Native Robustness

Native robustness in machine learning focuses on developing models inherently resistant to various forms of input perturbations, including adversarial attacks and noisy data, without relying solely on post-hoc defenses. Current research emphasizes techniques like ensemble methods, reprogramming existing models, and modifying training procedures (e.g., using different learning rates for specific model layers or incorporating regularization methods) to improve robustness across diverse model architectures, including convolutional neural networks, vision transformers, and large language models. This field is crucial for deploying reliable AI systems in safety-critical applications, such as healthcare and autonomous driving, where model resilience to unexpected inputs is paramount.

Papers

September 19, 2024

The Robustness of Spiking Neural Networks in Communication and its Application towards Network Efficiency in Federated Learning
Manh V. Nguyen, Liang Zhao, Bobin Deng, William Severa, Honghui Xu, Shaoen Wu
Neural Network Native Robustness Federated Learning Spiking Neural Network Timely Communication Chip Learning Efficient Network

September 18, 2024

A constrained optimization approach to improve robustness of neural networks
Shudian Zhao, Jan Kronqvist
Neural Network Adversarial Attack Native Robustness Fine Tuning Constrained Optimization Nonconvex Optimization Adversarial Data

September 17, 2024

September 14, 2024

Improving Robustness of Diffusion-Based Zero-Shot Speech Synthesis via Stable Formant Generation
Changjin Han, Seokgi Lee, Gyuhyeon Nam, Gyeongsu Chae
Native Robustness Zero Shot Speech Synthesis Diffusion Based Text Formant Frequency

September 11, 2024

September 7, 2024

Top-GAP: Integrating Size Priors in CNNs for more Interpretability, Robustness, and Bias Mitigation
Lars Nieradzik, Henrike Stephani, Janis Keuper
Convolutional Neural Network Native Robustness Inherent Interpretability CNN Model Bias Mitigation Object Localization Filling Gap Shape Prior Salient Region

September 5, 2024

September 4, 2024

Boosting Certified Robustness for Time Series Classification with Efficient Self-Ensemble
Chang Dong, Zhengyang Li, Liangwei Zheng, Weitong Chen, Wei Emma Zhang
Native Robustness Adversarial Robustness Time Series Classification Randomized Smoothing Robustness Certificate Robustness Radius Self Ensemble \Ell_p$ Robustness

September 3, 2024

Improving Robustness of Spectrogram Classifiers with Neural Stochastic Differential Equations
Joel Brogan, Olivera Kotevska, Anibely Torres, Sumit Jha, Mark Adams
Native Robustness Deep Learning Model Signal Processing Spectrogram Based Signal Classification Neural Stochastic Differential Equation Signal Identification

September 2, 2024

September 1, 2024

Enabling Trustworthy Federated Learning in Industrial IoT: Bridging the Gap Between Interpretability and Robustness
Senthil Kumar Jagatheesaperumal, Mohamed Rahouti, Ali Alfatemi, Nasir Ghani, Vu Khanh Quy, Abdellah Chehri
Native Robustness Federated Learning Inherent Interpretability Industrial Internet of Thing Industrial Internet

August 29, 2024

PromptSmooth: Certifying Robustness of Medical Vision-Language Models via Prompt Learning
Noor Hussein, Fahad Shamshad, Muzammal Naseer, Karthik Nandakumar
Native Robustness Vision Language Model Prompt Learning Medical Image Analysis Image Text Prompt Space

August 27, 2024

August 26, 2024

MEDSAGE: Enhancing Robustness of Medical Dialogue Summarization to ASR Errors with LLM-generated Synthetic Dialogues
Kuluhan Binici, Abhinav Ramesh Kashyap, Viktor Schlegel, Andy T. Liu, Vijay Prakash Dwivedi, Thanh-Tung Nguyen, Xiaoxue Gao, Nancy F. Chen, Stefan Winkler
Native Robustness Automatic Speech Recognition Medical Dialogue Automatic Speech Recognition Error Medical Dialogue Summarization

Native Robustness

Papers

The Robustness of Spiking Neural Networks in Communication and its Application towards Network Efficiency in Federated Learning

A constrained optimization approach to improve robustness of neural networks

Contextual Breach: Assessing the Robustness of Transformer-based QA Models

Evaluating and Improving the Robustness of LiDAR-based Localization and Mapping

Improving Robustness of Diffusion-Based Zero-Shot Speech Synthesis via Stable Formant Generation

A Cost-Aware Approach to Adversarial Robustness in Neural Networks

Introducing Perturb-ability Score (PS) to Enhance Robustness Against Evasion Adversarial Attacks on ML-NIDS

Top-GAP: Integrating Size Priors in CNNs for more Interpretability, Robustness, and Bias Mitigation

A Deep Generative Learning Approach for Two-stage Adaptive Robust Optimization

DART2: a robust multiple testing method to smartly leverage helpful or misleading ancillary information

Improving Robustness to Multiple Spurious Correlations by Multi-Objective Optimization

Boosting Certified Robustness for Time Series Classification with Efficient Self-Ensemble

Improving Robustness of Spectrogram Classifiers with Neural Stochastic Differential Equations

Adversarial Pruning: A Survey and Benchmark of Pruning Methods for Adversarial Robustness

Bootstrap SGD: Algorithmic Stability and Robustness

Enabling Trustworthy Federated Learning in Industrial IoT: Bridging the Gap Between Interpretability and Robustness

PromptSmooth: Certifying Robustness of Medical Vision-Language Models via Prompt Learning

No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery

CoopASD: Cooperative Machine Anomalous Sound Detection with Privacy Concerns

MEDSAGE: Enhancing Robustness of Medical Dialogue Summarization to ASR Errors with LLM-generated Synthetic Dialogues