English
Related papers

Related papers: Pruning Strategies for Backdoor Defense in LLMs

200 papers

The advent of multimodal deep learning models, such as CLIP, has unlocked new frontiers in a wide range of applications, from image-text understanding to classification tasks. However, these models are not safe for adversarial attacks,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Md. Iqbal Hossain , Afia Sajeeda , Neeresh Kumar Perla , Ming Shao

Fine-tuned Large Language Models (LLMs) are vulnerable to backdoor attacks through data poisoning, yet the internal mechanisms governing these attacks remain a black box. Previous research on interpretability for LLM safety tends to focus…

Cryptography and Security · Computer Science 2025-10-01 Miao Yu , Zhenhong Zhou , Moayad Aloqaily , Kun Wang , Biwei Huang , Stephen Wang , Yueming Jin , Qingsong Wen

Backdoors implanted in pre-trained language models (PLMs) can be transferred to various downstream tasks, which exposes a severe security threat. However, most existing backdoor attacks against PLMs are un-targeted and task-specific. Few…

Computation and Language · Computer Science 2024-12-20 Wei Du , Peixuan Li , Boqun Li , Haodong Zhao , Gongshen Liu

Despite the strong multimodal performance, large vision-language models (LVLMs) are vulnerable during fine-tuning to backdoor attacks, where adversaries insert trigger-embedded samples into the training data to implant behaviors that can be…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Zhifang Zhang , Bojun Yang , Shuo He , Weitong Chen , Wei Emma Zhang , Olaf Maennel , Lei Feng , Miao Xu

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

Fine-tuning has emerged as a critical process in leveraging Large Language Models (LLMs) for specific downstream tasks, enabling these models to achieve state-of-the-art performance across various domains. However, the fine-tuning process…

Artificial Intelligence · Computer Science 2025-04-08 Hao Du , Shang Liu , Lele Zheng , Yang Cao , Atsuyoshi Nakamura , Lei Chen

Backdoor attacks, which maliciously control a well-trained model's outputs of the instances with specific triggers, are recently shown to be serious threats to the safety of reusing deep neural networks (DNNs). In this work, we propose an…

Computation and Language · Computer Science 2021-10-18 Wenkai Yang , Yankai Lin , Peng Li , Jie Zhou , Xu Sun

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

Backdoor attacks pose a significant threat to the integrity and reliability of Artificial Intelligence (AI) models, enabling adversaries to manipulate model behavior by injecting poisoned data with hidden triggers. These attacks can lead to…

Machine Learning · Computer Science 2026-03-31 Osama Wehbi , Sarhad Arisdakessian , Omar Abdel Wahab , Azzam Mourad , Hadi Otrok , Jamal Bentahar

Deep neural networks (DNNs) and natural language processing (NLP) systems have developed rapidly and have been widely used in various real-world fields. However, they have been shown to be vulnerable to backdoor attacks. Specifically, the…

Computation and Language · Computer Science 2023-01-26 Jiali Wei , Ming Fan , Wenjing Jiao , Wuxia Jin , Ting Liu

Backdoor attacks pose a significant threat to Deep Neural Networks (DNNs) as they allow attackers to manipulate model predictions with backdoor triggers. To address these security vulnerabilities, various backdoor purification methods have…

Machine Learning · Computer Science 2024-10-17 Rui Min , Zeyu Qin , Nevin L. Zhang , Li Shen , Minhao Cheng

Large language models (LLMs) are increasingly deployed in settings where inducing a bias toward a certain topic can have significant consequences, and backdoor attacks can be used to produce such models. Prior work on backdoor attacks has…

Cryptography and Security · Computer Science 2026-02-17 Anudeep Das , Prach Chantasantitam , Gurjot Singh , Lipeng He , Mariia Ponomarenko , Florian Kerschbaum

As large language models are increasingly deployed in sensitive environments, fingerprinting attacks pose significant privacy and security risks. We present a study of LLM fingerprinting from both offensive and defensive perspectives. Our…

Cryptography and Security · Computer Science 2025-08-13 Kevin Kurian , Ethan Holland , Sean Oesch

Deep neural networks have been widely used in many critical applications, such as autonomous vehicles and medical diagnosis. However, their security is threatened by backdoor attacks, which are achieved by adding artificial patterns to…

Machine Learning · Computer Science 2024-02-26 Dong Huang , Qingwen Bu

Neural network pruning has been an essential technique to reduce the computation and memory requirements for using deep neural networks for resource-constrained devices. Most existing research focuses primarily on balancing the sparsity and…

Cryptography and Security · Computer Science 2022-08-05 Xiaoyong Yuan , Lan Zhang

Large language models have been shown to memorize significant portions of their training data, which they can reproduce when appropriately prompted. This work investigates the impact of simple pruning techniques on this behavior. Our…

Machine Learning · Computer Science 2025-02-25 Mansi Gupta , Nikhar Waghela , Sarthak Gupta , Shourya Goel , Sanjif Shanmugavelu

Backdoor attacks pose a significant threat to neural networks, enabling adversaries to manipulate model outputs on specific inputs, often with devastating consequences, especially in critical applications. While backdoor attacks have been…

Machine Learning · Computer Science 2025-07-30 Zhen Guo , Abhinav Kumar , Reza Tourani

Backdoor attacks pose a new threat to NLP models. A standard strategy to construct poisoned data in backdoor attacks is to insert triggers (e.g., rare words) into selected sentences and alter the original label to a target label. This…

Computation and Language · Computer Science 2022-04-28 Leilei Gan , Jiwei Li , Tianwei Zhang , Xiaoya Li , Yuxian Meng , Fei Wu , Yi Yang , Shangwei Guo , Chun Fan

The vulnerability of deep neural networks against adversarial examples - inputs with small imperceptible perturbations - has gained a lot of attention in the research community recently. Simultaneously, the number of parameters of…

Machine Learning · Computer Science 2021-08-20 Florian Merkle , Maximilian Samsinger , Pascal Schöttle

Backdoor attacks compromise model reliability by using triggers to manipulate outputs. Trigger inversion can accurately locate these triggers via a generator and is therefore critical for backdoor defense. However, the discrete nature of…

Cryptography and Security · Computer Science 2026-03-18 Ruyi Zhang , Heng Gao , Songlei Jian , Yusong Tan , Haifang Zhou
‹ Prev 1 3 4 5 6 7 10 Next ›