High frequency patterns play a key role in the generation of adversarial examples

Zhou, Yue; Hu, Xiaofang; Han, Jiaqi; Wang, Lidan; Duan, Shukai

doi:10.1016/j.neucom.2021.06.078

Cited by 13 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alternatively, the two issues might be addressed in a blended manner. For example, since adversarial perturbations have been shown to modify the frequencies of the resulting image spectrum [36], [37], an analysis in the frequency domain could be exploited for the detection of adversarial presentation attacks under the hypothesis that this frequency is kept along the PAI fabrication process.…”

Section: Black-box Resultsmentioning

confidence: 99%

Realistic Fingerprint Presentation Attacks Based on an Adversarial Approach

Casula,

Orrù,

Marrone

et al. 2024

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

Section: Black-box Resultsmentioning

confidence: 99%

Realistic Fingerprint Presentation Attacks Based on an Adversarial Approach

Casula,

Orrù,

Marrone

et al. 2024

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

“…Although great potentials and advantages the SNNs have held, their capabilities have not demonstrated as much as the ANNs, mainly because of the lack of the corresponding algorithms and the high-performance volatile memristors. [258,259] Therefore, multidisciplinary efforts to build an optimizing hardware platform to implement the SNNs, ANNs, and the hybrid ANNs-ANNs are necessary for an ultra-large-scale crossbar array-based system. In addition, the chip design is an important tache for the chip process.…”

Section: Challenges Progress and Opportunities For Volatile And Nonvo...mentioning

confidence: 99%

Volatile and Nonvolatile Memristive Devices for Neuromorphic Computing

Zhou

Wang

Sun

et al. 2022

Adv Elect Materials

Self Cite

140

View full text Add to dashboard Cite

(5 of 33)www.advelectronicmat.de state after operation an external stimulation (Figure 2f). As the increasing stimulation, the transition state entering to the metallic state leads to the Mott layer with low resistance state (LRS) (Figure 2g). The insulator to metal transition is in a timescale of femtosecond and picosecond, [69] while from the opposite transition from the metal state to the insulator state Figure 3. Second-order memristor for temporal information simulation. a) Conception of the second-order memristor. Adapted with permission. [51] Copyright 2015, American Chemical Society. b) Schematic of an artificial neuron consisting of dendrites, soma, and axon constructed by the secondorder memristor circuit. c) The temporal summation of excitatory postsynaptic currents (EPSCs) for the frequency-dependency conductance evolution of 2nd memristor. Adapted with permission. [52] Copyright 2018, Wiley. d) The second-order memristor networks consist of 128 inputs and 7 outputs for temporal learning simulation, from up to bottom denotes before training state with random weights and different learned motion speeds. Adapted with permission. [49] Copyright 2017, IEEE. e) Transient temperature evolution with Δt = 1 µs and Δt = 100 ns. Adapted with permission.

show abstract

“…Most adversarial attack algorithms exploit CNNs' high frequency distortion vulnerability of convolutional neural networks [53]. Some research aimed at detecting the adversarial attacks is based on image spectrum analysis [54] [55].…”

Section: The Theoretical Approach To the Problem Solutionmentioning

confidence: 99%

Low-Pass Image Filtering to Achieve Adversarial Robustness

Ziyadinov,

Tereshonok

2023

Preprint

View full text Add to dashboard Cite

In this paper, we continue the research cycle on the properties of convolutional neural network-based image recognition systems and ways to improve noise immunity and robustness [1]. Currently, a popular research area related to artificial neural networks is adversarial attacks. The effect of adversarial attacks on the image is not highly perceptible to the human eye, also it drastically reduces the neural network accuracy. Image perception by a machine is highly dependent on the propagation of high frequency distortions throughout the network. At the same time, a human efficiently ignores high-frequency distortions, perceiving the shape of objects as a whole. The approach proposed in this paper can improve the image recognition accuracy in the presence of high-frequency distortions, in particular, caused by adversarial attacks. The proposed technique makes it possible to measure up the logic of artificial neural network to that of a human, for whom high-frequency distortions are not decisive in object recognition.

show abstract

High frequency patterns play a key role in the generation of adversarial examples

Cited by 13 publications

References 9 publications

Realistic Fingerprint Presentation Attacks Based on an Adversarial Approach

Realistic Fingerprint Presentation Attacks Based on an Adversarial Approach

Volatile and Nonvolatile Memristive Devices for Neuromorphic Computing

Low-Pass Image Filtering to Achieve Adversarial Robustness

Contact Info

Product

Resources

About