The prosperity of machine learning has been accompanied by increasing attacks on the training process. Among them, poisoning attacks have become an emerging threat during …
When trying to gain better visibility into a machine learning model in order to understand and mitigate the associated risks, a potentially valuable source of evidence is: which training …
The success of machine learning is fueled by the increasing availability of computing power and large training datasets. The training data is used to learn new models or update existing …
M Goldblum, D Tsipras, C Xie, X Chen… - … on Pattern Analysis …, 2022 - ieeexplore.ieee.org
As machine learning systems grow in scale, so do their training data requirements, forcing practitioners to automate and outsource the curation of training data in order to achieve state …
We investigate a new method for injecting backdoors into machine learning models, based on compromising the loss-value computation in the model-training code. We use it to …
This work provides the community with a timely comprehensive review of backdoor attacks and countermeasures on deep learning. According to the attacker's capability and affected …
Federated Learning (FL) allows multiple participants to train machine learning models collaboratively by keeping their datasets local while only exchanging model updates. Alas …
Adversarial attacks alter NLP model predictions by perturbing test-time inputs. However, it is much less understood whether, and how, predictions can be manipulated with small …
Property inference attacks consider an adversary who has access to a trained ML model and tries to extract some global statistics of the training data. In this work, we study property …