English
Related papers

Related papers: On the Exploitability of Instruction Tuning

200 papers

This paper surveys research works in the quickly advancing field of instruction tuning (IT), which can also be referred to as supervised fine-tuning (SFT)\footnote{In this paper, unless specified otherwise, supervised fine-tuning (SFT) and…

Computation and Language · Computer Science 2025-10-07 Shengyu Zhang , Linfeng Dong , Xiaoya Li , Sen Zhang , Xiaofei Sun , Shuhe Wang , Jiwei Li , Runyi Hu , Tianwei Zhang , Fei Wu , Guoyin Wang

In-context learning, a paradigm bridging the gap between pre-training and fine-tuning, has demonstrated high efficacy in several NLP tasks, especially in few-shot settings. Despite being widely applied, in-context learning is vulnerable to…

Computation and Language · Computer Science 2024-10-10 Shuai Zhao , Meihuizi Jia , Luu Anh Tuan , Fengjun Pan , Jinming Wen

The lifecycle of large language models (LLMs) is far more complex than that of traditional machine learning models, involving multiple training stages, diverse data sources, and varied inference methods. While prior research on data…

Cryptography and Security · Computer Science 2025-02-21 Pengfei He , Yue Xing , Han Xu , Zhen Xiang , Jiliang Tang

As large language models (LLMs) gain popularity, their vulnerability to adversarial attacks emerges as a primary concern. While fine-tuning models on domain-specific datasets is often employed to improve model performance, it can…

Computation and Language · Computer Science 2026-02-24 Punya Syon Pandey , Samuel Simko , Kellin Pelrine , Zhijing Jin

Neural machine translation systems are known to be vulnerable to adversarial test inputs, however, as we show in this paper, these systems are also vulnerable to training attacks. Specifically, we propose a poisoning attack in which a…

Computation and Language · Computer Science 2021-07-13 Jun Wang , Chang Xu , Francisco Guzman , Ahmed El-Kishky , Yuqing Tang , Benjamin I. P. Rubinstein , Trevor Cohn

Instruction-tuning enhances the ability of large language models (LLMs) to follow user instructions more accurately, improving usability while reducing harmful outputs. However, this process may increase the model's dependence on user…

Computation and Language · Computer Science 2025-07-25 Kyubeen Han , Junseo Jang , Hongjin Kim , Geunyeong Jeong , Harksoo Kim

Machine learning is vulnerable to a wide variety of attacks. It is now well understood that by changing the underlying data distribution, an adversary can poison the model trained with it or introduce backdoors. In this paper we present a…

Machine Learning · Computer Science 2021-06-08 Ilia Shumailov , Zakhar Shumaylov , Dmitry Kazhdan , Yiren Zhao , Nicolas Papernot , Murat A. Erdogdu , Ross Anderson

Adversarial training (AT) is a robust learning algorithm that can defend against adversarial attacks in the inference phase and mitigate the side effects of corrupted data in the training phase. As such, it has become an indispensable…

Cryptography and Security · Computer Science 2023-05-02 Jingfeng Zhang , Bo Song , Bo Han , Lei Liu , Gang Niu , Masashi Sugiyama

Recent studies have widely investigated backdoor attacks on Large Language Models (LLMs) by inserting harmful question-answer (QA) pairs into their training data. However, we revisit existing attacks and identify two critical limitations:…

Computation and Language · Computer Science 2025-10-07 Jiawei Kong , Hao Fang , Xiaochen Yang , Kuofeng Gao , Bin Chen , Shu-Tao Xia , Ke Xu , Han Qiu

Today's text-to-image generative models are trained on millions of images sourced from the Internet, each paired with a detailed caption produced by Vision-Language Models (VLMs). This part of the training pipeline is critical for supplying…

Cryptography and Security · Computer Science 2025-06-30 Stanley Wu , Ronik Bhaskar , Anna Yoo Jeong Ha , Shawn Shan , Haitao Zheng , Ben Y. Zhao

Instruction tuning for large language models (LLMs) has gained attention from researchers due to its ability to unlock the potential of LLMs in following instructions. While instruction tuning offers advantages for facilitating the…

Artificial Intelligence · Computer Science 2023-05-17 Hao Chen , Yiming Zhang , Qi Zhang , Hantao Yang , Xiaomeng Hu , Xuetao Ma , Yifan Yanggong , Junbo Zhao

Instruction-tuning is a widely adopted finetuning method that enables large language models (LLMs) to generate output that more closely resembles human responses. However, no studies have shown that instruction-tuning actually teaches LLMs…

Computation and Language · Computer Science 2024-08-12 Khai Loong Aw , Syrielle Montariol , Badr AlKhamissi , Martin Schrimpf , Antoine Bosselut

A number of online services nowadays rely upon machine learning to extract valuable information from data collected in the wild. This exposes learning algorithms to the threat of data poisoning, i.e., a coordinate attack in which a fraction…

Prompting Large Language Models (LLMs), or providing context on the expected model of operation, is an effective way to steer the outputs of such models to satisfy human desiderata after they have been trained. But in rapidly evolving…

Machine Learning · Computer Science 2025-08-08 Younwoo Choi , Muhammad Adil Asif , Ziwen Han , John Willes , Rahul G. Krishnan

Deep neural networks are vulnerable to backdoor attacks, a type of adversarial attack that poisons the training data to manipulate the behavior of models trained on such data. Clean-label attacks are a more stealthy form of backdoor attacks…

Machine Learning · Computer Science 2024-07-17 Quang H. Nguyen , Nguyen Ngoc-Hieu , The-Anh Ta , Thanh Nguyen-Tang , Kok-Seng Wong , Hoang Thanh-Tung , Khoa D. Doan

Deep learning models have achieved high performance on many tasks, and thus have been applied to many security-critical scenarios. For example, deep learning-based face recognition systems have been used to authenticate users to access many…

Cryptography and Security · Computer Science 2017-12-18 Xinyun Chen , Chang Liu , Bo Li , Kimberly Lu , Dawn Song

Deep neural networks are susceptible to poisoning attacks by purposely polluted training data with specific triggers. As existing episodes mainly focused on attack success rate with patch-based samples, defense algorithms can easily detect…

Cryptography and Security · Computer Science 2021-01-11 Jinyin Chen , Longyuan Zhang , Haibin Zheng , Xueke Wang , Zhaoyan Ming

Machine learning models are brittle, and small changes in the training data can result in different predictions. We study the problem of proving that a prediction is robust to data poisoning, where an attacker can inject a number of…

Programming Languages · Computer Science 2020-06-25 Samuel Drews , Aws Albarghouthi , Loris D'Antoni

With the growing adoption of AI and machine learning systems in real-world applications, ensuring their fairness has become increasingly critical. The majority of the work in algorithmic fairness focus on assessing and improving the…

Machine Learning · Computer Science 2025-11-12 Eunice Chan , Hanghang Tong

The open-endedness of large language models (LLMs) combined with their impressive capabilities may lead to new safety issues when being exploited for malicious use. While recent studies primarily focus on probing toxic outputs that can be…

Computation and Language · Computer Science 2023-11-30 Jiaxin Wen , Pei Ke , Hao Sun , Zhexin Zhang , Chengfei Li , Jinfeng Bai , Minlie Huang