DPCOVID: Privacy-Preserving Federated Covid-19 Detection. (arXiv:2110.13760v1 [cs.CR])
Coronavirus (COVID-19) has shown an unprecedented global crisis by the detrimental effect on the global economy and health. The number…
DPCOVID: Privacy-Preserving Federated Covid-19 Detection. (arXiv:2110.13760v1 [cs.CR])
Coronavirus (COVID-19) has shown an unprecedented global crisis by the detrimental effect on the global economy and health. The number…
Secure Sum Outperforms Homomorphic Encryption in (Current) Collaborative Deep Learning. (arXiv:2006.02894v2 [cs.CR] UPDATED)
Deep learning (DL) approaches are achieving extraordinary results in a wide range of domains, but often require a massive collection…
Secure Sum Outperforms Homomorphic Encryption in (Current) Collaborative Deep Learning. (arXiv:2006.02894v2 [cs.CR] UPDATED)
Deep learning (DL) approaches are achieving extraordinary results in a wide range of domains, but often require a massive collection…
Secure Sum Outperforms Homomorphic Encryption in (Current) Collaborative Deep Learning. (arXiv:2006.02894v2 [cs.CR] UPDATED)
Deep learning (DL) approaches are achieving extraordinary results in a wide range of domains, but often require a massive collection…
Embedding and Extraction of Knowledge in Tree Ensemble Classifiers. (arXiv:2010.08281v3 [cs.CR] UPDATED)
The embedding and extraction of useful knowledge is a recent trend in machine learning applications, e.g., to supplement existing datasets…
Adversarial Robustness with Non-uniform Perturbations. (arXiv:2102.12002v3 [cs.LG] UPDATED)
Robustness of machine learning models is critical for security related applications, where real-world adversaries are uniquely focused on evading neural…
Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Data. (arXiv:2106.01336v3 [cs.LG] UPDATED)
We study stochastic convex optimization with heavy-tailed data under the constraint of differential privacy (DP). Most prior work on this…
ESP32 Clock Takes Time to Give Weather Info, Too
It’s fall in the northern hemisphere, so [Mike Rankin]’s kids are back in school and have returned to consulting him…
A Little Robustness Goes a Long Way: Leveraging Robust Features for Targeted Transfer Attacks. (arXiv:2106.02105v2 [cs.LG] UPDATED)
Adversarial examples for neural network image classifiers are known to be transferable: examples optimized to be misclassified by a source…