English
Related papers

Related papers: MBTSAD: Mitigating Backdoors in Language Models Ba…

200 papers

Post-training quantization is a key technique for reducing the memory and inference latency of large language models by quantizing weights and activations without requiring retraining. However, existing methods either (1) fail to account…

Machine Learning · Computer Science 2025-09-23 Jinuk Kim , Marwa El Halabi , Wonpyo Park , Clemens JS Schaefer , Deokjae Lee , Yeonhong Park , Jae W. Lee , Hyun Oh Song

Training deep neural networks from scratch on natural language processing (NLP) tasks requires significant amount of manually labeled text corpus and substantial time to converge, which usually cannot be satisfied by the customers. In this…

Computation and Language · Computer Science 2019-10-29 Yunzhe Tao , Saurabh Gupta , Satyapriya Krishna , Xiong Zhou , Orchid Majumder , Vineet Khare

Language models can be viewed as functions that embed text into Euclidean space, where the quality of the embedding vectors directly determines model performance, training such neural networks involves various uncertainties. This paper…

Computation and Language · Computer Science 2025-03-31 Yifei Duan , Raphael Shang , Deng Liang , Yongqiang Cai

Language models (LMs) can "memorize" information, i.e., encode training data in their weights in such a way that inference-time queries can lead to verbatim regurgitation of that data. This ability to extract training data can be…

With the help of conditioning mechanisms, the state-of-the-art diffusion models have achieved tremendous success in guided image generation, particularly in text-to-image synthesis. To gain a better understanding of the training process and…

Cryptography and Security · Computer Science 2023-10-24 Shengfang Zhai , Yinpeng Dong , Qingni Shen , Shi Pu , Yuejian Fang , Hang Su

Knowledge distillation (KD) is a standard route to compress Large Language Models (LLMs) into compact students, yet most pipelines uniformly apply token-wise loss regardless of teacher confidence. This indiscriminate supervision amplifies…

Computation and Language · Computer Science 2025-11-18 Haiduo Huang , Jiangcheng Song , Yadong Zhang , Pengju Ren

Pre-trained Natural Language Processing (NLP) models can be easily adapted to a variety of downstream language tasks. This significantly accelerates the development of language models. However, NLP models have been shown to be vulnerable to…

Computation and Language · Computer Science 2021-10-07 Kangjie Chen , Yuxian Meng , Xiaofei Sun , Shangwei Guo , Tianwei Zhang , Jiwei Li , Chun Fan

Knowledge distillation (KD) is a key technique for compressing large-scale language models (LLMs), yet prevailing logit-based methods typically employ static strategies that are misaligned with the dynamic learning process of student…

Computation and Language · Computer Science 2025-10-14 Xurong Xie , Zhucun Xue , Jiafu Wu , Jian Li , Yabiao Wang , Xiaobin Hu , Yong Liu , Jiangning Zhang

Prompt-tuning has emerged as an attractive paradigm for deploying large-scale language models due to its strong downstream task performance and efficient multitask serving ability. Despite its wide adoption, we empirically show that…

Computation and Language · Computer Science 2023-10-17 Chengkun Wei , Wenlong Meng , Zhikun Zhang , Min Chen , Minghu Zhao , Wenjing Fang , Lei Wang , Zihui Zhang , Wenzhi Chen

While pre-trained Vision-Language Models (VLMs) such as CLIP exhibit impressive representational capabilities for multimodal data, recent studies have revealed their vulnerability to backdoor attacks. To alleviate the threat, existing…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Jiawei Kong , Hao Fang , Sihang Guo , Chenxi Qing , Kuofeng Gao , Bin Chen , Shu-Tao Xia , Ke Xu

Poisoning backdoor attacks involve an adversary manipulating the training data to induce certain behaviors in the victim model by inserting a trigger in the signal at inference time. We adapted clean label backdoor (CLBD)-data poisoning…

Cryptography and Security · Computer Science 2024-09-16 Henry Li Xinyuan , Sonal Joshi , Thomas Thebaud , Jesus Villalba , Najim Dehak , Sanjeev Khudanpur

Learning on a massive amount of speech corpus leads to the recent success of many self-supervised speech models. With knowledge distillation, these models may also benefit from the knowledge encoded by language models that are pre-trained…

Computation and Language · Computer Science 2023-03-08 Jinjie Ni , Yukun Ma , Wen Wang , Qian Chen , Dianwen Ng , Han Lei , Trung Hieu Nguyen , Chong Zhang , Bin Ma , Erik Cambria

Compressing deep neural network (DNN) models becomes a very important and necessary technique for real-world applications, such as deploying those models on mobile devices. Knowledge distillation is one of the most popular methods for model…

Machine Learning · Computer Science 2020-03-02 Makoto Takamoto , Yusuke Morishita , Hitoshi Imaoka

Deep neural networks are vulnerable to backdoor attacks (Trojans), where an attacker poisons the training set with backdoor triggers so that the neural network learns to classify test-time triggers to the attacker's designated target class.…

Machine Learning · Computer Science 2023-08-10 Hang Wang , Zhen Xiang , David J. Miller , George Kesidis

Reasoning-centric large language models (LLMs) achieve strong performance by generating intermediate reasoning trajectories, but often incur excessive token usage and high inference-time decoding cost. We observe that, when solving the same…

Artificial Intelligence · Computer Science 2026-05-12 Han Yang , Mingyan Wu , Bailan He , Zeyu Cao , Sikuan Yan , Kevin Qinghong Lin , Zifeng Ding

Large-scale language models have achieved tremendous success across various natural language processing (NLP) applications. Nevertheless, language models are vulnerable to backdoor attacks, which inject stealthy triggers into models for…

Cryptography and Security · Computer Science 2023-02-09 Yujin Huang , Terry Yue Zhuo , Qiongkai Xu , Han Hu , Xingliang Yuan , Chunyang Chen

As ML models become increasingly complex and integral to high-stakes domains such as finance and healthcare, they also become more susceptible to sophisticated adversarial attacks. We investigate the threat posed by undetectable backdoors,…

Machine Learning · Computer Science 2024-09-10 Alkis Kalavasis , Amin Karbasi , Argyris Oikonomou , Katerina Sotiraki , Grigoris Velegkas , Manolis Zampetakis

Deep learning models are vulnerable to backdoor attacks, where attackers inject malicious behavior through data poisoning and later exploit triggers to manipulate deployed models. To improve the stealth and effectiveness of backdoors, prior…

Cryptography and Security · Computer Science 2024-09-10 Xiaolei Liu , Ming Yi , Kangyi Ding , Bangzhou Xin , Yixiao Xu , Li Yan , Chao Shen

Pre-trained language models (PLMs) have attracted enormous attention over the past few years with their unparalleled performances. Meanwhile, the soaring cost to train PLMs as well as their amazing generalizability have jointly contributed…

Computation and Language · Computer Science 2024-06-10 Tianrong Zhang , Zhaohan Xi , Ting Wang , Prasenjit Mitra , Jinghui Chen

Video Large Language Models (Video LLMs) have achieved remarkable results in video understanding tasks. However, they often suffer from heavy computational overhead due to the large number of visual tokens generated from multiple video…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Fengyuan Sun , Leqi Shen , Hui Chen , Sicheng Zhao , Jungong Han , Guiguang Ding