Results 181 to 190 of about 177,286 (215)

Adversarial Defense without <i>Adversarial Defense</i>: Enhancing Language Model Robustness via Instance-level Principal Component Removal. [PDF]

Trans Assoc Comput Linguist
Wang Y, Xiao C, Li Y, Middleton SE, Moubayed NA, Lin C.   +5 more
europepmc   +1 more source

Synthetic artificial intelligence in cardiology: from generative models to clinical applications. [PDF]

Eur Heart J Open
Parise G, Ceravolo R, Lucà F, Gulizia MM, Tetta C, Parise O, Nardi F, Grimaldi M, Gelsomino S.   +8 more
europepmc   +1 more source

Enhancing tumor deepfake detection in MRI scans using adversarial feature fusion ensembles. [PDF]

Sci Rep
Ali A, Basha HA, Thanuja K, Puneet, Gupta SK, Kim S.   +5 more
europepmc   +1 more source

Investigation of the Robustness and Transferability of Adversarial Patches in Multi-View Infrared Target Detection. [PDF]

J Imaging
Zhou Q, Zhou Z, Zhang Z, Luo W, Xiao F, Xia S, Zhu C, Wang L.   +7 more
europepmc   +1 more source

Comprehensive analysis of security threats and privacy issues in indoor localization systems. [PDF]

Sci Rep
Ayub A, Abidin ZZ, Alhammadi A, Khan MA, Soliman NF, Ghazali NB, Algarni AD.   +6 more
europepmc   +1 more source

A quantum resilient deepfake detection framework using enhanced resnext and post quantum cryptography defence. [PDF]

Sci Rep
Shreeya KN, Subburaj B, Saketh KSG, Padmavathy TV, Alphonse S, Subramanian G.   +5 more
europepmc   +1 more source

SecMLOps: A comprehensive framework for integrating security throughout the machine learning operations lifecycle. [PDF]

Empir Softw Eng
Zhang X, Zhao P, Jaskolka J, Li H, Lu R.
europepmc   +1 more source

A comprehensive survey of deep face verification systems adversarial attacks and defense strategies. [PDF]

Sci Rep
Kilany S, Mahfouz A.
europepmc   +1 more source

Some of the next articles are maybe not open access.

Related searches:

Learning Universal Adversarial Perturbation by Adversarial Example

Proceedings of the AAAI Conference on Artificial Intelligence, 2022
Deep learning models have shown to be susceptible to universal adversarial perturbation (UAP), which has aroused wide concerns in the community. Compared with the conventional adversarial attacks that generate adversarial samples at the instance level, UAP can fool the target model for different instances with only a single perturbation, enabling us to
Maosen Li, Yanhua Yang, Kun Wei, Xu Yang 0019, Heng Huang   +4 more
openaire   +1 more source