Cover Image

GRP-Obliteration: Unaligning LLMs With a Single Unlabeled Prompt

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Russinovich, Mark, Cai, Yanan, Hines, Keegan, Severi, Giorgio, Bullwinkel, Blake, Salem, Ahmed
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Obliviate: Efficient Unmemorization for Protecting Intellectual Property in Large Language Models
by: Russinovich, Mark, et al.
Published: (2025)

A Representation Engineering Perspective on the Effectiveness of Multi-Turn Jailbreaks
by: Bullwinkel, Blake, et al.
Published: (2025)

LogiPlan: A Structured Benchmark for Logical Planning and Relational Reasoning in LLMs
by: Cai, Yanan, et al.
Published: (2025)

The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggers
by: Bullwinkel, Blake, et al.
Published: (2026)

Jailbreaking is (Mostly) Simpler Than You Think
by: Russinovich, Mark, et al.
Published: (2025)

Hey, That's My Model! Introducing Chain & Hash, An LLM Fingerprinting Technique
by: Russinovich, Mark, et al.
Published: (2024)

Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack
by: Russinovich, Mark, et al.
Published: (2024)

Stateless Yet Not Forgetful: Implicit Memory as a Hidden Channel in LLMs
by: Salem, Ahmed, et al.
Published: (2026)

Are My Optimized Prompts Compromised? Exploring Vulnerabilities of LLM-based Optimizers
by: Zhao, Andrew, et al.
Published: (2025)

Realizing Unaligned Block-wise Pruning for DNN Acceleration on Mobile Devices
by: Lee, Hayun, et al.
Published: (2024)

Deep Positive-Unlabeled Anomaly Detection for Contaminated Unlabeled Data
by: Takahashi, Hiroshi, et al.
Published: (2024)

Understanding the Effects of Safety Unalignment on Large Language Models
by: Halloran, John T.
Published: (2026)

Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization
by: Razin, Noam, et al.
Published: (2024)

Content-Style Learning from Unaligned Domains: Identifiability under Unknown Latent Dimensions
by: Shrestha, Sagar, et al.
Published: (2024)

GED-Consistent Disentanglement of Aligned and Unaligned Substructures for Graph Similarity Learning
by: Zhan, Zhentao, et al.
Published: (2025)

Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data
by: Guo, Wei, et al.
Published: (2025)

Positive Unlabeled Contrastive Learning
by: Acharya, Anish, et al.
Published: (2022)

Collaborative Unlabeled Data Optimization
by: Shang, Xinyi, et al.
Published: (2025)

Augmenting Offline RL with Unlabeled Data
by: Wang, Zhao, et al.
Published: (2024)

Incorporating Unlabelled Data into Bayesian Neural Networks
by: Sharma, Mrinank, et al.
Published: (2023)

Angular Regularization for Positive-Unlabeled Learning on the Hypersphere
by: Sevetlidis, Vasileios, et al.
Published: (2025)

Can ChatGPT Learn My Life From a Week of First-Person Video?
by: Harris, Keegan
Published: (2025)

Inconsistency-Aware Minimization: Improving Generalization with Unlabeled Data
by: Kim, Hee-Sung, et al.
Published: (2026)

Noisy-Pair Robust Representation Alignment for Positive-Unlabeled Learning
by: Zhao, Hengwei, et al.
Published: (2025)

Learning from M-Tuple Dominant Positive and Unlabeled Data
by: Qin, Jiahe, et al.
Published: (2025)

Positive-Unlabeled Diffusion Models for Preventing Sensitive Data Generation
by: Takahashi, Hiroshi, et al.
Published: (2025)

Time-Prompt: Integrated Heterogeneous Prompts for Unlocking LLMs in Time Series Forecasting
by: Wang, Zesen, et al.
Published: (2025)

CAP: Controllable Alignment Prompting for Unlearning in LLMs
by: Wang, Zhaokun, et al.
Published: (2026)

Should You Use Your Large Language Model to Explore or Exploit?
by: Harris, Keegan, et al.
Published: (2025)

Tabular Data Adapters: Improving Outlier Detection for Unlabeled Private Data
by: Herurkar, Dayananda, et al.
Published: (2025)

Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration
by: Wilcoxson, Max, et al.
Published: (2024)

AllMatch: Exploiting All Unlabeled Data for Semi-Supervised Learning
by: Wu, Zhiyu, et al.
Published: (2024)

Candidate Pseudolabel Learning: Enhancing Vision-Language Models by Prompt Tuning with Unlabeled Data
by: Zhang, Jiahan, et al.
Published: (2024)

Evolutionary System Prompt Learning for Reinforcement Learning in LLMs
by: Zhang, Lunjun, et al.
Published: (2026)

Red-teaming Activation Probes using Prompted LLMs
by: Blandfort, Phil, et al.
Published: (2025)

Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights
by: Liang, Zhiyuan, et al.
Published: (2025)

Dark LLMs: The Growing Threat of Unaligned AI Models
by: Fire, Michael, et al.
Published: (2025)

Resilient Class-Incremental Learning: on the Interplay of Drifting, Unlabelled and Imbalanced Data Streams
by: Li, Jin, et al.
Published: (2026)

Integrating Distribution Matching into Semi-Supervised Contrastive Learning for Labeled and Unlabeled Data
by: Nakayama, Shogo, et al.
Published: (2026)

Cost-Sensitive Unbiased Risk Estimation for Multi-Class Positive-Unlabeled Learning
by: Zhang, Miao, et al.
Published: (2025)