Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Gubri, Martin"'
As large language models (LLMs) are increasingly deployed in user-facing applications, building trust and maintaining safety by accurately quantifying a model's confidence in its prediction becomes even more important. However, finding effective ways
Externí odkaz:
http://arxiv.org/abs/2403.05973
Large Language Model (LLM) services and models often come with legal rules on who can use them and how they must use them. Assessing the compliance of the released LLMs is crucial, as these rules protect the interests of the LLM contributor and preve
Externí odkaz:
http://arxiv.org/abs/2402.12991
The rapid advancement and widespread use of large language models (LLMs) have raised significant concerns regarding the potential leakage of personally identifiable information (PII). These models are often trained on vast quantities of web-collected
Externí odkaz:
http://arxiv.org/abs/2307.01881
Transferability is the property of adversarial examples to be misclassified by other models than the surrogate model for which they were crafted. Previous research has shown that early stopping the training of the surrogate model substantially increa
Externí odkaz:
http://arxiv.org/abs/2304.02688
We propose transferability from Large Geometric Vicinity (LGV), a new technique to increase the transferability of black-box adversarial attacks. LGV starts from a pretrained surrogate model and collects multiple weight sets from a few additional tra
Externí odkaz:
http://arxiv.org/abs/2207.13129
Graph-based Semi-Supervised Learning (GSSL) is a practical solution to learn from a limited amount of labelled data together with a vast amount of unlabelled data. However, due to their reliance on the known labels to infer the unknown labels, these
Externí odkaz:
http://arxiv.org/abs/2012.07381
An established way to improve the transferability of black-box evasion attacks is to craft the adversarial examples on an ensemble-based surrogate to increase diversity. We argue that transferability is fundamentally related to uncertainty. Based on
Externí odkaz:
http://arxiv.org/abs/2011.05074
Autor:
Gubri, Martin
Machine Learning models have been shown to be vulnerable to adversarial examples, ie. the manipulation of data by a attacker to defeat a defender's classifier at test time. We present a novel probabilistic definition of adversarial examples in perfec
Externí odkaz:
http://arxiv.org/abs/1801.01953
Autor:
Gubri, Martin
Despite state-of-the-art performance on natural data, Deep Neural Networks (DNNs) are highly vulnerable to adversarial examples, i.e., imperceptible, carefully crafted perturbations of inputs applied at test time. Adversarial examples can transfer: a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______2658::71fe00a83bc8bfea518be26c548dd5ec
http://orbilu.uni.lu/handle/10993/55429
http://orbilu.uni.lu/handle/10993/55429