On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “reprogramming”

Adversarial Reprogramming of Text Classification Neural Networkscs.LG

Adversaries reprogram text classification models without changing the original network.

problem Reprogramming neural networks trained on discrete input spaces like text classification.

method Context-based vocabulary remapping model for white-box and black-box settings.

result Successfully repurposed various text-classification models for new tasks.

Adversarial Reprogramming Text Classification Neural Networks Discrete Input Space Vocabulary Remapping

2018-09-06abs ↗pdf ↗

Robustness Reprogramming for Representation Learningcs.LG

Reprogram deep models to resist adversarial attacks without changing parameters.

problem Improving deep learning models' robustness against adversarial and noisy inputs.

method Proposes a non-linear robust pattern matching technique and three reprogramming paradigms.

result Demonstrates effective reprogramming of deep models for robustness without altering parameters.

representation learning deep learning adversarial robustness model reprogramming robust pattern matching

2024-10-06abs ↗pdf ↗

Adversarial Reprogramming of Neural Networkscs.LG

New attacks reprogram neural networks to perform new tasks.

problem Neural networks are vulnerable to adversarial attacks that can cause mistakes or specific outputs.

method Develops attacks that reprogram models to perform tasks chosen by the attacker, without specifying outputs.

result Demonstrates reprogramming on six models, including counting and classification tasks.

adversarial attacks neural networks reprogramming machine learning image recognition

2018-06-28abs ↗pdf ↗

Transfer Learning without Knowing: Reprogramming Black-box Machine Learning Models with Scarce Data and Limited Resourcescs.CV

BAR reprograms black-box ML models for transfer learning with scarce data.

problem Transfer learning with limited data and resources.

method Zeroth-order optimization and multi-label mapping techniques to reprogram black-box models.

result BAR outperforms state-of-the-art methods and baseline transfer learning approaches.

transfer learning black-box models scarce data limited resources autism spectrum disorder

2020-07-17abs ↗pdf ↗

Protecting Neural Networks with Hierarchical Random Switching: Towards Better Robustness-Accuracy Trade-off for Stochastic Defensescs.LG

Paper proposes HRS to improve neural network robustness without significant accuracy loss.

problem Vulnerability of neural networks to adversarial attacks and performance degradation.

method Hierarchical Random Switching (HRS) for robustness without sacrificing accuracy.

result HRS significantly improves adversarial robustness with minimal accuracy loss.

neural networks adversarial attacks stochastic defenses robustness accuracy trade-off

2019-08-20abs ↗pdf ↗

Meta Learning Backpropagation And Improving Itcs.LG

VSML unifies meta learning concepts and enables simple backpropagation.

problem Improving and unifying meta learning concepts for neural networks.

method Unified approach using variable shared meta learning and simple weight-sharing.

result Simple backpropagation can be implemented and meta learned without gradient calculation.

meta learning backpropagation neural networks variable sharing meta recurrent NNs

2020-12-29abs ↗pdf ↗