Matches in SemOpenAlex for { <https://semopenalex.org/work/W3102908045> ?p ?o ?g. }
- W3102908045 endingPage "6" @default.
- W3102908045 startingPage "1" @default.
- W3102908045 abstract "Despite the great achievements of deep neural networks (DNNs), the vulnerability of state-of-the-art DNNs raises security concerns of DNNs in many application domains requiring high reliability. We propose the fault sneaking attack on DNNs, where the adversary aims to misclassify certain input images into any target labels by modifying the DNN parameters. We apply ADMM (alternating direction method of multipliers) for solving the optimization problem of the fault sneaking attack with two constraints: 1) the classification of the other images should be unchanged and 2) the parameter modifications should be minimized. Specifically, the first constraint requires us not only to inject designated faults (misclassifications), but also to hide the faults for stealthy or sneaking considerations by maintaining model accuracy. The second constraint requires us to minimize the parameter modifications (using 0 norm to measure the number of modifications and 2 norm to measure the magnitude of modifications). Comprehensive experimental evaluation demonstrates that the proposed framework can inject multiple sneaking faults without losing the overall test accuracy performance.CCS CONCEPTS•Security and privacy → Domain-specific security and privacy architectures;Network security; •Networks → Network performance analysis; •Theory of computation → Theory and algorithms for application domains;" @default.
- W3102908045 created "2020-11-23" @default.
- W3102908045 creator A5025596795 @default.
- W3102908045 creator A5043582832 @default.
- W3102908045 creator A5045682482 @default.
- W3102908045 creator A5057715825 @default.
- W3102908045 creator A5073885088 @default.
- W3102908045 creator A5083131515 @default.
- W3102908045 date "2019-06-02" @default.
- W3102908045 modified "2023-10-10" @default.
- W3102908045 title "Fault Sneaking Attack: a Stealthy Framework for Misleading Deep Neural Networks" @default.
- W3102908045 cites W2085992264 @default.
- W3102908045 cites W2105693192 @default.
- W3102908045 cites W2112507308 @default.
- W3102908045 cites W2112796928 @default.
- W3102908045 cites W2144906988 @default.
- W3102908045 cites W2157116240 @default.
- W3102908045 cites W2164278908 @default.
- W3102908045 cites W2167421362 @default.
- W3102908045 cites W2180612164 @default.
- W3102908045 cites W2420341751 @default.
- W3102908045 cites W2475053276 @default.
- W3102908045 cites W2479004360 @default.
- W3102908045 cites W2505343551 @default.
- W3102908045 cites W2537014044 @default.
- W3102908045 cites W2557283755 @default.
- W3102908045 cites W2612654412 @default.
- W3102908045 cites W2741933435 @default.
- W3102908045 cites W2769824527 @default.
- W3102908045 cites W2771112233 @default.
- W3102908045 cites W2782017896 @default.
- W3102908045 cites W2798302089 @default.
- W3102908045 cites W2807835252 @default.
- W3102908045 cites W2900971432 @default.
- W3102908045 cites W2902931196 @default.
- W3102908045 cites W2913535645 @default.
- W3102908045 cites W2963207607 @default.
- W3102908045 cites W2963389226 @default.
- W3102908045 cites W2963424284 @default.
- W3102908045 cites W2963564844 @default.
- W3102908045 cites W2963612069 @default.
- W3102908045 cites W2963685823 @default.
- W3102908045 cites W2963777745 @default.
- W3102908045 cites W2963857521 @default.
- W3102908045 cites W2964082701 @default.
- W3102908045 cites W2964153729 @default.
- W3102908045 cites W2964253222 @default.
- W3102908045 cites W3118608800 @default.
- W3102908045 hasPublicationYear "2019" @default.
- W3102908045 type Work @default.
- W3102908045 sameAs 3102908045 @default.
- W3102908045 citedByCount "13" @default.
- W3102908045 countsByYear W31029080452018 @default.
- W3102908045 countsByYear W31029080452019 @default.
- W3102908045 countsByYear W31029080452020 @default.
- W3102908045 countsByYear W31029080452021 @default.
- W3102908045 countsByYear W31029080452022 @default.
- W3102908045 crossrefType "proceedings-article" @default.
- W3102908045 hasAuthorship W3102908045A5025596795 @default.
- W3102908045 hasAuthorship W3102908045A5043582832 @default.
- W3102908045 hasAuthorship W3102908045A5045682482 @default.
- W3102908045 hasAuthorship W3102908045A5057715825 @default.
- W3102908045 hasAuthorship W3102908045A5073885088 @default.
- W3102908045 hasAuthorship W3102908045A5083131515 @default.
- W3102908045 hasBestOaLocation W31029080451 @default.
- W3102908045 hasConcept C121332964 @default.
- W3102908045 hasConcept C134306372 @default.
- W3102908045 hasConcept C154945302 @default.
- W3102908045 hasConcept C163258240 @default.
- W3102908045 hasConcept C17744445 @default.
- W3102908045 hasConcept C191795146 @default.
- W3102908045 hasConcept C199539241 @default.
- W3102908045 hasConcept C2524010 @default.
- W3102908045 hasConcept C2776036281 @default.
- W3102908045 hasConcept C2984842247 @default.
- W3102908045 hasConcept C33923547 @default.
- W3102908045 hasConcept C36503486 @default.
- W3102908045 hasConcept C38652104 @default.
- W3102908045 hasConcept C41008148 @default.
- W3102908045 hasConcept C41065033 @default.
- W3102908045 hasConcept C43214815 @default.
- W3102908045 hasConcept C50644808 @default.
- W3102908045 hasConcept C62520636 @default.
- W3102908045 hasConcept C95713431 @default.
- W3102908045 hasConceptScore W3102908045C121332964 @default.
- W3102908045 hasConceptScore W3102908045C134306372 @default.
- W3102908045 hasConceptScore W3102908045C154945302 @default.
- W3102908045 hasConceptScore W3102908045C163258240 @default.
- W3102908045 hasConceptScore W3102908045C17744445 @default.
- W3102908045 hasConceptScore W3102908045C191795146 @default.
- W3102908045 hasConceptScore W3102908045C199539241 @default.
- W3102908045 hasConceptScore W3102908045C2524010 @default.
- W3102908045 hasConceptScore W3102908045C2776036281 @default.
- W3102908045 hasConceptScore W3102908045C2984842247 @default.
- W3102908045 hasConceptScore W3102908045C33923547 @default.
- W3102908045 hasConceptScore W3102908045C36503486 @default.
- W3102908045 hasConceptScore W3102908045C38652104 @default.
- W3102908045 hasConceptScore W3102908045C41008148 @default.