1 citations · 1 across the 3 of their papers we have counts for
3 papers
Differential Zonotopes for Verifying Global Robustness of DNNs
Anagha Athavale, Samuel Teuber, Matteo Maffei +3
The robustness of deep neural networks (DNNs) is critical in security-sensitive applications, where small input perturbations should not alter model predictions. This property is c…
Wanilla: Sound Noninterference Analysis for WebAssembly
Markus Scherer, Jeppe Fredsgaard Blaabjerg, Alexander Sjösten +1
WebAssembly (Wasm) is rapidly gaining popularity as a distribution format for software components embedded in various security-critical domains. Unfortunately, despite its prudent…
Verifying Global Two-Safety Properties in Neural Networks with Confidence
Anagha Athavale, Ezio Bartocci, Maria Christakis +3
We present the first automated verification technique for confidence-based 2-safety properties, such as global robustness and global fairness, in deep neural networks (DNNs). Our a…