Entity · benchmark
MNIST
benchmarkactive
mnist-b117d755·6 events·first seen Aliases: MNIST
Co-occurring entities
NeuronSoupResNet-18Q-DIBAInput-Aware Dynamic Backdoor Attack Against Quantum Neural NetworksFashion-MNISTNational Institute of Standards and TechnologyAI Risk Management FrameworkAnthropicHugging Faceadversarial traininghuman uncertainty alignmentmodel calibrationdataset cartographysoft-label learningCIFAR-10Random CodingFlow MatchingWatermarking
More like this (12)
Recent events (6)
NeuronSoup: Asynchronous shared-neuron temporal graph architecture evolved without backpropagation
NeuronSoup is a neural computation architecture that replaces synchronous layer-by-layer processing with asynchronous, delay-mediated signal propagation through a pool of physically shared neurons, optimized entirely by a genetic algorithm rather than gradient descent. On MNIST digit classification using frozen ResNet18 features, the evolved network achieves 85.9% test accuracy with 204 active paths through 266 hidden neurons, fitting in 115 KB. The architecture requires no differentiable computation graph, adapts computation depth per sample, and discovers lateral pathway interactions without explicit engineering. The authors argue genetic algorithms are the appropriate optimizer for this problem class and discuss why CMA-ES fails at this scale.
Q-DIBA: First input-aware dynamic backdoor attack against Quantum Neural Networks
Researchers introduce Q-DIBA, the first input-aware dynamic backdoor attack targeting Quantum Neural Networks (QNNs), addressing limitations of prior fixed-trigger quantum backdoor methods. The approach jointly trains a classical trigger generator and a victim QNN using a three-mode mini-batch strategy and an ensemble density contrastive loss operating on post-ansatz quantum states before measurement. Experiments on MNIST and Fashion-MNIST demonstrate high attack success rates, stealthiness, and resilience against defenses including spectral-signature detection and fine-tuning. The work highlights a novel security threat relevant to near-term quantum machine learning deployments.
Anthropic proposes ambitious federal funding increase for NIST AI measurement and standards
Anthropic published a policy proposal in April 2023 calling for a significant increase in federal funding for the National Institute of Standards and Technology (NIST) to support AI measurement, evaluation, and standards work. The post argues that rigorous AI capability and risk measurement is a prerequisite for effective regulation, and outlines a concrete funding program building on NIST's existing AI Risk Management Framework and related work. Anthropic frames this as a 'shovel-ready' complement to broader AI governance proposals, recommending at minimum a $15 million increase over FY2023 levels.
How to Train Your Model Dynamically Using Adversarial Data
This Hugging Face blog post describes a methodology for dynamically training models using adversarial data, likely in the context of improving robustness against adversarial examples. The post covers techniques for generating and incorporating adversarial inputs during the training loop to improve model resilience. Published in mid-2022, it targets practitioners looking to harden ML models against distribution shift and adversarial attacks.
Controlled Audit of Human vs. Synthetic Soft-Labels for Calibration and Uncertainty Alignment
This paper presents a controlled study disentangling the effects of human soft-labels from label mode-shift corrections in soft-label learning, using MNIST and a synthetic variant. The authors find that human soft-labels primarily act as a regularizer improving calibration on difficult samples and promoting stable training convergence, rather than simply correcting mislabeled data. Dataset cartography analysis shows models trained on human soft-labels mirror human uncertainty patterns, while those trained on synthetic labels fail to align. The work provides a diagnostic testbed for evaluating human-AI uncertainty alignment.
Dynamics-Level Watermarking of Flow Matching Models with Random Codes
This paper proposes embedding watermarks directly into the velocity field (continuous dynamics) of flow matching generative models, rather than into weights or outputs. The method uses key-dependent perturbations added during training, formulated as random coding over a continuous channel, allowing black-box message recovery at detection time. The perturbation is designed to leave the generated distribution unchanged. Experiments on MNIST and CIFAR-10 demonstrate reliable message recovery, preserved generation quality, and chance-level decoding without the secret key.