English
Related papers

Related papers: Winter Soldier: Backdooring Language Models at Pre…

200 papers

Chain-of-Thought (CoT) reasoning has emerged as a powerful technique for enhancing large language models' capabilities by generating intermediate reasoning steps for complex tasks. A common practice for equipping LLMs with reasoning is to…

Cryptography and Security · Computer Science 2026-01-29 Harsh Chaudhari , Ethan Rathbun , Hanna Foerster , Jamie Hayes , Matthew Jagielski , Milad Nasr , Ilia Shumailov , Alina Oprea

This paper explores the risk that a large language model (LLM) trained for code generation on data mined from software repositories will generate content that discloses sensitive information included in its training data. We decompose this…

Cryptography and Security · Computer Science 2026-04-16 Rafiqul Rabin , Sean McGregor , Nick Judd

During fine-tuning, large language models (LLMs) are increasingly vulnerable to data-poisoning backdoor attacks, which compromise their reliability and trustworthiness. However, existing defense strategies suffer from limited…

Cryptography and Security · Computer Science 2025-10-13 Shuai Zhao , Xinyi Wu , Shiqian Zhao , Xiaobao Wu , Zhongliang Guo , Yanhao Jia , Anh Tuan Luu

Large-scale pre-trained models are increasingly adapted to downstream tasks through a new paradigm called prompt learning. In contrast to fine-tuning, prompt learning does not update the pre-trained model's parameters. Instead, it only…

Cryptography and Security · Computer Science 2023-10-19 Yixin Wu , Rui Wen , Michael Backes , Pascal Berrang , Mathias Humbert , Yun Shen , Yang Zhang

Backdoor Attacks have been a serious vulnerability against Large Language Models (LLMs). However, previous methods only reveal such risk in specific models, or present tasks transferability after attacking the pre-trained phase. So, how…

Cryptography and Security · Computer Science 2024-08-20 Pengzhou Cheng , Zongru Wu , Tianjie Ju , Wei Du , Zhuosheng Zhang Gongshen Liu

Knowledge erasure in large language models (LLMs) is important for ensuring compliance with data and AI regulations, safeguarding user privacy, mitigating bias, and misinformation. Existing unlearning methods aim to make the process of…

Cryptography and Security · Computer Science 2025-06-24 Yash Sinha , Manit Baser , Murari Mandal , Dinil Mon Divakaran , Mohan Kankanhalli

Backdoor attacks are a kind of emergent security threat in deep learning. After being injected with a backdoor, a deep neural model will behave normally on standard inputs but give adversary-specified predictions once the input contains…

Cryptography and Security · Computer Science 2022-10-20 Yangyi Chen , Fanchao Qi , Hongcheng Gao , Zhiyuan Liu , Maosong Sun

Pre-training language models (LMs) on large-scale unlabeled text data makes the model much easier to achieve exceptional downstream performance than their counterparts directly trained on the downstream tasks. In this work, we study what…

Computation and Language · Computer Science 2022-02-21 Cheng-Han Chiang , Hung-yi Lee

Recent advances in neural network based language models lead to successful deployments of such models, improving user experience in various applications. It has been demonstrated that strong performance of language models comes along with…

Cryptography and Security · Computer Science 2021-02-24 Huseyin A. Inan , Osman Ramadan , Lukas Wutschitz , Daniel Jones , Victor Rühle , James Withers , Robert Sim

The advancement of Large Language Models (LLMs) has significantly impacted various domains, including Web search, healthcare, and software development. However, as these models scale, they become more vulnerable to cybersecurity risks,…

Cryptography and Security · Computer Science 2024-10-01 Qin Liu , Wenjie Mo , Terry Tong , Jiashu Xu , Fei Wang , Chaowei Xiao , Muhao Chen

Pre-training on public data is an effective method to improve the performance for federated learning (FL) with differential privacy (DP). This paper investigates how large language models (LLMs) trained on public data can improve the…

Machine Learning · Computer Science 2024-08-08 Shanshan Wu , Zheng Xu , Yanxiang Zhang , Yuanbo Zhang , Daniel Ramage

Recent research on large language models (LLMs) has demonstrated their ability to understand and employ deceptive behavior, even without explicit prompting. However, such behavior has only been observed in rare, specialized cases and has…

Computation and Language · Computer Science 2025-06-24 Laurène Vaugrante , Francesca Carlon , Maluna Menke , Thilo Hagendorff

In recent years, attention-based models have excelled across various domains but remain vulnerable to backdoor attacks, often from downloading or fine-tuning on poisoned datasets. Many current methods to mitigate backdoors in NLP models…

Cryptography and Security · Computer Science 2025-01-07 Yidong Ding , Jiafei Niu , Ping Yi

Modern machine learning pipelines leverage large amounts of public data, making it infeasible to guarantee data quality and leaving models open to poisoning and backdoor attacks. Provably bounding model behavior under such attacks remains…

Machine Learning · Computer Science 2024-10-31 Philip Sosnin , Mark N. Müller , Maximilian Baader , Calvin Tsay , Matthew Wicker

With the advancement of technology, large language models (LLMs) have achieved remarkable performance across various natural language processing (NLP) tasks, powering LLM-integrated applications like Microsoft Copilot. However, as LLMs…

Cryptography and Security · Computer Science 2025-08-05 Yulin Chen , Haoran Li , Zihao Zheng , Yangqiu Song , Dekai Wu , Bryan Hooi

The success of machine learning is fueled by the increasing availability of computing power and large training datasets. The training data is used to learn new models or update existing ones, assuming that it is sufficiently representative…

We revisit the efficacy of several practical methods for approximate machine unlearning developed for large-scale deep learning. In addition to complying with data deletion requests, one often-cited potential application for unlearning…

Machine Learning · Computer Science 2026-01-16 Martin Pawelczyk , Jimmy Z. Di , Yiwei Lu , Gautam Kamath , Ayush Sekhari , Seth Neel

As Large Language Models (LLMs) are widely used, understanding them systematically is key to improving their safety and realizing their full potential. Although many models are aligned using techniques such as reinforcement learning from…

Machine Learning · Computer Science 2025-05-16 Sajib Biswas , Mao Nishino , Samuel Jacob Chacko , Xiuwen Liu

Modern large language models (LLMs) exhibit critical vulnerabilities to poison pill attacks: localized data poisoning that alters specific factual knowledge while preserving overall model utility. We systematically demonstrate these attacks…

Cryptography and Security · Computer Science 2025-02-27 Peng Yifeng , Wu Zhizheng , Chen Chen

Large language model (LLM) safety is a critical issue, with numerous studies employing red team testing to enhance model security. Among these, jailbreak methods explore potential vulnerabilities by crafting malicious prompts that induce…

Computation and Language · Computer Science 2025-03-07 Honglin Mu , Han He , Yuxin Zhou , Yunlong Feng , Yang Xu , Libo Qin , Xiaoming Shi , Zeming Liu , Xudong Han , Qi Shi , Qingfu Zhu , Wanxiang Che