English
Related papers

Related papers: DistillGuard: Evaluating Defenses Against LLM Know…

200 papers

Distillation-based federated learning has emerged as a promising collaborative learning approach, where clients share the output logit vectors of a public dataset rather than their private model parameters. This practice reduces the risk of…

Cryptography and Security · Computer Science 2024-02-01 Yonghao Yu , Shunan Zhu , Jinglu Hu

Large language models (LLMs) are increasingly deployed worldwide, yet their safety alignment remains predominantly English-centric. This allows for vulnerabilities in non-English contexts, especially with low-resource languages. We…

Computation and Language · Computer Science 2026-04-27 Max Zhang , Derek Liu , Kai Zhang , Joshua Franco , Haihao Liu

Neural networks (NNs) are already deployed in hardware today, becoming valuable intellectual property (IP) as many hours are invested in their training and optimization. Therefore, attackers may be interested in copying, reverse…

Cryptography and Security · Computer Science 2022-04-04 Mahdieh Grailoo , Zain Ul Abideen , Mairo Leier , Samuel Pagliarini

Model extraction attacks pose significant security threats to deployed language models, potentially compromising intellectual property and user privacy. This survey provides a comprehensive taxonomy of LLM-specific extraction attacks and…

Cryptography and Security · Computer Science 2025-07-09 Kaixiang Zhao , Lincan Li , Kaize Ding , Neil Zhenqiang Gong , Yue Zhao , Yushun Dong

Knowledge distillation has emerged as a pivotal technique for transferring knowledge from stronger large language models (LLMs) to smaller, more efficient models. However, traditional distillation approaches face challenges related to…

Computation and Language · Computer Science 2026-04-14 Ruihan Jin , Pengpeng Shao , Zhengqi Wen , Jinyang Wu , Mingkuan Feng , Shuo Yang , Chu Yuan Zhang , Jianhua Tao

We show that defensive distillation is not secure: it is no more resistant to targeted misclassification attacks than unprotected neural networks.

Cryptography and Security · Computer Science 2016-07-18 Nicholas Carlini , David Wagner

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

Knowledge Distillation (KD) is increasingly adopted to transfer capabilities from large language models to smaller ones, offering significant improvements in efficiency and utility while often surpassing standard fine-tuning. Beyond…

Neural networks provide state-of-the-art results for most machine learning tasks. Unfortunately, neural networks are vulnerable to adversarial examples: given an input $x$ and any target classification $t$, it is possible to find a new…

Cryptography and Security · Computer Science 2017-03-23 Nicholas Carlini , David Wagner

Knowledge distillation from large language models (LLMs) assumes that the teacher's output distribution is a high-quality training signal. On reasoning tasks, this assumption is frequently violated. A model's intermediate representations…

Computation and Language · Computer Science 2026-03-16 Ryan Brown , Chris Russell

Self-distillation has emerged as an effective post-training paradigm for LLMs, often improving performance while shortening reasoning traces. However, in mathematical reasoning, we find that it can reduce response length while degrading…

Computation and Language · Computer Science 2026-05-21 Jeonghye Kim , Xufang Luo , Minbeom Kim , Sangmook Lee , Dohyung Kim , Jiwon Jeon , Dongsheng Li , Yuqing Yang

Split Federated Learning (SFL) is an emerging paradigm for privacy-preserving distributed learning. However, it remains vulnerable to sophisticated data poisoning attacks targeting local features, labels, smashed data, and model weights.…

Machine Learning · Computer Science 2025-11-17 Yuhan Xie , Chen Lyu

Closed-weight generative services are increasingly deployed through query-based APIs, where users can obtain generated outputs while model parameters remain inaccessible. However, such deployment does not prevent model stealing: an attacker…

Cryptography and Security · Computer Science 2026-05-22 Yilan Gao , Sida Huang , Hongyuan Zhang , Xuelong Li

Distillation attacks create a deployment trade-off for model providers: the same outputs that make a model more useful can also make it easier to imitate. We study this trade-off through a minimax game between a utility-constrained teacher…

Machine Learning · Computer Science 2026-05-29 Youssef Allouah , Mahdi Haghifam , Sanmi Koyejo , Reza Shokri

The deployment of large language models (LLMs) faces considerable challenges concerning resource constraints and inference efficiency. Recent research has increasingly focused on smaller, task-specific models enhanced by distilling…

Computation and Language · Computer Science 2024-09-20 Wei Wang , Zhaowei Li , Qi Xu , Yiqing Cai , Hang Song , Qi Qi , Ran Zhou , Zhida Huang , Tao Wang , Li Xiao

This paper proposes the DistillCSE framework, which performs contrastive learning under the self-training paradigm with knowledge distillation. The potential advantage of DistillCSE is its self-enhancing feature: using a base model to…

Computation and Language · Computer Science 2023-12-25 Jiahao Xu , Wei Shao , Lihui Chen , Lemao Liu

Dataset distillation offers a potential means to enhance data efficiency in deep learning. Recent studies have shown its ability to counteract backdoor risks present in original training samples. In this study, we delve into the theoretical…

Machine Learning · Computer Science 2025-06-03 Ming-Yu Chung , Sheng-Yen Chou , Chia-Mu Yu , Pin-Yu Chen , Sy-Yen Kuo , Tsung-Yi Ho

The radioactive nature of Large Language Model (LLM) watermarking enables the detection of watermarks inherited by student models when trained on the outputs of watermarked teacher models, making it a promising tool for preventing…

Computation and Language · Computer Science 2025-05-27 Leyi Pan , Aiwei Liu , Shiyu Huang , Yijian Lu , Xuming Hu , Lijie Wen , Irwin King , Philip S. Yu

Large Language Models (LLMs) demonstrate exceptional reasoning capabilities, often achieving state-of-the-art performance in various tasks. However, their substantial computational and memory demands, due to billions of parameters, hinder…

Computation and Language · Computer Science 2024-11-25 Xunyu Zhu , Jian Li , Can Ma , Weiping Wang

Adversarial training is a widely adopted strategy to bolster the robustness of neural network models against adversarial attacks. This paper revisits the fundamental assumptions underlying image classification and suggests that representing…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Erh-Chung Chen , Che-Rung Lee