English
Related papers

Related papers: Protecting Language Models Against Unauthorized Di…

200 papers

Model distillation enables efficient emulation of frontier large language models (LLMs), creating a need for robust mechanisms to detect when a third-party student model has trained on a teacher model's outputs. However, existing…

Machine Learning · Computer Science 2026-05-18 Yixuan Even Xu , John Kirchenbauer , Yash Savani , Asher Trockman , Alexander Robey , Tom Goldstein , Fei Fang , J. Zico Kolter

Knowledge distillation allows smaller neural networks to emulate the performance of larger, teacher models with reduced computational demands. Traditional methods for Large Language Models (LLMs) often necessitate extensive fine-tuning,…

Computation and Language · Computer Science 2025-05-02 Tyler McDonald , Ali Emami

Knowledge distillation from proprietary LLM APIs poses a growing threat to model providers, yet defenses against this attack remain fragmented and unevaluated. We present DistillGuard, a framework for systematically evaluating output-level…

Cryptography and Security · Computer Science 2026-03-10 Bo Jiang

We propose the task of knowledge distillation detection, which aims to determine whether a student model has been distilled from a given teacher, under a practical setting where only the student's weights and the teacher's API are…

Machine Learning · Computer Science 2025-10-03 Qin Shi , Amber Yijia Zheng , Qifan Song , Raymond A. Yeh

Knowledge distillation addresses the problem of transferring knowledge from a teacher model to a student model. In this process, we typically have multiple types of knowledge extracted from the teacher model. The problem is to make full use…

Computation and Language · Computer Science 2023-02-02 Chenglong Wang , Yi Lu , Yongyu Mu , Yimin Hu , Tong Xiao , Jingbo Zhu

Proprietary large language models (LLMs) embody substantial economic value and are generally exposed only as black-box APIs, yet adversaries can still exploit their outputs to extract knowledge via distillation. Existing defenses focus…

Computation and Language · Computer Science 2026-05-07 Hao Fang , Tianyi Zhang , Tianqu Zhuang , Jiawei Kong , Kuofeng Gao , Bin Chen , Leqi Zheng , Shu-Tao Xia , Ke Xu

Recent research on knowledge distillation has increasingly focused on logit distillation because of its simplicity, effectiveness, and versatility in model compression. In this paper, we introduce Refined Logit Distillation (RLD) to address…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Wujie Sun , Defang Chen , Siwei Lyu , Genlang Chen , Chun Chen , Can Wang

Distilling reasoning traces from strong large language models into smaller ones is a promising route to improve intelligence in resource-constrained settings. Existing approaches face a fundamental trade-off: offline distillation from…

Computation and Language · Computer Science 2026-05-15 Yumeng Zhang , Zhengbang Yang , Yevin Nikhel Goonatilake , Zhuangdi Zhu

LLM unlearning is a technique to remove the impacts of undesirable knowledge from the model without retraining from scratch, which is indispensable towards trustworthy AI. Existing unlearning methods face significant limitations:…

Machine Learning · Computer Science 2026-03-02 Yisheng Zhong , Zhengbang Yang , Zhuangdi Zhu

Watermarking has emerged as a critical technique for combating misinformation and protecting intellectual property in large language models (LLMs). A recent discovery, termed watermark radioactivity, reveals that watermarks embedded in…

Computation and Language · Computer Science 2025-08-26 Xin Yi , Yue Li , Shunfan Zheng , Linlin Wang , Xiaoling Wang , Liang He

Artificial Intelligence (AI) has increasingly influenced modern society, recently in particular through significant advancements in Large Language Models (LLMs). However, high computational and storage demands of LLMs still limit their…

Computation and Language · Computer Science 2025-04-23 Daniel Hendriks , Philipp Spitzer , Niklas Kühl , Gerhard Satzger

Data watermarking in language models injects traceable signals, such as specific token sequences or stylistic patterns, into copyrighted text, allowing copyright holders to track and verify training data ownership. Previous data…

Cryptography and Security · Computer Science 2025-07-29 Xinyue Cui , Johnny Tian-Zheng Wei , Swabha Swayamdipta , Robin Jia

Frontier models that generate extended reasoning traces inadvertently produce rich token sequences that can facilitate model distillation. Recognizing this vulnerability, model owners may seek sampling strategies that limit the…

Artificial Intelligence · Computer Science 2025-10-28 Yash Savani , Asher Trockman , Zhili Feng , Yixuan Even Xu , Avi Schwarzschild , Alexander Robey , Marc Finzi , J. Zico Kolter

In recent years, knowledge distillation has become a cornerstone of efficiently deployed machine learning, with labs and industries using knowledge distillation to train models that are inexpensive and resource-optimized. Trojan attacks…

Machine Learning · Computer Science 2023-03-13 Leonard Tang , Tom Shlomi , Alexander Cai

Knowledge distillation is a method of transferring the knowledge from a complex deep neural network (DNN) to a smaller and faster DNN, while preserving its accuracy. Recent variants of knowledge distillation include teaching assistant…

Machine Learning · Computer Science 2023-04-11 Minghong Gao

As Large Language Models (LLMs) continue to grow in both capability and cost, transferring frontier capabilities into smaller, deployable students has become a central engineering problem, and knowledge distillation remains the dominant…

Machine Learning · Computer Science 2026-05-19 Mingyang Song , Mao Zheng

With the rapid advancement of speech generative models, unauthorized voice cloning poses significant privacy and security risks. Speech watermarking offers a viable solution for tracing sources and preventing misuse. Current watermarking…

Sound · Computer Science 2025-09-30 Yang Cui , Peter Pan , Lei He , Sheng Zhao

Large language models (LLMs) are trained on massive corpora that may contain sensitive information, creating privacy risks under membership inference attacks (MIAs). Knowledge distillation is widely used to compress LLMs into smaller…

Machine Learning · Computer Science 2026-01-13 Ziyao Cui , Minxing Zhang , Jian Pei

Owing to their powerful semantic reasoning capabilities, Large Language Models (LLMs) have been effectively utilized as recommenders, achieving impressive performance. However, the high inference latency of LLMs significantly restricts…

Information Retrieval · Computer Science 2024-08-21 Yu Cui , Feng Liu , Pengbo Wang , Bohao Wang , Heng Tang , Yi Wan , Jun Wang , Jiawei Chen

Reasoning distillation aims to transfer multi-step reasoning capabilities from large language models to smaller, more efficient ones. While recent methods have shown promising gains, they typically rely on static teacher-student hierarchies…

Machine Learning · Computer Science 2026-05-12 Khouloud Saadi , Di Wang