Cover Image

UCD: Unlearning in LLMs via Contrastive Decoding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Suriyakumar, Vinith M., Sekhari, Ayush, Wilson, Ashia
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Cryptography and Security Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Unstable Unlearning: The Hidden Risk of Concept Resurgence in Diffusion Models
by: Suriyakumar, Vinith M., et al.
Published: (2024)

GaussMark: A Practical Approach for Structural Watermarking of Language Models
by: Block, Adam, et al.
Published: (2025)

Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks
by: Di, Jimmy Z., et al.
Published: (2022)

Machine Unlearning Fails to Remove Data Poisoning Attacks
by: Pawelczyk, Martin, et al.
Published: (2024)

Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs
by: Xu, Xiaoyu, et al.
Published: (2025)

One-shot Empirical Privacy Estimation for Federated Learning
by: Andrew, Galen, et al.
Published: (2023)

SAEs $\textit{Can}$ Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs
by: Muhamed, Aashiq, et al.
Published: (2025)

Layered Unlearning for Adversarial Relearning
by: Qian, Timothy, et al.
Published: (2025)

LLM Unlearning Should Be Form-Independent
by: Ye, Xiaotian, et al.
Published: (2025)

Machine Unlearning Meets Adversarial Robustness via Constrained Interventions on LLMs
by: Rezkellah, Fatmazohra, et al.
Published: (2025)

From Theft to Bomb-Making: The Ripple Effect of Unlearning in Defending Against Jailbreak Attacks
by: Zhang, Zhexin, et al.
Published: (2024)

Textual Unlearning Gives a False Sense of Unlearning
by: Du, Jiacheng, et al.
Published: (2024)

Contrastive Unlearning: A Contrastive Approach to Machine Unlearning
by: Lee, Hong kyu, et al.
Published: (2024)

Unlearned but Not Forgotten: Data Extraction after Exact Unlearning in LLM
by: Wu, Xiaoyu, et al.
Published: (2025)

TwinGate: Stateful Defense against Decompositional Jailbreaks in Untraceable Traffic via Asymmetric Contrastive Learning
by: Sun, Bowen, et al.
Published: (2026)

LLM Ghostbusters: Surgical Hallucination Suppression via Adaptive Unlearning
by: Spracklen, Joseph, et al.
Published: (2026)

UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI
by: Shumailov, Ilia, et al.
Published: (2024)

Adversarial Decoding: Generating Readable Documents for Adversarial Objectives
by: Zhang, Collin, et al.
Published: (2024)

Efficient Federated Unlearning under Plausible Deniability
by: Varshney, Ayush K., et al.
Published: (2024)

Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models
by: Yuan, Hongbang, et al.
Published: (2024)

Evaluation without Generation: Non-Generative Assessment of Harmful Model Specialization with Applications to CSAM
by: Suriyakumar, Vinith M., et al.
Published: (2026)

How Vulnerable Are Edge LLMs?
by: Ding, Ao, et al.
Published: (2026)

An Adversarial Perspective on Machine Unlearning for AI Safety
by: Łucki, Jakub, et al.
Published: (2024)

The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation
by: Xiong, Alexander, et al.
Published: (2025)

Sockpuppetting: Jailbreaking LLMs by Combining Prefilling with Optimization
by: Dotsinski, Asen, et al.
Published: (2026)

Coercing LLMs to do and reveal (almost) anything
by: Geiping, Jonas, et al.
Published: (2024)

Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts
by: Gao, Hongcheng, et al.
Published: (2024)

Multi-Trigger Poisoning Amplifies Backdoor Vulnerabilities in LLMs
by: Sivapiromrat, Sanhanat, et al.
Published: (2025)

Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs
by: Zhao, Xuandong, et al.
Published: (2024)

The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
by: Wallace, Eric, et al.
Published: (2024)

Machine Unlearning of Pre-trained Large Language Models
by: Yao, Jin, et al.
Published: (2024)

Bias Amplification in RAG: Poisoning Knowledge Retrieval to Steer LLMs
by: Wang, Linlin, et al.
Published: (2025)

Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs
by: Mathew, Yohan, et al.
Published: (2024)

Self-Evaluation as a Defense Against Adversarial Attacks on LLMs
by: Brown, Hannah, et al.
Published: (2024)

Future Events as Backdoor Triggers: Investigating Temporal Vulnerabilities in LLMs
by: Price, Sara, et al.
Published: (2024)

Randomized Masked Finetuning: An Efficient Way to Mitigate Memorization of PIIs in LLMs
by: Joshi, Kunj, et al.
Published: (2025)

Can We Infer Confidential Properties of Training Data from LLMs?
by: Huang, Pengrun, et al.
Published: (2025)

Securing Large Language Models (LLMs) from Prompt Injection Attacks
by: Suri, Omar Farooq Khan, et al.
Published: (2025)

LARGO: Latent Adversarial Reflection through Gradient Optimization for Jailbreaking LLMs
by: Li, Ran, et al.
Published: (2025)

Jailbreaking LLMs via Calibration
by: Lu, Yuxuan, et al.
Published: (2026)