Cover Image

DistilLock: Safeguarding LLMs from Unauthorized Knowledge Distillation on the Edge

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mohanty, Asmita, Kang, Gezheng, Gao, Lei, Annavaram, Murali
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Differentially Private Knowledge Distillation via Synthetic Text Generation
by: Flemings, James, et al.
Published: (2024)

PrivacySIM: Evaluating LLM Simulation of User Privacy Behavior
by: Flemings, James, et al.
Published: (2026)

Safeguarding Text-to-Image Generative Models Against Unauthorized Knowledge Distillation
by: Gao, Yilan, et al.
Published: (2026)

MPC-Pipe: an Efficient Pipeline Scheme for Secure Multi-party Machine Learning Inference
by: Wang, Yongqin, et al.
Published: (2022)

LRD-MPC: Efficient MPC Inference through Low-rank Decomposition
by: Tang, Tingting, et al.
Published: (2026)

Adaptively Private Next-Token Prediction of Large Language Models
by: Flemings, James, et al.
Published: (2024)

Differentially Private Next-Token Prediction of Large Language Models
by: Flemings, James, et al.
Published: (2024)

Edge Private Graph Neural Networks with Singular Value Perturbation
by: Tang, Tingting, et al.
Published: (2024)

Resource-Efficient Automatic Software Vulnerability Assessment via Knowledge Distillation and Particle Swarm Optimization
by: Gao, Chaoyang, et al.
Published: (2025)

How to Backdoor the Knowledge Distillation
by: Wu, Chen, et al.
Published: (2025)

HYDRA-FL: Hybrid Knowledge Distillation for Robust and Accurate Federated Learning
by: Khan, Momin Ahmad, et al.
Published: (2024)

Towards Building Secure UAV Navigation with FHE-aware Knowledge Distillation
by: Kaushik, Arjun Ramesh, et al.
Published: (2024)

On Membership Inference Attacks in Knowledge Distillation
by: Cui, Ziyao, et al.
Published: (2025)

FGAD: Self-boosted Knowledge Distillation for An Effective Federated Graph Anomaly Detection Framework
by: Cai, Jinyu, et al.
Published: (2024)

Lossless Anti-Distillation Sampling
by: Diao, Zibo, et al.
Published: (2026)

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users
by: Hilel, Almog, et al.
Published: (2025)

It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs
by: Park, Sangwoo, et al.
Published: (2026)

Osmosis Distillation: Model Hijacking with the Fewest Samples
by: Shi, Yuchen, et al.
Published: (2026)

Cascading Adversarial Bias from Injection to Distillation in Language Models
by: Chaudhari, Harsh, et al.
Published: (2025)

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs
by: Liang, Buyun, et al.
Published: (2025)

FedSiKD: Clients Similarity and Knowledge Distillation: Addressing Non-i.i.d. and Constraints in Federated Learning
by: Alsenani, Yousef, et al.
Published: (2024)

Unveiling Client Privacy Leakage from Public Dataset Usage in Federated Distillation
by: Shi, Haonan, et al.
Published: (2025)

GraphDART: Graph Distillation for Efficient Advanced Persistent Threat Detection
by: Rabooki, Saba Fathi, et al.
Published: (2025)

Federated Learning on Non-iid Data via Local and Global Distillation
by: Zheng, Xiaolin, et al.
Published: (2023)

UNIDEAL: Curriculum Knowledge Distillation Federated Learning
by: Yang, Yuwen, et al.
Published: (2023)

Boosting Digital Safeguards: Blending Cryptography and Steganography
by: Maiti, Anamitra, et al.
Published: (2024)

Safeguarding Graph Neural Networks against Topology Inference Attacks
by: Fu, Jie, et al.
Published: (2025)

SWaRL: Safeguard Code Watermarking via Reinforcement Learning
by: Javidnia, Neusha, et al.
Published: (2026)

MERLOT: A Distilled LLM-based Mixture-of-Experts Framework for Scalable Encrypted Traffic Classification
by: Chen, Yuxuan, et al.
Published: (2024)

ExpShield: Safeguarding Web Text from Unauthorized Crawling and LLM Exploitation
by: Liu, Ruixuan, et al.
Published: (2024)

DROP: Poison Dilution via Knowledge Distillation for Federated Learning
by: Syros, Georgios, et al.
Published: (2025)

Evidencing Unauthorized Training Data from AI Generated Content using Information Isotopes
by: Tao, Qi, et al.
Published: (2025)

Video Watermarking: Safeguarding Your Video from (Unauthorized) Annotations by Video-based LLMs
by: Li, Jinmin, et al.
Published: (2024)

Locket: Robust Feature-Locking Technique for Language Models
by: He, Lipeng, et al.
Published: (2025)

Deep-Lock: Secure Authorization for Deep Neural Networks
by: Alam, Manaar, et al.
Published: (2020)

Pay Attention to the Triggers: Constructing Backdoors That Survive Distillation
by: De Muri, Giovanni, et al.
Published: (2025)

GuardReasoner: Towards Reasoning-based LLM Safeguards
by: Liu, Yue, et al.
Published: (2025)

Do Not Merge My Model! Safeguarding Open-Source LLMs Against Unauthorized Model Merging
by: Li, Qinfeng, et al.
Published: (2025)

How Vulnerable Are Edge LLMs?
by: Ding, Ao, et al.
Published: (2026)

Turning Black Box into White Box: Dataset Distillation Leaks
by: Chen, Huajie, et al.
Published: (2026)