Amnexia 9th Birthday: ECZODIA, Linds, DNNS, Nikolina @ Kilomètre25 - 23 Aug feat. ECZODIA, Nikolina, DNNS + more

#SESH #ECZODIA #Nikolina #DNNS

https://sesh.sx/events/12215444

I am really proud to announce that our latest effort on showing the advantages of our analog/digital #neuromorphic spiking neural network chips in solving complex biomedical applications has just been published here: https://rdcu.be/ef5N0

The demonstrates that *small* *highly variable* and *low accuracy* #SNNs can indeed be useful, without having to resort to #backprop in large-scale #DNNs! 😉

Ending the session, we saw Park et al.'s "DeepTaster: Adversarial Perturbation-Based Fingerprinting to Identify Proprietary Dataset Use in Deep Neural Networks" demonstrating the detection of unlawful dataset use in #DNNs. (https://www.acsac.org/2023/program/final/s321.html) 4/4
#DeepLearning #DataSecurity
ACSAC2023 Program – powered by OpenConf

'Densely Connected G-invariant Deep Neural Networks with Signed Permutation Representations', by Devanshu Agrawal, James Ostrowski.

http://jmlr.org/papers/v24/23-0294.html

#representations #dnns #dnn

Densely Connected G-invariant Deep Neural Networks with Signed Permutation Representations

DeepSec 2023 Talk: Skynet wants your Passwords! The Role of AI in Automating Social Engineering – Alexander Hurbean & Wolfgang Ettlinger
We techies love solving problems with cool technology, to where we attempt to implement the e
https://blog.deepsec.net/deepsec-2023-talk-skynet-wants-your-passwords-the-role-of-ai-in-automating-social-engineering-alexander-hurbean-wolfgang-ettlinger/
#Conference #AI #AttackPrevention #Deepfakes #DeepSec2023 #DNNs #SocialEngineering #Talk #Transformers
DeepSec 2023 Talk: Skynet wants your Passwords! The Role of AI in Automating Social Engineering - Alexander Hurbean & Wolfgang Ettlinger

This presentation at DeepSec 2023 explores the use of Artificial Intelligence Large Language Models for social engineering campaigns.

DeepSec In-Depth Security Conference

Training DNNs Resilient to Adversarial and Random Bit-Flips by Learning Quantization Ranges

https://openreview.net/forum?id=BxjHMPwZIH

#adversarial #quantization #dnns

Training DNNs Resilient to Adversarial and Random Bit-Flips by...

Promoting robustness in deep neural networks (DNNs) is crucial for their reliable deployment in uncertain environments, such as low-power settings or in the presence of adversarial attacks. In...

OpenReview

Beyond Distribution Shift: Spurious Features Through the Lens of Training Dynamics

https://openreview.net/forum?id=Tkvmt9nDmB

#learned #dnns #generalization

Beyond Distribution Shift: Spurious Features Through the Lens of...

Deep Neural Networks (DNNs) are prone to learning spurious features that correlate with the label during training but are irrelevant to the learning problem. This hurts model generalization and...

OpenReview

Compressors such as #gzip + #kNN (k-nearest-neighbor i.e. your grandparents' #classifier) beats the living daylights of Deep neural networks (#DNNs) in sentence classification.
H/t @lgessler

Without any training parameters, this non-parametric, easy and lightweight (no #GPU) method achieves results that are competitive with non-pretrained deep learning methods on six in-distribution datasets.It even outperforms BERT on all five OOD datasets.

#AI #machinelearning

https://aclanthology.org/2023.findings-acl.426/

“Low-Resource” Text Classification: A Parameter-Free Classification Method with Compressors

Zhiying Jiang, Matthew Yang, Mikhail Tsirlin, Raphael Tang, Yiqin Dai, Jimmy Lin. Findings of the Association for Computational Linguistics: ACL 2023. 2023.

ACL Anthology

'Integrating Random Effects in Deep Neural Networks', by Giora Simchoni, Saharon Rosset.

http://jmlr.org/papers/v24/22-0501.html

#dnns #dnn #deep

Integrating Random Effects in Deep Neural Networks