Cover Image

Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chu, Zhaoyang, Wan, Yao, Zhang, Zhikun, Wang, Di, Yang, Zhou, Zhang, Hongyu, Zhou, Pan, Shi, Xuanhua, Jin, Hai, Lo, David
Format:	Preprint
Published:	2025
Subjects:	Software Engineering Artificial Intelligence Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Mitigating Sensitive Information Leakage in LLMs4Code through Machine Unlearning
by: Gu, Shanzhi, et al.
Published: (2025)

Graph Neural Networks for Vulnerability Detection: A Counterfactual Explanation
by: Chu, Zhaoyang, et al.
Published: (2024)

Gotcha! This Model Uses My Code! Evaluating Membership Leakage Risks in Code Models
by: Yang, Zhou, et al.
Published: (2023)

Backdoors in Code Summarizers: How Bad Is It?
by: Wang, Chenyu, et al.
Published: (2025)

Decoding Secret Memorization in Code LLMs Through Token-Level Characterization
by: Nie, Yuqing, et al.
Published: (2024)

Defending Code Language Models against Backdoor Attacks with Deceptive Cross-Entropy Loss
by: Yang, Guang, et al.
Published: (2024)

Automated TEE Adaptation with LLMs: Identifying, Transforming, and Porting Sensitive Functions in Programs
by: Han, Ruidong, et al.
Published: (2025)

Finding Memory Leaks in C/C++ Programs via Neuro-Symbolic Augmented Static Analysis
by: Huang, Huihui, et al.
Published: (2026)

Out of Distribution, Out of Luck: How Well Can LLMs Trained on Vulnerability Datasets Detect Top 25 CWE Weaknesses?
by: Li, Yikun, et al.
Published: (2025)

How Agentic AI Coding Assistants Become the Attacker's Shell
by: Liu, Yue, et al.
Published: (2026)

Similar but Patched Code Considered Harmful -- The Impact of Similar but Patched Code on Recurring Vulnerability Detection and How to Remove Them
by: Tan, Zixuan, et al.
Published: (2024)

"Your AI, My Shell": Demystifying Prompt Injection Attacks on Agentic AI Coding Editors
by: Liu, Yue, et al.
Published: (2025)

CEBin: A Cost-Effective Framework for Large-Scale Binary Code Similarity Detection
by: Wang, Hao, et al.
Published: (2024)

RepoMark: A Data-Usage Auditing Framework for Code Large Language Models
by: Qu, Wenjie, et al.
Published: (2025)

FDI: Attack Neural Code Generation Systems through User Feedback Channel
by: Sun, Zhensu, et al.
Published: (2024)

SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
by: Hu, Qi, et al.
Published: (2026)

RESCUE: Retrieval Augmented Secure Code Generation
by: Shi, Jiahao, et al.
Published: (2025)

KEENHash: Hashing Programs into Function-Aware Embeddings for Large-Scale Binary Code Similarity Analysis
by: Liu, Zhijie, et al.
Published: (2025)

LLM-Assisted Model-Based Fuzzing of Protocol Implementations
by: Huang, Changze, et al.
Published: (2025)

An Empirical Study on Remote Code Execution in Machine Learning Model Hosting Ecosystems
by: Siddiq, Mohammed Latif, et al.
Published: (2026)

Semantics-Aligned, Curriculum-Driven, and Reasoning-Enhanced Vulnerability Repair Framework
by: Yang, Chengran, et al.
Published: (2025)

KVerus: Scalable and Resilient Formal Verification Proof Generation for Rust Code
by: Liu, Yuwei, et al.
Published: (2026)

PPT4J: Patch Presence Test for Java Binaries
by: Pan, Zhiyuan, et al.
Published: (2023)

Overeager Coding Agents: Measuring Out-of-Scope Actions on Benign Tasks
by: Qu, Yubin, et al.
Published: (2026)

SandCell: Sandboxing Rust Beyond Unsafe Code
by: Zhang, Jialun, et al.
Published: (2025)

Concerned with Data Contamination? Assessing Countermeasures in Code Language Model
by: Cao, Jialun, et al.
Published: (2024)

Beyond Function-Level Analysis: Context-Aware Reasoning for Inter-Procedural Vulnerability Detection
by: Li, Yikun, et al.
Published: (2026)

Transferable Backdoor Attacks for Code Models via Sharpness-Aware Adversarial Perturbation
by: Chang, Shuyu, et al.
Published: (2026)

Demonstration Attack against In-Context Learning for Code Intelligence
by: Ge, Yifei, et al.
Published: (2024)

CKGFuzzer: LLM-Based Fuzz Driver Generation Enhanced By Code Knowledge Graph
by: Xu, Hanxiang, et al.
Published: (2024)

DITING: A Static Analyzer for Identifying Bad Partitioning Issues in TEE Applications
by: Ma, Chengyan, et al.
Published: (2025)

MCGMark: An Encodable and Robust Online Watermark for Tracing LLM-Generated Malicious Code
by: Ning, Kaiwen, et al.
Published: (2024)

D-LiFT: Improving LLM-based Decompiler Backend via Code Quality-driven Fine-tuning
by: Zou, Muqi, et al.
Published: (2025)

Models Are Codes: Towards Measuring Malicious Code Poisoning Attacks on Pre-trained Model Hubs
by: Zhao, Jian, et al.
Published: (2024)

{A New Hope}: Contextual Privacy Policies for Mobile Applications and An Approach Toward Automated Generation
by: Pan, Shidong, et al.
Published: (2024)

CleanVul: Automatic Function-Level Vulnerability Detection in Code Commits Using LLM Heuristics
by: Li, Yikun, et al.
Published: (2024)

Finding Missing Input Validation in TEEs via LLM-Assisted Symbolic Execution
by: Ma, Chengyan, et al.
Published: (2026)

VERCATION: Precise Vulnerable Open-source Software Version Identification based on Static Analysis and LLM
by: Cheng, Yiran, et al.
Published: (2024)

FidelityGPT: Correcting Decompilation Distortions with Retrieval Augmented Generation
by: Zhou, Zhiping, et al.
Published: (2025)

DeCoMa: Detecting and Purifying Code Dataset Watermarks through Dual Channel Code Abstraction
by: Xiao, Yuan, et al.
Published: (2025)