OpenAI Blog
Adversarial training methods for semi-supervised text classification
Read the original on OpenAI Blog →The Flow has not summarised this story yet — read it at OpenAI Blog.
Related stories
arXiv AI
Jul 15
Generalized Distribution-Free Semi-Supervised Learning with Risk Rewrite
arXiv:2607. 11947v1 Announce Type: cross Abstract: Typical semi-supervised learning (SSL) methods rely on distributional assumptions, and their performance degrades when these are violated.
arXiv Machine Learning
Jun 3
Position: Adversarial ML for LLMs Is Not Making Any Progress
arXiv:2502. 02260v2 Announce Type: replace Abstract: In the past decade, considerable research effort has been devoted to securing machine learning (ML) models that operate in adversarial settings.
arXiv AI
Jul 3
Population-Based Multi-Objective Training of Discriminators for Semi-Supervised GANs
arXiv:2607. 01907v1 Announce Type: cross Abstract: Semi-supervised generative adversarial networks (SSL-GANs) can exploit large unlabeled datasets while retaining a classifier in the discriminator, but their training is often unstable.
arXiv Machine Learning
Aug 11
Targeted Label-Flipping and Oversampling Attacks on Federated Conditional GANs
arXiv:2608. 09314v1 Announce Type: new Abstract: In a federated learning setup for GANs, several adversarial attacks are possible.
Hugging Face Trending Papers
Aug 10
Targeted Label-Flipping and Oversampling Attacks on Federated Conditional GANs
In a federated learning setup for GANs, several adversarial attacks are possible. One such attack is label flipping, in which malicious clients deliberately alter label information during local training in order to manipulate the global generator.
arXiv Machine Learning
1d ago
Evasion Attacks: How Adversarial Noise Bypasses ML Classifiers
The paper reports a reproducible study of evasion attacks on image and text classifiers. A compact convolutional network on MNIST achieved 98.63% clean accuracy but dropped to 60.20% under FGSM with ε=0.15 and 1.72% with ε=0.30, while PGD reduced accuracy to 32.47% and 0.41%; a bit‑depth‑reduction defense only partially restored performance. In contrast, a DistilBERT model fine‑tuned on the SMS Spam Collection reached 98.75% accuracy and 94.96% F1‑score, yet a sequence of predefined perturbations produced only modest probability shifts and did not flip spam to ham predictions.