Cover Image

On the Hidden Costs of Counterfactual Knowledge Training in LLM Unlearning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ye, Xiaotian, Wang, Xiaohan, Zhang, Mengqi, Wu, Shu
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

When Machine Unlearning Meets Retrieval-Augmented Generation (RAG): Keep Secret or Forget Knowledge?
by: Wang, Shang, et al.
Published: (2024)

Counterfactual Evaluation for Blind Attack Detection in LLM-based Evaluation Systems
by: Liu, Lijia, et al.
Published: (2025)

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

SafeReview: Defending LLM-based Review Systems Against Adversarial Hidden Prompts
by: Xin, Yuan, et al.
Published: (2026)

Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation
by: Zhao, Shuai, et al.
Published: (2024)

Hidden Data Privacy Breaches in Federated Learning
by: Gong, Xueluan, et al.
Published: (2024)

SRTJ: Self-Evolving Rule-Driven Training-Free LLM Jailbreaking
by: Li, Jindong, et al.
Published: (2026)

From Domains to Instances: Dual-Granularity Data Synthesis for LLM Unlearning
by: Xu, Xiaoyu, et al.
Published: (2026)

Large Language Models as Carriers of Hidden Messages
by: Hoscilowicz, Jakub, et al.
Published: (2024)

LLM-based Privacy Data Augmentation Guided by Knowledge Distillation with a Distribution Tutor for Medical Text Classification
by: Song, Yiping, et al.
Published: (2024)

The Hidden Cost of Modeling P(X): Vulnerability to Membership Inference Attacks in Generative Text Classifiers
by: Makroo, Owais, et al.
Published: (2025)

LibVulnWatch: A Deep Assessment Agent System and Leaderboard for Uncovering Hidden Vulnerabilities in Open-Source AI Libraries
by: Wu, Zekun, et al.
Published: (2025)

Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy
by: Ren, Jie, et al.
Published: (2025)

Federated TrustChain: Blockchain-Enhanced LLM Training and Unlearning
by: Zuo, Xuhan, et al.
Published: (2024)

Sugar-Coated Poison: Benign Generation Unlocks LLM Jailbreaking
by: Wu, Yu-Hang, et al.
Published: (2025)

GuidedBench: Measuring and Mitigating the Evaluation Discrepancies of In-the-wild LLM Jailbreak Methods
by: Huang, Ruixuan, et al.
Published: (2025)

Model-Agnostic Lifelong LLM Safety via Externalized Attack-Defense Co-Evolution
by: Zhang, Xiaozhe, et al.
Published: (2026)

Textual Unlearning Gives a False Sense of Unlearning
by: Du, Jiacheng, 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)

Security Attacks on LLM-based Code Completion Tools
by: Cheng, Wen, et al.
Published: (2024)

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

LexiMark: Robust Watermarking via Lexical Substitutions to Enhance Membership Verification of an LLM's Textual Training Data
by: German, Eyal, et al.
Published: (2025)

AdvAgent: Controllable Blackbox Red-teaming on Web Agents
by: Xu, Chejian, et al.
Published: (2024)

The Landscape of Prompt Injection Threats in LLM Agents: From Taxonomy to Analysis
by: Wang, Peiran, et al.
Published: (2026)

Can LLM Infer Risk Information From MCP Server System Logs?
by: Fu, Jiayi, et al.
Published: (2025)

Self-Disguise Attack: Induce the LLM to disguise itself for AIGT detection evasion
by: Zhou, Yinghan, et al.
Published: (2025)

A Framework for Cost-Effective and Self-Adaptive LLM Shaking and Recovery Mechanism
by: Chen, Zhiyu, et al.
Published: (2024)

Interpretable LLM Guardrails via Sparse Representation Steering
by: He, Zeqing, et al.
Published: (2025)

LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments
by: Zhang, Chiyu, et al.
Published: (2026)

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface
by: Labunets, Andrey, et al.
Published: (2025)

Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
by: Yang, Wenkai, et al.
Published: (2024)

GraphSteal: Structural Knowledge Stealing from Graph RAG via Traversal Reconstruction
by: Gu, Jinze, et al.
Published: (2026)

How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States
by: Zhou, Zhenhong, et al.
Published: (2024)

Invisible Entropy: Towards Safe and Efficient Low-Entropy LLM Watermarking
by: Gu, Tianle, et al.
Published: (2025)

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

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

AttnTrace: Contextual Attribution of Prompt Injection and Knowledge Corruption
by: Wang, Yanting, et al.
Published: (2025)

PersonaMark: Personalized LLM watermarking for model protection and user attribution
by: Zhang, Yuehan, et al.
Published: (2024)

Watermarking LLM Agent Trajectories
by: Meng, Wenlong, et al.
Published: (2026)