Zobrazeno 1 - 10
of 6 279
pro vyhledávání: '"A. Schöpf"'
Machine unlearning is gaining increasing attention as a way to remove adversarial data poisoning attacks from already trained models and to comply with privacy and AI regulations. The objective is to unlearn the effect of undesired data from a traine
Externí odkaz:
http://arxiv.org/abs/2412.00761
This paper explores how Large Language Models (LLMs) can automate consensus-seeking in supply chain management (SCM), where frequent decisions on problems such as inventory levels and delivery times require coordination among companies. Traditional S
Externí odkaz:
http://arxiv.org/abs/2411.10184
Autor:
Chundawat, Vikram S, Niroula, Pushkar, Dhungana, Prasanna, Schoepf, Stefan, Mandal, Murari, Brintrup, Alexandra
Federated learning (FL) has enabled collaborative model training across decentralized data sources or clients. While adding new participants to a shared model does not pose great technical hurdles, the removal of a participant and their related infor
Externí odkaz:
http://arxiv.org/abs/2410.04144
Autor:
Rawat, Ambrish, Schoepf, Stefan, Zizzo, Giulio, Cornacchia, Giandomenico, Hameed, Muhammad Zaid, Fraser, Kieran, Miehling, Erik, Buesser, Beat, Daly, Elizabeth M., Purcell, Mark, Sattigeri, Prasanna, Chen, Pin-Yu, Varshney, Kush R.
As generative AI, particularly large language models (LLMs), become increasingly integrated into production applications, new attack surfaces and vulnerabilities emerge and put a focus on adversarial threats in natural language and multi-modal system
Externí odkaz:
http://arxiv.org/abs/2409.15398
Autor:
Schöpf, Jörg, Piva, Valentina, van Loosdrecht, Paul H. M., Lindfors-Vrejoiu, Ionela, Shafar, Padraic, Kumah, Divine P., Zhang, Xuanyi, Yao, Lide, van Dijken, Sebastian
In ferromagnetic oxide epitaxial multilayers, magnetic properties and interlayer coupling are determined by a variety of factors. Beyond the contribution of interlayer exchange coupling, strain and interfacial effects, such as structural reconstructi
Externí odkaz:
http://arxiv.org/abs/2406.17432
Adversarial attacks by malicious actors on machine learning systems, such as introducing poison triggers into training datasets, pose significant risks. The challenge in resolving such an attack arises in practice when only a subset of the poisoned d
Externí odkaz:
http://arxiv.org/abs/2406.09173
Logically constrained term rewriting is a relatively new formalism where rules are equipped with constraints over some arbitrary theory. Although there are many recent advances with respect to rewriting induction, completion, complexity analysis and
Externí odkaz:
http://arxiv.org/abs/2405.01174
We present a machine unlearning approach that is both retraining- and label-free. Most existing machine unlearning approaches require a model to be fine-tuned to remove information while preserving performance. This is computationally expensive and n
Externí odkaz:
http://arxiv.org/abs/2402.19308
We show that (local) confluence of terminating locally constrained rewrite systems is undecidable, even when the underlying theory is decidable. Several confluence criteria for logically constrained rewrite systems are known. These were obtained by r
Externí odkaz:
http://arxiv.org/abs/2402.13552
Data entry constitutes a fundamental component of the machine learning pipeline, yet it frequently results in the introduction of labelling errors. When a model has been trained on a dataset containing such errors its performance is reduced. This lea
Externí odkaz:
http://arxiv.org/abs/2402.10098