English
Related papers

Related papers: Detecting Stealthy Backdoor Samples based on Intra…

200 papers

We study how training data contributes to the emergence of toxic behaviors in large language models. Most prior work on reducing model toxicity adopts reactive approaches, such as fine-tuning pre-trained (and potentially toxic) models to…

Machine Learning · Computer Science 2025-12-08 Zachary Coalson , Juhan Bae , Nicholas Carlini , Sanghyun Hong

Federated learning (FL) addresses privacy and data-silo issues in the training of large language models (LLMs). Most prior work focuses on improving the efficiency of federated learning for LLMs (FedLLM). However, security in open federated…

Cryptography and Security · Computer Science 2026-04-21 Mingxiang Tao , Yu Tian , Wenxuan Tu , Yue Yang , Xue Yang , Xiangyan Tang

Large Language Models (LLMs) are often fine-tuned to adapt their general-purpose knowledge to specific tasks and domains such as cyber threat intelligence (CTI). Fine-tuning is mostly done through proprietary datasets that may contain…

Cryptography and Security · Computer Science 2026-03-13 Shashie Dilhara Batan Arachchige , Benjamin Zi Hao Zhao , Hassan Jameel Asghar , Dinusha Vatsalan , Dali Kaafar

In the era of large language models (LLMs), detecting pretraining data has been increasingly important due to concerns about fair evaluation and ethical risks. Current methods differentiate members and non-members by designing scoring…

Computation and Language · Computer Science 2025-03-18 Hengxiang Zhang , Songxin Zhang , Bingyi Jing , Hongxin Wei

Poisoning of data sets is a potential security threat to large language models that can lead to backdoored models. A description of the internal mechanisms of backdoored language models and how they process trigger inputs, e.g., when…

Machine Learning · Computer Science 2024-05-07 Max Lamparth , Anka Reuel

We consider the challenge of mitigating the generation of negative or toxic content by the Large Language Models (LLMs) in response to certain prompts. We propose integrating risk-averse principles into LLM fine-tuning to minimize the…

Artificial Intelligence · Computer Science 2025-01-14 Sapana Chaudhary , Ujwal Dinesha , Dileep Kalathil , Srinivas Shakkottai

Data contamination poses a significant threat to the reliable evaluation of Large Language Models (LLMs). This issue arises when benchmark samples may inadvertently appear in training sets, compromising the validity of reported performance.…

Computation and Language · Computer Science 2026-03-19 Yongding Tao , Tian Wang , Yihong Dong , Huanyu Liu , Kechi Zhang , Xiaolong Hu , Ge Li

Large language models (LLMs) are excellent few-shot learners. They can perform a wide variety of tasks purely based on natural language prompts provided to them. These prompts contain data of a specific downstream task -- often the private…

Machine Learning · Computer Science 2024-11-19 Haonan Duan , Adam Dziedzic , Mohammad Yaghini , Nicolas Papernot , Franziska Boenisch

Federated large language models (FedLLMs) enable cross-silo collaborative training among institutions while preserving data locality, making them appealing for privacy-sensitive domains such as law, finance, and healthcare. However, the…

Computation and Language · Computer Science 2026-02-26 Yingqi Hu , Zhuo Zhang , Jingyuan Zhang , Jinghua Wang , Qifan Wang , Lizhen Qu , Zenglin Xu

In the domain of large language models (LLMs), in-context learning (ICL) has been recognized for its innovative ability to adapt to new tasks, relying on examples rather than retraining or fine-tuning. This paper delves into the critical…

Cryptography and Security · Computer Science 2025-06-03 Pengfei He , Han Xu , Yue Xing , Hui Liu , Makoto Yamada , Jiliang Tang

Large language model (LLM) unlearning has become a critical mechanism for removing undesired data, knowledge, or behaviors from pre-trained models while retaining their general utility. Yet, with the rise of open-weight LLMs, we ask: can…

Machine Learning · Computer Science 2025-10-21 Bingqi Shang , Yiwei Chen , Yihua Zhang , Bingquan Shen , Sijia Liu

Fine-tuning on task-specific question-answer pairs is a predominant method for enhancing the performance of instruction-tuned large language models (LLMs) on downstream tasks. However, in certain specialized domains, such as healthcare or…

Computation and Language · Computer Science 2024-10-18 Shuyang Jiang , Yusheng Liao , Ya Zhang , Yanfeng Wang , Yu Wang

Recent studies have revealed a security threat to natural language processing (NLP) models, called the Backdoor Attack. Victim models can maintain competitive performance on clean samples while behaving abnormally on samples with a specific…

Computation and Language · Computer Science 2021-03-30 Wenkai Yang , Lei Li , Zhiyuan Zhang , Xuancheng Ren , Xu Sun , Bin He

Machine learning models are increasingly present in our everyday lives; as a result, they become targets of adversarial attackers seeking to manipulate the systems we interact with. A well-known vulnerability is a backdoor introduced into a…

Machine Learning · Computer Science 2026-02-12 Enrico Ahlers , Daniel Passon , Yannic Noller , Lars Grunske

At present, backdoor attacks attract attention as they do great harm to deep learning models. The adversary poisons the training data making the model being injected with a backdoor after being trained unconsciously by victims using the…

Cryptography and Security · Computer Science 2023-03-06 Shengfang Zhai , Qingni Shen , Xiaoyi Chen , Weilong Wang , Cong Li , Yuejian Fang , Zhonghai Wu

Red-teaming, or identifying prompts that elicit harmful responses, is a critical step in ensuring the safe and responsible deployment of large language models (LLMs). Developing effective protection against many modes of attack prompts…

Computation and Language · Computer Science 2025-03-03 Seanie Lee , Minsu Kim , Lynn Cherif , David Dobre , Juho Lee , Sung Ju Hwang , Kenji Kawaguchi , Gauthier Gidel , Yoshua Bengio , Nikolay Malkin , Moksh Jain

With the rapid development of generative artificial intelligence, particularly large language models a number of sub-fields of deep learning have made significant progress and are now very useful in everyday applications. For…

Machine Learning · Computer Science 2025-04-23 Orson Mengara

Large Language Models (LLMs) like OpenAI's GPT series, Anthropic's Claude, and Meta's LLaMa have shown remarkable capabilities in text generation. However, their susceptibility to toxic prompts presents significant security challenges. This…

Cryptography and Security · Computer Science 2024-12-03 Jie Li , Yi Liu , Chongyang Liu , Xiaoning Ren , Ling Shi , Weisong Sun , Yinxing Xue

Backdoor attacks inject poisoning samples during training, with the goal of forcing a machine learning model to output an attacker-chosen class when presented a specific trigger at test time. Although backdoor attacks have been demonstrated…

LLMs produce harmful and undesirable behavior when trained on datasets containing even a small fraction of poisoned data. We demonstrate that GPT models remain vulnerable to fine-tuning on poisoned data, even when safeguarded by moderation…

Cryptography and Security · Computer Science 2025-07-18 Dillon Bowen , Brendan Murphy , Will Cai , David Khachaturov , Adam Gleave , Kellin Pelrine