English
Related papers

Related papers: On the Exploitability of Instruction Tuning

200 papers

Recently, the newly emerged multimodal models, which leverage both visual and linguistic modalities to train powerful encoders, have gained increasing attention. However, learning from a large-scale unlabeled dataset also exposes the model…

Cryptography and Security · Computer Science 2023-06-06 Ziqing Yang , Xinlei He , Zheng Li , Michael Backes , Mathias Humbert , Pascal Berrang , Yang Zhang

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

Fine-tuning pretrained language models (PLMs) on downstream tasks has become common practice in natural language processing. However, most of the PLMs are vulnerable, e.g., they are brittle under adversarial attacks or imbalanced data,…

Computation and Language · Computer Science 2022-05-03 Shoujie Tong , Qingxiu Dong , Damai Dai , Yifan song , Tianyu Liu , Baobao Chang , Zhifang Sui

Deep learning has become a cornerstone of modern artificial intelligence, enabling transformative applications across a wide range of domains. As the core element of deep learning, the quality and security of training data critically…

Cryptography and Security · Computer Science 2025-04-01 Pinlong Zhao , Weiyao Zhu , Pengfei Jiao , Di Gao , Ou Wu

In the current landscape of large language models (LLMs), the process of instruction tuning serves as an essential step. Considering the high computing power overhead, data-efficient instruction tuning was proposed to reduce the training…

Computation and Language · Computer Science 2025-01-06 Qi Zhang , Yiming Zhang , Haobo Wang , Junbo Zhao

Indiscriminate data poisoning attacks aim to decrease a model's test accuracy by injecting a small amount of corrupted training data. Despite significant interest, existing attacks remain relatively ineffective against modern machine…

Machine Learning · Computer Science 2023-06-07 Yiwei Lu , Gautam Kamath , Yaoliang Yu

Targeted data poisoning attacks manipulate model predictions on specific test samples by injecting malicious data into training. Yet existing evaluations report average attack success rates over randomly selected targets, obscuring true…

Machine Learning · Computer Science 2026-05-25 William Xu , Chenyu Zhang , Yihan Wang , Matthew Y. R. Yang , Zuoqiu Liu , Gautam Kamath , Yaoliang Yu , Yiwei Lu

With the development of large language models (LLMs) like ChatGPT, both their vast applications and potential vulnerabilities have come to the forefront. While developers have integrated multiple safety mechanisms to mitigate their misuse,…

Computation and Language · Computer Science 2024-07-23 Xiao Liu , Liangzhi Li , Tong Xiang , Fuying Ye , Lu Wei , Wangyue Li , Noa Garcia

Machine learning algorithms are used to construct a mathematical model for a system based on training data. Such a model is capable of making highly accurate predictions without being explicitly programmed to do so. These techniques have a…

Cryptography and Security · Computer Science 2022-02-22 Cato Pauling , Michael Gimson , Muhammed Qaid , Ahmad Kida , Basel Halak

Large Language Models (LLMs) are increasingly being integrated into the scientific peer-review process, raising new questions about their reliability and resilience to manipulation. In this work, we investigate the potential for hidden…

Cryptography and Security · Computer Science 2026-03-31 Matteo Gioele Collu , Umberto Salviati , Roberto Confalonieri , Mauro Conti , Giovanni Apruzzese

Large Language Models (LLMs) have found several use cases in education, ranging from automatic question generation to essay evaluation. In this paper, we explore the potential of using Large Language Models (LLMs) to author Intelligent…

Computation and Language · Computer Science 2024-04-26 Sankalan Pal Chowdhury , Vilém Zouhar , Mrinmaya Sachan

Large Language Models (LLMs) are being enhanced with the ability to use tools and to process multiple modalities. These new capabilities bring new benefits and also new security risks. In this work, we show that an attacker can use visual…

Cryptography and Security · Computer Science 2023-10-06 Xiaohan Fu , Zihan Wang , Shuheng Li , Rajesh K. Gupta , Niloofar Mireshghallah , Taylor Berg-Kirkpatrick , Earlence Fernandes

Backdoor attacks pose a serious threat to the secure deployment of large language models (LLMs), enabling adversaries to implant hidden behaviors triggered by specific inputs. However, existing methods often rely on manually crafted…

Cryptography and Security · Computer Science 2025-11-24 Yige Li , Zhe Li , Wei Zhao , Nay Myat Min , Hanxun Huang , Xingjun Ma , Jun Sun

We surface a new threat to closed-weight Large Language Models (LLMs) that enables an attacker to compute optimization-based prompt injections. Specifically, we characterize how an attacker can leverage the loss-like information returned…

Cryptography and Security · Computer Science 2025-05-13 Andrey Labunets , Nishit V. Pandya , Ashish Hooda , Xiaohan Fu , Earlence Fernandes

Machine learning systems are deployed in critical settings, but they might fail in unexpected ways, impacting the accuracy of their predictions. Poisoning attacks against machine learning induce adversarial modification of data used by a…

Machine Learning · Computer Science 2021-05-13 Matthew Jagielski , Giorgio Severi , Niklas Pousette Harger , Alina Oprea

Self-play post-training methods has emerged as an effective approach for finetuning large language models and turn the weak language model into strong language model without preference data. However, the theoretical foundations for…

Machine Learning · Computer Science 2026-02-03 Shangzhe Li , Xuchao Zhang , Chetan Bansal , Weitong Zhang

In an era where language models are increasingly integrated into decision-making and communication, understanding the biases within Large Language Models (LLMs) becomes imperative, especially when these models are applied in the economic…

Computation and Language · Computer Science 2024-07-30 Ahmed Agiza , Mohamed Mostagir , Sherief Reda

Machine learning is susceptible to poisoning attacks, in which an attacker controls a small fraction of the training data and chooses that data with the goal of inducing some behavior unintended by the model developer in the trained model.…

Machine Learning · Computer Science 2023-11-21 Evan Rose , Fnu Suya , David Evans

With tools like GitHub Copilot, automatic code suggestion is no longer a dream in software engineering. These tools, based on large language models, are typically trained on massive corpora of code mined from unvetted public sources. As a…

Cryptography and Security · Computer Science 2024-01-25 Hojjat Aghakhani , Wei Dai , Andre Manoel , Xavier Fernandes , Anant Kharkar , Christopher Kruegel , Giovanni Vigna , David Evans , Ben Zorn , Robert Sim

In recent years, instruction tuning has gained increasing attention and emerged as a crucial technique to enhance the capabilities of Large Language Models (LLMs). To construct high-quality instruction datasets, many instruction processing…

Computation and Language · Computer Science 2024-06-25 Yixin Ou , Ningyu Zhang , Honghao Gui , Ziwen Xu , Shuofei Qiao , Yida Xue , Runnan Fang , Kangwei Liu , Lei Li , Zhen Bi , Guozhou Zheng , Huajun Chen