H Wu, O Isac, A Zeljić, T Tagomori, M Daggitt… - … on Computer Aided …, 2024 - Springer
Marabou 2.0: A Versatile Formal Analyzer of Neural Networks | SpringerLink Skip to main content Advertisement SpringerLink Account Menu Find a journal Publish with us Track your …
Although neural networks are effective tools for processing information from image-based sensors to produce control actions, their complex nature limits their use in safety-critical …
H Wu, T Tagomori, A Robey, F Yang… - … IEEE Conference on …, 2023 - ieeexplore.ieee.org
We consider the problem of certifying the robustness of deep neural networks against real- world distribution shifts. To do so, we bridge the gap between hand-crafted specifications …
In contrast with ad-hoc methods for eXplainable Artificial Intelligence (XAI), formal explainability offers important guarantees of rigor. However, formal explainability is hindered …
Fair representation learning transforms user data into a representation that ensures fairness and utility regardless of the downstream application. However, learning individually fair …
H Boche, A Fono, G Kutyniok - arXiv preprint arXiv:2401.10310, 2024 - arxiv.org
Deep learning still has drawbacks in terms of trustworthiness, which describes a comprehensible, fair, safe, and reliable method. To mitigate the potential risk of AI, clear …
Most real world applications require dealing with stochasticity like sensor noise or predictive uncertainty, where formal specifications of desired behavior are inherently probabilistic …
H Boche, A Fono, G Kutyniok - 2024 IEEE International …, 2024 - ieeexplore.ieee.org
The lack of trustworthiness is a major downside of deep learning. To mitigate the associated risks clear obligations of deep learning models have been proposed via regulatory …
Y Yuan, S Wang, Z Su - 32nd USENIX Security Symposium (USENIX …, 2023 - usenix.org
The objective of neural network (NN) robustness certification is to determine if a NN changes its predictions when mutations are made to its inputs. While most certification research …