Optimizing Information Loss Towards Robust Neural Networks

August 07, 2020 Β· Declared Dead Β· πŸ› Proceedings of the 2020 Workshop on DYnamic and Novel Advances in Machine Learning and Intelligent Cyber Security

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Philip Sperl, Konstantin BΓΆttinger arXiv ID 2008.03072 Category cs.CR: Cryptography & Security Cross-listed cs.LG, stat.ML Citations 3 Venue Proceedings of the 2020 Workshop on DYnamic and Novel Advances in Machine Learning and Intelligent Cyber Security Last Checked 4 months ago
Abstract
Neural Networks (NNs) are vulnerable to adversarial examples. Such inputs differ only slightly from their benign counterparts yet provoke misclassifications of the attacked NNs. The required perturbations to craft the examples are often negligible and even human imperceptible. To protect deep learning-based systems from such attacks, several countermeasures have been proposed with adversarial training still being considered the most effective. Here, NNs are iteratively retrained using adversarial examples forming a computational expensive and time consuming process often leading to a performance decrease. To overcome the downsides of adversarial training while still providing a high level of security, we present a new training approach we call \textit{entropic retraining}. Based on an information-theoretic-inspired analysis, entropic retraining mimics the effects of adversarial training without the need of the laborious generation of adversarial examples. We empirically show that entropic retraining leads to a significant increase in NNs' security and robustness while only relying on the given original data. With our prototype implementation we validate and show the effectiveness of our approach for various NN architectures and data sets.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Cryptography & Security

Died the same way β€” πŸ‘» Ghosted