FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4286308003> ?p ?o ?g. }

• W4286308003 abstract "With the future 6G era, spiking neural networks (SNNs) can be powerful processing tools in various areas due to their strong artificial intelligence (AI) processing capabilities, such as biometric recognition, AI robotics, autonomous drive, and healthcare. However, within Cyber Physical System (CPS), SNNs are surprisingly vulnerable to adversarial examples generated by benign samples with human-imperceptible noise, this will lead to serious consequences such as face recognition anomalies, autonomous drive-out of control, and wrong medical diagnosis. Only by fully understanding the principles of adversarial attacks with adversarial samples can we defend against them. Nowadays, most existing adversarial attacks result in a severe accuracy degradation to trained SNNs. Still, the critical issue is that they only generate adversarial samples by randomly adding, deleting, and flipping spike trains, making them easy to identify by filters, even by human eyes. Besides, the attack performance and speed also can be improved further. Hence, Spike Probabilistic Attack (SPA) is presented in this paper and aims to generate adversarial samples with more minor perturbations, greater model accuracy degradation, and faster iteration. SPA uses Poisson coding to generate spikes as probabilities, directly converting input data into spikes for faster speed and generating uniformly distributed perturbation for better attack performance. Moreover, an objective function is constructed for minor perturbations and keeping attack success rate, which speeds up the convergence by adjusting parameters. Both white-box and black-box settings are conducted to evaluate the merits of SPA. Experimental results show the model's accuracy under white-box attack decreases by 9.2S%~31.1S% better than others, and average success rates are 74.87% under the black-box setting. The experimental results indicate that SPA has better attack performance than other existing attacks in the white-box and better transferability performance in the black-box setting," @default.
• W4286308003 created "2022-07-21" @default.
• W4286308003 creator A5000291486 @default.
• W4286308003 creator A5034637087 @default.
• W4286308003 creator A5058120371 @default.
• W4286308003 creator A5067332736 @default.
• W4286308003 date "2022-05-01" @default.
• W4286308003 modified "2023-09-25" @default.
• W4286308003 title "SPA: An Efficient Adversarial Attack on Spiking Neural Networks using Spike Probabilistic" @default.
• W4286308003 cites W101771737 @default.
• W4286308003 cites W1570411240 @default.
• W4286308003 cites W2010520207 @default.
• W4286308003 cites W2020676607 @default.
• W4286308003 cites W2085949935 @default.
• W4286308003 cites W2138913040 @default.
• W4286308003 cites W2141840773 @default.
• W4286308003 cites W2147101007 @default.
• W4286308003 cites W2160815625 @default.
• W4286308003 cites W2271476098 @default.
• W4286308003 cites W2513853720 @default.
• W4286308003 cites W2619510810 @default.
• W4286308003 cites W2621826044 @default.
• W4286308003 cites W2774644650 @default.
• W4286308003 cites W2775079417 @default.
• W4286308003 cites W2779025322 @default.
• W4286308003 cites W2783525259 @default.
• W4286308003 cites W2790138085 @default.
• W4286308003 cites W2798878556 @default.
• W4286308003 cites W2854632500 @default.
• W4286308003 cites W2946092987 @default.
• W4286308003 cites W2962804204 @default.
• W4286308003 cites W2962847335 @default.
• W4286308003 cites W2963271936 @default.
• W4286308003 cites W2963857521 @default.
• W4286308003 cites W2965877203 @default.
• W4286308003 cites W2969542116 @default.
• W4286308003 cites W2974328520 @default.
• W4286308003 cites W2978279179 @default.
• W4286308003 cites W2980481100 @default.
• W4286308003 cites W2984844508 @default.
• W4286308003 cites W2995256488 @default.
• W4286308003 cites W3038988173 @default.
• W4286308003 cites W3041566370 @default.
• W4286308003 cites W3043809678 @default.
• W4286308003 cites W3090384356 @default.
• W4286308003 cites W3091443325 @default.
• W4286308003 cites W3093729901 @default.
• W4286308003 cites W3103266921 @default.
• W4286308003 cites W3124478039 @default.
• W4286308003 cites W3196874059 @default.
• W4286308003 cites W3199910846 @default.
• W4286308003 cites W3202199260 @default.
• W4286308003 cites W3202425151 @default.
• W4286308003 cites W4231081240 @default.
• W4286308003 cites W4232220759 @default.
• W4286308003 doi "https://doi.org/10.1109/ccgrid54584.2022.00046" @default.
• W4286308003 hasPublicationYear "2022" @default.
• W4286308003 type Work @default.
• W4286308003 citedByCount "1" @default.
• W4286308003 countsByYear W42863080032023 @default.
• W4286308003 crossrefType "proceedings-article" @default.
• W4286308003 hasAuthorship W4286308003A5000291486 @default.
• W4286308003 hasAuthorship W4286308003A5034637087 @default.
• W4286308003 hasAuthorship W4286308003A5058120371 @default.
• W4286308003 hasAuthorship W4286308003A5067332736 @default.
• W4286308003 hasConcept C115903868 @default.
• W4286308003 hasConcept C119857082 @default.
• W4286308003 hasConcept C153180895 @default.
• W4286308003 hasConcept C154945302 @default.
• W4286308003 hasConcept C184297639 @default.
• W4286308003 hasConcept C190839683 @default.
• W4286308003 hasConcept C205649164 @default.
• W4286308003 hasConcept C2781390188 @default.
• W4286308003 hasConcept C34413123 @default.
• W4286308003 hasConcept C37736160 @default.
• W4286308003 hasConcept C41008148 @default.
• W4286308003 hasConcept C49937458 @default.
• W4286308003 hasConcept C50644808 @default.
• W4286308003 hasConcept C58640448 @default.
• W4286308003 hasConcept C90509273 @default.
• W4286308003 hasConceptScore W4286308003C115903868 @default.
• W4286308003 hasConceptScore W4286308003C119857082 @default.
• W4286308003 hasConceptScore W4286308003C153180895 @default.
• W4286308003 hasConceptScore W4286308003C154945302 @default.
• W4286308003 hasConceptScore W4286308003C184297639 @default.
• W4286308003 hasConceptScore W4286308003C190839683 @default.
• W4286308003 hasConceptScore W4286308003C205649164 @default.
• W4286308003 hasConceptScore W4286308003C2781390188 @default.
• W4286308003 hasConceptScore W4286308003C34413123 @default.
• W4286308003 hasConceptScore W4286308003C37736160 @default.
• W4286308003 hasConceptScore W4286308003C41008148 @default.
• W4286308003 hasConceptScore W4286308003C49937458 @default.
• W4286308003 hasConceptScore W4286308003C50644808 @default.
• W4286308003 hasConceptScore W4286308003C58640448 @default.
• W4286308003 hasConceptScore W4286308003C90509273 @default.
• W4286308003 hasFunder F4320321001 @default.
• W4286308003 hasLocation W42863080031 @default.
• W4286308003 hasOpenAccess W4286308003 @default.
• W4286308003 hasPrimaryLocation W42863080031 @default.
• W4286308003 hasRelatedWork W157632740 @default.

• next