NeurIPS 2025 Workshop Reliable ML Submissions

Not All Samples Are Equal: Quantifying Instance-level Difficulty in Targeted Data Poisoning
William Xu, Yiwei Lu, Yihan Wang, Matthew Y. R. Yang, Zuoqiu Liu, Gautam Kamath, Yaoliang Yu
- Published: 29 Sept 2025, Last Modified: 22 Oct 2025
- NeurIPS 2025 - Reliable ML Workshop
- Readers: Everyone
BridgePure: Limited Protection Leakage Can Break Black-Box Data Protection
Yihan Wang, Yiwei Lu, Xiao-Shan Gao, Gautam Kamath, Yaoliang Yu
- Published: 29 Sept 2025, Last Modified: 22 Oct 2025
- NeurIPS 2025 - Reliable ML Workshop
- Readers: Everyone
From Semantics to Symbols: A Two-Stage Framework for Deconstructing LLM Reasoning into Concepts and Rules
Yanchen Yin
- Published: 29 Sept 2025, Last Modified: 12 Oct 2025
- NeurIPS 2025 - Reliable ML Workshop
- Readers: Everyone
Certified Adversarial Robustness via Mixture-of-Gaussians Randomized Smoothing
Vaughn Rostermundt, Brendon G. Anderson
- Published: 29 Sept 2025, Last Modified: 24 Oct 2025
- NeurIPS 2025 - Reliable ML Workshop
- Readers: Everyone
Is Safety Standard Same for Everyone? User-Specific Safety Evaluation of Large Language Models
Yeonjun In, Wonjoong Kim, Kanghoon Yoon, Sungchul Kim, Mehrab Tanjim, Sangwu Park, Kibum Kim, Chanyoung Park
- Published: 29 Sept 2025, Last Modified: 12 Oct 2025
- NeurIPS 2025 - Reliable ML Workshop
- Readers: Everyone
Adaptive Norm Selection Prevents Catastrophic Overfitting in Fast Adversarial Training
Fares B. Mehouachi, Saif Jabari
- Published: 29 Sept 2025, Last Modified: 24 Oct 2025
- NeurIPS 2025 - Reliable ML Workshop
- Readers: Everyone
Robust Federated Learning under Heterogeneous Data with Generalized Heavy-Ball Momentum
Riccardo Zaccone, Sai Praneeth Karimireddy, Carlo Masone, Marco Ciccone
- Published: 29 Sept 2025, Last Modified: 13 Oct 2025
- NeurIPS 2025 - Reliable ML Workshop
- Readers: Everyone
The Impact of Training Data on Adversarial Robustness
Marco Zimmerli, Andreas Plesner, Till Aczel, Roger Wattenhofer
- Published: 29 Sept 2025, Last Modified: 15 Oct 2025
- NeurIPS 2025 - Reliable ML Workshop
- Readers: Everyone
Keep It Real: Challenges in Attacking Compression-Based Adversarial Purification
Samuel Räber, Till Aczel, Andreas Plesner, Roger Wattenhofer
- Published: 29 Sept 2025, Last Modified: 15 Oct 2025
- NeurIPS 2025 - Reliable ML Workshop
- Readers: Everyone
Reliable Unlearning Harmful Information in LLMs with Metamorphosis Representation Projection
Chengcan Wu, Zeming Wei, Huanran Chen, Yinpeng Dong, Meng Sun
- Published: 29 Sept 2025, Last Modified: 12 Oct 2025
- NeurIPS 2025 - Reliable ML Workshop
- Readers: Everyone
Data Decomposition beyond Splitting for Causal Estimation
Xuelin Yang, Dhruv Singal, Rina Friedberg, Niloy Biswas
- Published: 29 Sept 2025, Last Modified: 29 Oct 2025
- NeurIPS 2025 - Reliable ML Workshop
- Readers: Everyone
Towards Context-Aware Domain Generalization: Understanding the Benefits and Limits of Marginal Transfer Learning
Jens Müller, Lars Kühmichel, Martin Rohbeck, Stefan T. Radev, Ullrich Koethe
- Published: 29 Sept 2025, Last Modified: 22 Oct 2025
- NeurIPS 2025 - Reliable ML Workshop
- Readers: Everyone
Don’t Make It Up: Preserving Ignorance Awareness in LLM Fine-Tuning
William F. Shen, Xinchi Qiu, Nicola Cancedda, Nicholas D. Lane
- Published: 29 Sept 2025, Last Modified: 12 Oct 2025
- NeurIPS 2025 - Reliable ML Workshop
- Readers: Everyone
Text‑Guided Data Attribution: Attributing the Influence of Simplicity Bias to Dataset
Kumar Shubham, Pranav Sastry, Prathosh AP
- Published: 29 Sept 2025, Last Modified: 12 Oct 2025
- NeurIPS 2025 - Reliable ML Workshop
- Readers: Everyone
Regularized Robustly Reliable Learners and Instance Targeted Attacks
Avrim Blum, Donya Saless
- Published: 29 Sept 2025, Last Modified: 12 Oct 2025
- NeurIPS 2025 - Reliable ML Workshop
- Readers: Everyone
Why is Your Language Model a Poor Implicit Reward Model?
Noam Razin, Yong Lin, Jiarui Yao, Sanjeev Arora
- Published: 29 Sept 2025, Last Modified: 12 Oct 2025
- NeurIPS 2025 - Reliable ML Workshop
- Readers: Everyone
Efficiently Robust In-Context Reinforcement Learning with Adversarial Generalization and Adaptation
Juncheng Dong, Hao-Lun Hsu, Miroslav Pajic, Vahid Tarokh
- Published: 29 Sept 2025, Last Modified: 24 Oct 2025
- NeurIPS 2025 - Reliable ML Workshop
- Readers: Everyone
Concept-Based Masking: A Patch-Agnostic Defense Against Adversarial Patch Attacks
Ayushi Mehrotra, Derek Peng, Dipkamal Bhusal, Nidhi Rastogi
- Published: 29 Sept 2025, Last Modified: 15 Oct 2025
- NeurIPS 2025 - Reliable ML Workshop
- Readers: Everyone
AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin
Shuo Yang, Qihui Zhang, Yuyang Liu, Yue Huang, Xiaojun Jia, Kun-Peng Ning, Jia-Yu Yao, jigang wang, Dai Hailiang, Yibing Song, Li Yuan
- Published: 29 Sept 2025, Last Modified: 12 Oct 2025
- NeurIPS 2025 - Reliable ML Workshop
- Readers: Everyone
Generalizing Robustness from $\ell_p$ to Unforeseen Attack via Calibrated Adversarial Sampling
Rui Wang, Zeming Wei, Xiyue Zhang, Meng Sun
- Published: 29 Sept 2025, Last Modified: 12 Oct 2025
- NeurIPS 2025 - Reliable ML Workshop
- Readers: Everyone
ERGO: Entropy-guided Resetting for Generation Optimization in Multi-turn Language Models
Haziq Mohammad Khalid, Athikash Jeyaganthan, Timothy Do, Yicheng Fu, Vasu Sharma, Sean O'Brien, Kevin Zhu
- Published: 29 Sept 2025, Last Modified: 12 Oct 2025
- NeurIPS 2025 - Reliable ML Workshop
- Readers: Everyone
Clean-Label Physical Backdoor Attacks with Data Distillation
Thinh Dao, Khoa D Doan, Kok-Seng Wong
- Published: 29 Sept 2025, Last Modified: 12 Oct 2025
- NeurIPS 2025 - Reliable ML Workshop
- Readers: Everyone
Cost Efficient Fairness Audit Under Partial Feedback
Nirjhar Das, Mohit Sharma, Praharsh Nanavati, Kirankumar Shiragur, Amit Deshpande
- Published: 29 Sept 2025, Last Modified: 17 Oct 2025
- NeurIPS 2025 - Reliable ML Workshop
- Readers: Everyone
Unlocking Transfer Learning for Open-World Few-Shot Recognition
Byeonggeun Kim, Juntae Lee, Kyuhong Shim, Simyung Chang
- Published: 29 Sept 2025, Last Modified: 13 Oct 2025
- NeurIPS 2025 - Reliable ML Workshop
- Readers: Everyone