Zobrazeno 1 - 10
of 33
pro vyhledávání: '"Müller, Mark Niklas"'
Rigorous software testing is crucial for developing and maintaining high-quality code, making automated test generation a promising avenue for both improving software quality and boosting the effectiveness of code generation methods. However, while c
Externí odkaz:
http://arxiv.org/abs/2406.12952
Public benchmarks play an essential role in the evaluation of large language models. However, data contamination can lead to inflated performance, rendering them unreliable for model comparison. It is therefore crucial to detect contamination and est
Externí odkaz:
http://arxiv.org/abs/2405.16281
Federated learning works by aggregating locally computed gradients from multiple clients, thus enabling collaborative training without sharing private client data. However, prior work has shown that the data can actually be recovered by the server us
Externí odkaz:
http://arxiv.org/abs/2405.15586
Autor:
Balauca, Stefan, Müller, Mark Niklas, Mao, Yuhao, Baader, Maximilian, Fischer, Marc, Vechev, Martin
Training neural networks with high certified accuracy against adversarial examples remains an open problem despite significant efforts. While certification methods can effectively leverage tight convex relaxations for bound computation, in training,
Externí odkaz:
http://arxiv.org/abs/2403.07095
Federated learning is a framework for collaborative machine learning where clients only share gradient updates and not their private data with a server. However, it was recently shown that gradient inversion attacks can reconstruct this data from the
Externí odkaz:
http://arxiv.org/abs/2403.03945
Large language models are widespread, with their performance on benchmarks frequently guiding user preferences for one model over another. However, the vast amount of data these models are trained on can inadvertently lead to contamination with publi
Externí odkaz:
http://arxiv.org/abs/2402.02823
While the ImageNet dataset has been driving computer vision research over the past decade, significant label noise and ambiguity have made top-1 accuracy an insufficient measure of further progress. To address this, new label-sets and evaluation prot
Externí odkaz:
http://arxiv.org/abs/2401.02430
Many recent prompting strategies for large language models (LLMs) query the model multiple times sequentially -- first to produce intermediate results and then the final answer. However, using these methods, both decoder and model are unaware of pote
Externí odkaz:
http://arxiv.org/abs/2311.04954
Convex relaxations are a key component of training and certifying provably safe neural networks. However, despite substantial progress, a wide and poorly understood accuracy gap to standard networks remains, raising the question of whether this is du
Externí odkaz:
http://arxiv.org/abs/2311.04015
As robustness verification methods are becoming more precise, training certifiably robust neural networks is becoming ever more relevant. To this end, certified training methods compute and then optimize an upper bound on the worst-case loss over a r
Externí odkaz:
http://arxiv.org/abs/2306.10426