Cover Image

SPARD: Defending Harmful Fine-Tuning Attack via Safety Projection with Relevance-Diversity Data Selection

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Shuhao, Jiang, Weisen, Gong, Yeqi, Luo, Shengda, Zhuo, Chengxiang, Li, Zang, Kwok, James T., Zhang, Yu
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MetaMoE: Diversity-Aware Proxy Selection for Privacy-Preserving Mixture-of-Experts Unification
by: Jiang, Weisen, et al.
Published: (2026)

Defending MoE LLMs against Harmful Fine-Tuning via Safety Routing Alignment
by: Kim, Jaehan, et al.
Published: (2025)

MetaDefense: Defending Finetuning-based Jailbreak Attack Before and During Generation
by: Jiang, Weisen, et al.
Published: (2025)

Safety Anchor: Defending Harmful Fine-tuning via Geometric Bottlenecks
by: Lu, Guoxin, et al.
Published: (2026)

Rethinking Fraud Safety Evaluation: Multi-Round Attacks Reveal Safety-Utility Tradeoffs in Graph-Context LLM Defenders
by: Jiang, Laura, et al.
Published: (2026)

Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning
by: Zhao, Shuai, et al.
Published: (2024)

Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs
by: Liu, Fan, et al.
Published: (2024)

SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
by: Xu, Zhangchen, et al.
Published: (2024)

PEFTGuard: Detecting Backdoor Attacks Against Parameter-Efficient Fine-Tuning
by: Sun, Zhen, et al.
Published: (2024)

E-MIA: Exam-Style Black-Box Membership Inference Attacks against RAG Systems
by: Guan, Zelin, et al.
Published: (2026)

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

To Defend Against Cyber Attacks, We Must Teach AI Agents to Hack
by: Zhuo, Terry Yue, et al.
Published: (2026)

Defending against Data Poisoning Attacks in Federated Learning via User Elimination
by: Galanis, Nick
Published: (2024)

Defending Against Neural Network Model Inversion Attacks via Data Poisoning
by: Zhou, Shuai, et al.
Published: (2024)

Benign Fine-Tuning Breaks Safety Alignment in Audio LLMs
by: Roh, Jaechul, et al.
Published: (2026)

CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning
by: Yi, Biao, et al.
Published: (2025)

Attention is All You Need to Defend Against Indirect Prompt Injection Attacks in LLMs
by: Zhong, Yinan, et al.
Published: (2025)

Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction
by: Chen, Yulin, et al.
Published: (2025)

Defending Against Attack on the Cloned: In-Band Active Man-in-the-Middle Detection for the Signal Protocol
by: Teng, Wil Liam, et al.
Published: (2024)

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets
by: Lu, Ning, et al.
Published: (2025)

PlanGuard: Defending Agents against Indirect Prompt Injection via Planning-based Consistency Verification
by: Gong, Guangyu, et al.
Published: (2026)

FL-Defender: Combating Targeted Attacks in Federated Learning
by: Jebreel, Najeeb, et al.
Published: (2022)

Defending against Backdoor Attack on Deep Neural Networks
by: Cheng, Hao, et al.
Published: (2020)

Invariant Aggregator for Defending against Federated Backdoor Attacks
by: Wang, Xiaoyang, et al.
Published: (2022)

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

Persistent Backdoor Attacks under Continual Fine-Tuning of LLMs
by: Cui, Jing, et al.
Published: (2025)

Prompt Injection Attack to Tool Selection in LLM Agents
by: Shi, Jiawen, et al.
Published: (2025)

Attack via Overfitting: 10-shot Benign Fine-tuning to Jailbreak LLMs
by: Xie, Zhixin, et al.
Published: (2025)

No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms
by: Kazdan, Joshua, et al.
Published: (2025)

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

CleanStack: A New Dual-Stack for Defending Against Stack-Based Memory Corruption Attacks
by: Chong, Lei
Published: (2025)

JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation
by: Zhang, Shenyi, et al.
Published: (2025)

Concept-Aware Privacy Mechanisms for Defending Embedding Inversion Attacks
by: Tsai, Yu-Che, et al.
Published: (2026)

No Free Lunch for Defending Against Prefilling Attack by In-Context Learning
by: Xue, Zhiyu, et al.
Published: (2024)

Defending Against Beta Poisoning Attacks in Machine Learning Models
by: Gulciftci, Nilufer, et al.
Published: (2025)

Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning Attacks
by: Halloran, John T., et al.
Published: (2026)

NeST: Neuron Selective Tuning for LLM Safety
by: Behrouzi, Sasha, et al.
Published: (2026)

HarmChip: Evaluating Hardware Security Centric LLM Safety via Jailbreak Benchmarking
by: Wang, Zeng, et al.
Published: (2026)

Open-Weight LLM Fine-Tuning Defenses are Susceptible to Simple Attacks
by: Kuo, Kevin, et al.
Published: (2026)

Multi-Screaming-Channel Attacks: Frequency Diversity for Enhanced Attacks
by: Guillaume, Jeremy, et al.
Published: (2025)