Zobrazeno 1 - 10
of 103
pro vyhledávání: '"Jovanović, Nikola"'
Watermarking has emerged as a promising way to detect LLM-generated text. To apply a watermark an LLM provider, given a secret key, augments generations with a signal that is later detectable by any party with the same key. Recent work has proposed t
Externí odkaz:
http://arxiv.org/abs/2405.20777
The goal of Fair Representation Learning (FRL) is to mitigate biases in machine learning models by learning data representations that enable high accuracy on downstream tasks while minimizing discrimination based on sensitive attributes. The evaluati
Externí odkaz:
http://arxiv.org/abs/2405.18161
LLM watermarking has attracted attention as a promising way to detect AI-generated content, with some works suggesting that current schemes may already be fit for deployment. In this work we dispute this claim, identifying watermark stealing (WS) as
Externí odkaz:
http://arxiv.org/abs/2402.19361
Aiming to train and deploy predictive models, organizations collect large amounts of detailed client data, risking the exposure of private information in the event of a breach. To mitigate this, policymakers increasingly demand compliance with the da
Externí odkaz:
http://arxiv.org/abs/2311.10500
Malicious server (MS) attacks have enabled the scaling of data stealing in federated learning to large batch sizes and secure aggregation, settings previously considered private. However, many concerns regarding the client-side detectability of MS at
Externí odkaz:
http://arxiv.org/abs/2306.03013
Reliable neural networks (NNs) provide important inference-time reliability guarantees such as fairness and robustness. Complementarily, privacy-preserving NN inference protects the privacy of client data. So far these two emerging areas have been la
Externí odkaz:
http://arxiv.org/abs/2210.15614
Fair representation learning (FRL) is a popular class of methods aiming to produce fair classifiers via data preprocessing. Recent regulatory directives stress the need for FRL methods that provide practical certificates, i.e., provable upper bounds
Externí odkaz:
http://arxiv.org/abs/2210.07213
State-of-the-art neural network verifiers are fundamentally based on one of two paradigms: either encoding the whole verification problem via tight multi-neuron convex relaxations or applying a Branch-and-Bound (BaB) procedure leveraging imprecise bu
Externí odkaz:
http://arxiv.org/abs/2205.00263
Recent work shows that sensitive user data can be reconstructed from gradient updates, breaking the key privacy promise of federated learning. While success was demonstrated primarily on image data, these methods do not directly transfer to other dom
Externí odkaz:
http://arxiv.org/abs/2202.08827
We study the problem of adversarially robust self-supervised learning on graphs. In the contrastive learning framework, we introduce a new method that increases the adversarial robustness of the learned representations through i) adversarial transfor
Externí odkaz:
http://arxiv.org/abs/2102.13085