Cover Image

Fragile Giants: Understanding the Susceptibility of Models to Subpopulation Attacks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Gupta, Isha, Lycklama, Hidde, Opel, Emanuel, Rose, Evan, Hithnawi, Anwar
Format:	Preprint
Published:	2024
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

UTrace: Poisoning Forensics for Private Collaborative Learning
by: Rose, Evan, et al.
Published: (2024)

DPolicy: Managing Privacy Risks Across Multiple Releases with Differential Privacy
by: Küchler, Nicolas, et al.
Published: (2025)

Artemis: Efficient Commit-and-Prove SNARKs for zkML
by: Lycklama, Hidde, et al.
Published: (2024)

Holding Secrets Accountable: Auditing Privacy-Preserving Machine Learning
by: Lycklama, Hidde, et al.
Published: (2024)

Understanding Adversarial Transfer: Why Representation-Space Attacks Fail Where Data-Space Attacks Succeed
by: Gupta, Isha, et al.
Published: (2025)

Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks
by: Poppi, Samuele, et al.
Published: (2024)

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models
by: Gupta, Isha, et al.
Published: (2025)

Evaluating Model Performance Under Worst-case Subpopulations
by: Li, Mike, et al.
Published: (2024)

Enhancing Retail Sales Forecasting with Optimized Machine Learning Models
by: Ganguly, Priyam, et al.
Published: (2024)

Subpopulation-Specific Synthetic EHR for Better Mortality Prediction
by: Perets, Oriel, et al.
Published: (2023)

Selection of the Best Policy under Fairness Constraints for Subpopulations
by: Zhu, Tingyu, et al.
Published: (2026)

Fragility-aware Classification for Understanding Risk and Improving Generalization
by: Yang, Chen, et al.
Published: (2025)

Learning With Multi-Group Guarantees For Clusterable Subpopulations
by: Dai, Jessica, et al.
Published: (2024)

Conformal Prediction Adaptive to Unknown Subpopulation Shifts
by: Wang, Nien-Shao, et al.
Published: (2025)

Sample-efficient Learning of Concepts with Theoretical Guarantees: from Data to Concepts without Interventions
by: Fokkema, Hidde, et al.
Published: (2025)

Clustered Calibration: Representation-Aware Probability Calibration via Learned Subpopulations
by: Lavi, Tomer, et al.
Published: (2025)

Unsupervised Domain Adaptation for Binary Classification with an Unobservable Source Subpopulation
by: Ying, Chao, et al.
Published: (2025)

Visualizing Machine Learning Models for Enhanced Financial Decision-Making and Risk Management
by: Ganguly, Priyam, et al.
Published: (2025)

Robustness to Subpopulation Shift with Domain Label Noise via Regularized Annotation of Domains
by: Stromberg, Nathan, et al.
Published: (2024)

Novel Node Category Detection Under Subpopulation Shift
by: Chung, Hsing-Huan, et al.
Published: (2024)

Assessing Generalization for Subpopulation Representative Modeling via In-Context Learning
by: Simmons, Gabriel, et al.
Published: (2024)

Can LLMs Understand Time Series Anomalies?
by: Zhou, Zihao, et al.
Published: (2024)

FragileFlow: Spectral Control of Correct-but-Fragile Predictions for Foundation Model Robustness
by: Li, Zhuoyun, et al.
Published: (2026)

Bypassing the Safety Training of Open-Source LLMs with Priming Attacks
by: Vega, Jason, et al.
Published: (2023)

Contrast Sets for Evaluating Language-Guided Robot Policies
by: Anwar, Abrar, et al.
Published: (2024)

The Risks of Recourse in Binary Classification
by: Fokkema, Hidde, et al.
Published: (2023)

Understanding Model Ensemble in Transferable Adversarial Attack
by: Yao, Wei, et al.
Published: (2024)

Model Privacy: A Unified Framework for Understanding Model Stealing Attacks and Defenses
by: Wang, Ganghua, et al.
Published: (2025)

Policy-Oriented Binary Classification: Improving (KD-)CART Final Splits for Subpopulation Targeting
by: Wang, Lei Bill, et al.
Published: (2025)

Mind the GAP: Improving Robustness to Subpopulation Shifts with Group-Aware Priors
by: Rudner, Tim G. J., et al.
Published: (2024)

TOFU: Towards Obfuscated Federated Updates by Encoding Weight Updates into Gradients from Proxy Data
by: Garg, Isha, et al.
Published: (2022)

Understanding In-Context Learning of Linear Models in Transformers Through an Adversarial Lens
by: Anwar, Usman, et al.
Published: (2024)

Verification of Machine Unlearning is Fragile
by: Zhang, Binchi, et al.
Published: (2024)

The Fragility of Optimized Bandit Algorithms
by: Fan, Lin, et al.
Published: (2021)

Diverse Prototypical Ensembles Improve Robustness to Subpopulation Shift
by: To, Minh Nguyen Nhat, et al.
Published: (2025)

On The Fragility of Benchmark Contamination Detection in Reasoning Models
by: Wang, Han, et al.
Published: (2025)

Open-Weight LLM Fine-Tuning Defenses are Susceptible to Simple Attacks
by: Kuo, Kevin, et al.
Published: (2026)

Certifying Counterfactual Bias in LLMs
by: Chaudhary, Isha, et al.
Published: (2024)

Curriculum-enhanced GroupDRO: Challenging the Norm of Avoiding Curriculum Learning in Subpopulation Shift Setups
by: Barbalau, Antonio
Published: (2024)

Understanding Mode Connectivity via Parameter Space Symmetry
by: Zhao, Bo, et al.
Published: (2025)