Cover Image

Open-Weight LLM Fine-Tuning Defenses are Susceptible to Simple Attacks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kuo, Kevin, Yadav, Chhavi, Smith, Virginia
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Attacks and Defenses Against LLM Fingerprinting
by: Kurian, Kevin, et al.
Published: (2025)

Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents
by: Zhan, Qiusi, et al.
Published: (2025)

Dummy-Aware Weighted Attack (DAWA): Breaking the Safe Sink in Dummy Class Defenses
by: Yu, Yunrui, et al.
Published: (2026)

A Multi-Agent LLM Defense Pipeline Against Prompt Injection Attacks
by: Hossain, S M Asif, et al.
Published: (2025)

Checkpoint-GCG: Auditing and Attacking Fine-Tuning-Based Prompt Injection Defenses
by: Yang, Xiaoxue, et al.
Published: (2025)

AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks
by: Zeng, Yifan, et al.
Published: (2024)

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

AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
by: Debenedetti, Edoardo, et al.
Published: (2024)

Membership Inference Attacks for Unseen Classes
by: Thaker, Pratiksha, et al.
Published: (2025)

PAE MobiLLM: Privacy-Aware and Efficient LLM Fine-Tuning on the Mobile Device via Additive Side-Tuning
by: Yang, Xingke, et al.
Published: (2025)

Attack and Defense of Deep Learning Models in the Field of Web Attack Detection
by: Shi, Lijia, et al.
Published: (2024)

FairProof : Confidential and Certifiable Fairness for Neural Networks
by: Yadav, Chhavi, et al.
Published: (2024)

ExpProof : Operationalizing Explanations for Confidential Models with ZKPs
by: Yadav, Chhavi, et al.
Published: (2025)

Synthetic Tabular Data: Methods, Attacks and Defenses
by: Cormode, Graham, et al.
Published: (2025)

A Taxonomy of Attacks and Defenses in Split Learning
by: Shabbir, Aqsa, et al.
Published: (2025)

Early Approaches to Adversarial Fine-Tuning for Prompt Injection Defense: A 2022 Study of GPT-3 and Contemporary Models
by: Sandoval, Gustavo, et al.
Published: (2025)

MarkTune: Improving the Quality-Detectability Trade-off in Open-Weight LLM Watermarking
by: Zhao, Yizhou, et al.
Published: (2025)

Dashed Line Defense: Plug-And-Play Defense Against Adaptive Score-Based Query Attacks
by: Fu, Yanzhang, et al.
Published: (2026)

A No-Defense Defense Against Gradient-Based Adversarial Attacks on ML-NIDS: Is Less More?
by: elShehaby, Mohamed, et al.
Published: (2026)

Data Reconstruction Attacks and Defenses: A Systematic Evaluation
by: Liu, Sheng, et al.
Published: (2024)

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

A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework
by: Chu, Kexin
Published: (2026)

Watch Out! Simple Horizontal Class Backdoor Can Trivially Evade Defense
by: Ma, Hua, et al.
Published: (2023)

Uncovering Attacks and Defenses in Secure Aggregation for Federated Deep Learning
by: Zhang, Yiwei, et al.
Published: (2024)

PECAN: A Deterministic Certified Defense Against Backdoor Attacks
by: Zhang, Yuhao, et al.
Published: (2023)

SecureLearn -- An Attack-agnostic Defense for Multiclass Machine Learning Against Data Poisoning Attacks
by: Paracha, Anum, et al.
Published: (2025)

Acceptance Cards:A Four-Diagnostic Standard for Safe Fine-Tuning Defense Claims
by: Konrad, Phongsakon Mark, et al.
Published: (2026)

Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable
by: Bertran, Martin, et al.
Published: (2024)

Exploring Secure Machine Learning Through Payload Injection and FGSM Attacks on ResNet-50
by: Yadav, Umesh, et al.
Published: (2025)

Security in the Fine-Tuning Lifecycle of Large Language Models: Threats, Defenses,Evaluation, and Future Directions
by: Li, Wenjuan, et al.
Published: (2026)

Inferring Sensitive Attributes from Knowledge Graph Embeddings: Attack and Defense Strategies
by: Hayder, Yasmine
Published: (2026)

Attack Smarter: Attention-Driven Fine-Grained Webpage Fingerprinting Attacks
by: Yuan, Yali, et al.
Published: (2025)

Exploiting Defenses against GAN-Based Feature Inference Attacks in Federated Learning
by: Luo, Xinjian, et al.
Published: (2020)

AttackLLM: LLM-based Attack Pattern Generation for an Industrial Control System
by: Ahmed, Chuadhry Mujeeb
Published: (2025)

Fine-tuning is Not Fine: Mitigating Backdoor Attacks in GNNs with Limited Clean Data
by: Zhang, Jiale, et al.
Published: (2025)

SVDefense: Effective Defense against Gradient Inversion Attacks via Singular Value Decomposition
by: Luo, Chenxiang, et al.
Published: (2025)

Test-time Adversarial Defense with Opposite Adversarial Path and High Attack Time Cost
by: Yeh, Cheng-Han, et al.
Published: (2024)

Sponge Attacks on Sensing AI: Energy-Latency Vulnerabilities and Defense via Model Pruning
by: Hasan, Syed Mhamudul, et al.
Published: (2025)

KDk: A Defense Mechanism Against Label Inference Attacks in Vertical Federated Learning
by: Arazzi, Marco, et al.
Published: (2024)

Certifiable Black-Box Attacks with Randomized Adversarial Examples: Breaking Defenses with Provable Confidence
by: Hong, Hanbin, et al.
Published: (2023)