- W4313171097 cites W4246166885 @default.
- W4313171097 cites W4285355904 @default.
- W4313171097 doi "https://doi.org/10.1109/issre55969.2022.00036" @default.
- W4313171097 hasPublicationYear "2022" @default.
- W4313171097 type Work @default.
- W4313171097 citedByCount "2" @default.
- W4313171097 countsByYear W43131710972023 @default.
- W4313171097 crossrefType "proceedings-article" @default.
- W4313171097 hasAuthorship W4313171097A5070061214 @default.
- W4313171097 hasAuthorship W4313171097A5073641368 @default.
- W4313171097 hasAuthorship W4313171097A5091644091 @default.
- W4313171097 hasConcept C111919701 @default.
- W4313171097 hasConcept C113775141 @default.
- W4313171097 hasConcept C119857082 @default.
- W4313171097 hasConcept C120314980 @default.
- W4313171097 hasConcept C121332964 @default.
- W4313171097 hasConcept C127313418 @default.
- W4313171097 hasConcept C149635348 @default.
- W4313171097 hasConcept C154945302 @default.
- W4313171097 hasConcept C165205528 @default.
- W4313171097 hasConcept C175551986 @default.
- W4313171097 hasConcept C177774035 @default.
- W4313171097 hasConcept C2775928411 @default.
- W4313171097 hasConcept C2777904410 @default.
- W4313171097 hasConcept C2779010991 @default.
- W4313171097 hasConcept C2779585090 @default.
- W4313171097 hasConcept C41008148 @default.
- W4313171097 hasConcept C63540848 @default.
- W4313171097 hasConcept C97355855 @default.
- W4313171097 hasConceptScore W4313171097C111919701 @default.
- W4313171097 hasConceptScore W4313171097C113775141 @default.
- W4313171097 hasConceptScore W4313171097C119857082 @default.
- W4313171097 hasConceptScore W4313171097C120314980 @default.
- W4313171097 hasConceptScore W4313171097C121332964 @default.
- W4313171097 hasConceptScore W4313171097C127313418 @default.
- W4313171097 hasConceptScore W4313171097C149635348 @default.
- W4313171097 hasConceptScore W4313171097C154945302 @default.
- W4313171097 hasConceptScore W4313171097C165205528 @default.
- W4313171097 hasConceptScore W4313171097C175551986 @default.
- W4313171097 hasConceptScore W4313171097C177774035 @default.
- W4313171097 hasConceptScore W4313171097C2775928411 @default.
- W4313171097 hasConceptScore W4313171097C2777904410 @default.
- W4313171097 hasConceptScore W4313171097C2779010991 @default.
- W4313171097 hasConceptScore W4313171097C2779585090 @default.
- W4313171097 hasConceptScore W4313171097C41008148 @default.
- W4313171097 hasConceptScore W4313171097C63540848 @default.
- W4313171097 hasConceptScore W4313171097C97355855 @default.
- W4313171097 hasLocation W43131710971 @default.
- W4313171097 hasOpenAccess W4313171097 @default.
- W4313171097 hasPrimaryLocation W43131710971 @default.
- W4313171097 hasRelatedWork W2011624601 @default.
- W4313171097 hasRelatedWork W2377919138 @default.
- W4313171097 hasRelatedWork W2378857091 @default.
- W4313171097 hasRelatedWork W2491314273 @default.
- W4313171097 hasRelatedWork W2931688134 @default.
- W4313171097 hasRelatedWork W2999756192 @default.
- W4313171097 hasRelatedWork W4226090359 @default.
- W4313171097 hasRelatedWork W4312356560 @default.
- W4313171097 hasRelatedWork W4382701072 @default.
- W4313171097 hasRelatedWork W936373746 @default.
- W4313171097 isParatext "false" @default.
- W4313171097 isRetracted "false" @default.
- W4313171097 workType "article" @default.