Search Results for author:
Found 8 papers, 4 papers with code
Mitigating Data Poisoning in Text Classification with Differential Privacy
NLP models are vulnerable to data poisoning attacks.
Measuring and Mitigating Name Biases in Neural Machine Translation
In this paper we describe a new source of bias prevalent in NMT systems, relating to translations of sentences containing person names.
IMBERT: Making BERT Immune to Insertion-based Backdoor Attacks
Backdoor attacks are an insidious security threat against machine learning models.
Mitigating Backdoor Poisoning Attacks through the Lens of Spurious Correlation
Modern NLP models are often trained over large untrusted datasets, raising the potential for a malicious adversary to compromise model behaviour.
TRS: Transferability Reduced Ensemble via Encouraging Gradient Diversity and Model Smoothness
To answer these questions, in this work we first theoretically analyze and outline sufficient conditions for adversarial transferability between models; then propose a practical algorithm to reduce the transferability between base models within an ensemble to improve its robustness.
On the Differential Privacy of Bayesian Inference
We study how to communicate findings of Bayesian inference to third parties, while preserving the strong guarantee of differential privacy.
Bayesian Differential Privacy through Posterior Sampling
All our general results hold for arbitrary database metrics, including those for the common definition of differential privacy.
