CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yi, Biao, Huang, Tiansheng, Zhang, Baolei, Li, Tong, Nie, Lihai, Liu, Zheli, Shen, Li
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models
by: Yi, Biao, et al.
Published: (2025)

BadActs: A Universal Backdoor Defense in the Activation Space
by: Yi, Biao, et al.
Published: (2024)

Gradient Surgery for Safe LLM Fine-Tuning
by: Yi, Biao, et al.
Published: (2025)

Who Taught the Lie? Responsibility Attribution for Poisoned Knowledge in Retrieval-Augmented Generation
by: Zhang, Baolei, et al.
Published: (2025)

Hiding in Plain Sight: A Steganographic Approach to Stealthy LLM Jailbreaks
by: Geng, Jianing, et al.
Published: (2025)

Practical Poisoning Attacks against Retrieval-Augmented Generation
by: Zhang, Baolei, et al.
Published: (2025)

Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation
by: Huang, Tiansheng, et al.
Published: (2025)

Your Semantic-Independent Watermark is Fragile: A Semantic Perturbation Attack against EaaS Watermark
by: Fei, Zekun, et al.
Published: (2024)

Eliciting Harmful Capabilities by Fine-Tuning On Safeguarded Outputs
by: Kaunismaa, Jackson, et al.
Published: (2026)

Pharmacist: Safety Alignment Data Curation for Large Language Models against Harmful Fine-tuning
by: Liu, Guozhi, et al.
Published: (2025)

Benchmarking Poisoning Attacks against Retrieval-Augmented Generation
by: Zhang, Baolei, et al.
Published: (2025)

Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning
by: Huang, Tiansheng, et al.
Published: (2024)

Privacy-Preserving Parameter-Efficient Fine-Tuning for Large Language Model Services
by: Li, Yansong, et al.
Published: (2023)

Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey
by: Huang, Tiansheng, et al.
Published: (2024)

Traceback of Poisoning Attacks to Retrieval-Augmented Generation
by: Zhang, Baolei, et al.
Published: (2025)

The 'Sure' Trap: Multi-Scale Poisoning Analysis of Stealthy Compliance-Only Backdoors in Fine-Tuned Large Language Models
by: Tan, Yuting, et al.
Published: (2025)

Copyright Traps for Large Language Models
by: Meeus, Matthieu, et al.
Published: (2024)

Internal Safety Collapse in Frontier Large Language Models
by: Wu, Yutao, et al.
Published: (2026)

EnchTable: Unified Safety Alignment Transfer in Fine-tuned Large Language Models
by: Wu, Jialin, et al.
Published: (2025)

SCOUT: A Defense Against Data Poisoning Attacks in Fine-Tuned Language Models
by: Afane, Mohamed, et al.
Published: (2025)

Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models
by: Ding, Yi, et al.
Published: (2025)

Deep Research Brings Deeper Harm
by: Chen, Shuo, et al.
Published: (2025)

LLMAtKGE: Large Language Models as Explainable Attackers against Knowledge Graph Embeddings
by: Li, Ting, et al.
Published: (2025)

Practical Framework for Privacy-Preserving and Byzantine-robust Federated Learning
by: Zhang, Baolei, et al.
Published: (2025)

The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training
by: Zhang, Rui, et al.
Published: (2026)

Why Safeguarded Ships Run Aground? Aligned Large Language Models' Safety Mechanisms Tend to Be Anchored in The Template Region
by: Leong, Chak Tou, et al.
Published: (2025)

RED QUEEN: Safeguarding Large Language Models against Concealed Multi-Turn Jailbreaking
by: Jiang, Yifan, et al.
Published: (2024)

Continuous Embedding Attacks via Clipped Inputs in Jailbreaking Large Language Models
by: Xu, Zihao, et al.
Published: (2024)

Harnessing Task Overload for Scalable Jailbreak Attacks on Large Language Models
by: Dong, Yiting, et al.
Published: (2024)

Safeguarding Large Language Models: A Survey
by: Dong, Yi, et al.
Published: (2024)

LMO-DP: Optimizing the Randomization Mechanism for Differentially Private Fine-Tuning (Large) Language Models
by: Yang, Qin, et al.
Published: (2024)

HarmLevelBench: Evaluating Harm-Level Compliance and the Impact of Quantization on Model Alignment
by: Belkhiter, Yannis, et al.
Published: (2024)

Helpful or Harmful? Exploring the Efficacy of Large Language Models for Online Grooming Prevention
by: Prosser, Ellie, et al.
Published: (2024)

Dynamic Adversarial Fine-Tuning Reorganizes Refusal Geometry
by: Lan, Wenhao, et al.
Published: (2026)

Embedding with Large Language Models for Classification of HIPAA Safeguard Compliance Rules
by: Rahman, Md Abdur, et al.
Published: (2024)

Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning
by: Chua, Lynn, et al.
Published: (2024)

Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models
by: Shen, Guobin, et al.
Published: (2024)

EmMark: Robust Watermarks for IP Protection of Embedded Quantized Large Language Models
by: Zhang, Ruisi, et al.
Published: (2024)

Privately Learning from Graphs with Applications in Fine-tuning Large Language Models
by: Yin, Haoteng, et al.
Published: (2024)

Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection
by: Yan, Jun, et al.
Published: (2023)