FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4376126095> ?p ?o ?g. }

• W4376126095 endingPage "100053" @default.
• W4376126095 startingPage "100053" @default.
• W4376126095 abstract "Resistive memory (ReRAM) or memristor devices offer the prospect of more efficient computing. While memristors have been used for a variety of computing systems, their usage has gained significant popularity in the domain of deep learning. Weight matrices in deep neural networks can be mapped to crossbar architectures with memristive junctions, generally resulting in superior performance and energy efficiency. However, the nascent nature of ReRAM technology is directly associated with the presence of inherent non-idealities in the ReRAM devices currently available. Deep neural networks have already been shown to be susceptible to adversarial attacks, often by targeting vulnerabilities in the networks’ internal representation of input data. In this paper, we explore the causal relationship between device-level non-idealities in ReRAM devices and the classification performance of memristor-based neural network accelerators. Specifically, our aim is to generate images which bypass adversarial defense mechanisms in software neural networks but trigger non-trivial performance discrepancies in ReRAM-based neural networks. To this end, we have proposed a framework to generate adversarial images in the hypervolume between the two decision boundaries, thereby leveraging non-ideal device behavior for performance detriment. We employ state-of-the-art tools in explainable artificial intelligence to characterize our adversarial image samples, and derive a new metric to quantify susceptibility to adversarial attacks at the pixel and device-levels." @default.
• W4376126095 created "2023-05-12" @default.
• W4376126095 creator A5006831191 @default.
• W4376126095 creator A5015005145 @default.
• W4376126095 creator A5020014870 @default.
• W4376126095 creator A5050225133 @default.
• W4376126095 creator A5091922174 @default.
• W4376126095 creator A5091922175 @default.
• W4376126095 date "2023-07-01" @default.
• W4376126095 modified "2023-10-05" @default.
• W4376126095 title "Exploiting device-level non-idealities for adversarial attacks on ReRAM-based neural networks" @default.
• W4376126095 cites W1542981317 @default.
• W4376126095 cites W1964288235 @default.
• W4376126095 cites W1970974872 @default.
• W4376126095 cites W1987355931 @default.
• W4376126095 cites W1993522825 @default.
• W4376126095 cites W1997761795 @default.
• W4376126095 cites W2007339694 @default.
• W4376126095 cites W2015570990 @default.
• W4376126095 cites W2016922062 @default.
• W4376126095 cites W2021383442 @default.
• W4376126095 cites W2021797032 @default.
• W4376126095 cites W2022208730 @default.
• W4376126095 cites W2026429700 @default.
• W4376126095 cites W2026788380 @default.
• W4376126095 cites W2038348996 @default.
• W4376126095 cites W2039161462 @default.
• W4376126095 cites W2069418413 @default.
• W4376126095 cites W2080625874 @default.
• W4376126095 cites W2094452907 @default.
• W4376126095 cites W2101091847 @default.
• W4376126095 cites W2112181056 @default.
• W4376126095 cites W2127277527 @default.
• W4376126095 cites W2134716787 @default.
• W4376126095 cites W2136811604 @default.
• W4376126095 cites W2149380925 @default.
• W4376126095 cites W2162341456 @default.
• W4376126095 cites W2162651880 @default.
• W4376126095 cites W2165911664 @default.
• W4376126095 cites W2243397390 @default.
• W4376126095 cites W2313154504 @default.
• W4376126095 cites W2320080161 @default.
• W4376126095 cites W2323986115 @default.
• W4376126095 cites W2345421161 @default.
• W4376126095 cites W2397312330 @default.
• W4376126095 cites W2508602506 @default.
• W4376126095 cites W2516467421 @default.
• W4376126095 cites W2564219748 @default.
• W4376126095 cites W2581282721 @default.
• W4376126095 cites W2587722835 @default.
• W4376126095 cites W2613411459 @default.
• W4376126095 cites W2743001015 @default.
• W4376126095 cites W2771420577 @default.
• W4376126095 cites W2774297425 @default.
• W4376126095 cites W2781163782 @default.
• W4376126095 cites W2782791387 @default.
• W4376126095 cites W2791362176 @default.
• W4376126095 cites W2792604105 @default.
• W4376126095 cites W2806068823 @default.
• W4376126095 cites W2834392565 @default.
• W4376126095 cites W2890653437 @default.
• W4376126095 cites W2910128286 @default.
• W4376126095 cites W2913104037 @default.
• W4376126095 cites W2913347375 @default.
• W4376126095 cites W2942736824 @default.
• W4376126095 cites W2944325859 @default.
• W4376126095 cites W2946007558 @default.
• W4376126095 cites W2946641467 @default.
• W4376126095 cites W2952615984 @default.
• W4376126095 cites W2962700793 @default.
• W4376126095 cites W2962921201 @default.
• W4376126095 cites W2971211335 @default.
• W4376126095 cites W3015724253 @default.
• W4376126095 cites W3017900531 @default.
• W4376126095 cites W3018945530 @default.
• W4376126095 cites W3023377875 @default.
• W4376126095 cites W3035117791 @default.
• W4376126095 cites W3088347860 @default.
• W4376126095 cites W3095769467 @default.
• W4376126095 cites W3098316772 @default.
• W4376126095 cites W3103557498 @default.
• W4376126095 cites W3109868631 @default.
• W4376126095 cites W3165794952 @default.
• W4376126095 cites W3174261480 @default.
• W4376126095 cites W3184531420 @default.
• W4376126095 cites W3209340614 @default.
• W4376126095 cites W3214696084 @default.
• W4376126095 cites W4224943560 @default.
• W4376126095 cites W4229445200 @default.
• W4376126095 cites W4254436426 @default.
• W4376126095 doi "https://doi.org/10.1016/j.memori.2023.100053" @default.
• W4376126095 hasPublicationYear "2023" @default.
• W4376126095 type Work @default.
• W4376126095 citedByCount "0" @default.
• W4376126095 crossrefType "journal-article" @default.
• W4376126095 hasAuthorship W4376126095A5006831191 @default.
• W4376126095 hasAuthorship W4376126095A5015005145 @default.
• W4376126095 hasAuthorship W4376126095A5020014870 @default.

• next