Zobrazeno 1 - 10
of 10 067
pro vyhledávání: '"A. Kwiatkowska"'
Game theory provides an effective way to model strategic interactions among rational agents. In the context of formal verification, these ideas can be used to produce guarantees on the correctness of multi-agent systems, with a diverse range of appli
Externí odkaz:
http://arxiv.org/abs/2411.05599
Autor:
Chen, Jialuo, Wang, Jingyi, Zhang, Xiyue, Sun, Youcheng, Kwiatkowska, Marta, Chen, Jiming, Cheng, Peng
Due to the vast testing space, the increasing demand for effective and efficient testing of deep neural networks (DNNs) has led to the development of various DNN test case prioritization techniques. However, the fact that DNNs can deliver high-confid
Externí odkaz:
http://arxiv.org/abs/2409.09130
Most methods for neural network verification focus on bounding the image, i.e., set of outputs for a given input set. This can be used to, for example, check the robustness of neural network predictions to bounded perturbations of an input. However,
Externí odkaz:
http://arxiv.org/abs/2408.09262
Modern machine learning models are sensitive to the manipulation of both the training data (poisoning attacks) and inference data (adversarial examples). Recognizing this issue, the community has developed many empirical defenses against both attacks
Externí odkaz:
http://arxiv.org/abs/2406.11522
The ubiquity of deep learning algorithms in various applications has amplified the need for assuring their robustness against small input perturbations such as those occurring in adversarial attacks. Existing complete verification techniques offer pr
Externí odkaz:
http://arxiv.org/abs/2406.10154
A common issue in learning decision-making policies in data-rich settings is spurious correlations in the offline dataset, which can be caused by hidden confounders. Instrumental variable (IV) regression, which utilises a key unconfounded variable kn
Externí odkaz:
http://arxiv.org/abs/2405.08498
Consider an agent acting to achieve its temporal goal, but with a "trembling hand". In this case, the agent may mistakenly instruct, with a certain (typically small) probability, actions that are not intended due to faults or imprecision in its actio
Externí odkaz:
http://arxiv.org/abs/2404.16163
Online planning for partially observable Markov decision processes (POMDPs) provides efficient techniques for robot decision-making under uncertainty. However, existing methods fall short of preventing safety violations in dynamic environments. This
Externí odkaz:
http://arxiv.org/abs/2404.15557
We consider a variant of continuous-state partially-observable stochastic games with neural perception mechanisms and an asymmetric information structure. One agent has partial information, with the observation function implemented as a neural networ
Externí odkaz:
http://arxiv.org/abs/2404.10679
The lack of transparency of Deep Neural Networks continues to be a limitation that severely undermines their reliability and usage in high-stakes applications. Promising approaches to overcome such limitations are Prototype-Based Self-Explainable Neu
Externí odkaz:
http://arxiv.org/abs/2403.13740