English
Related papers

Related papers: Defending Pre-trained Language Models as Few-shot …

200 papers

Machine learning models are vulnerable to data-poisoning attacks, in which an attacker maliciously modifies the training set to change the prediction of a learned model. In a trigger-less attack, the attacker can modify the training set but…

Machine Learning · Computer Science 2022-10-18 Yuhao Zhang , Aws Albarghouthi , Loris D'Antoni

Large Language Models (LLMs) are vulnerable to prompt injection attacks, and several defenses have recently been proposed, often claiming to mitigate these attacks successfully. However, we argue that existing studies lack a principled…

Cryptography and Security · Computer Science 2025-05-27 Yuqi Jia , Zedian Shao , Yupei Liu , Jinyuan Jia , Dawn Song , Neil Zhenqiang Gong

Large Language Models (LLMs) are increasingly popular, powering a wide range of applications. Their widespread use has sparked concerns, especially through jailbreak attacks that bypass safety measures to produce harmful content. In this…

Cryptography and Security · Computer Science 2025-12-25 Zhengchun Shang , Wenlan Wei , Weiheng Bai

Machine learning (ML) models are susceptible to various risks to security, privacy, and fairness. Most defenses are designed to protect against each risk individually (intended interactions) but can inadvertently affect susceptibility to…

Cryptography and Security · Computer Science 2025-11-10 Asim Waheed , Vasisht Duddu , Rui Zhang , Sebastian Szyller

Large Language Models (LLMs) are swiftly advancing in architecture and capability, and as they integrate more deeply into complex systems, the urgency to scrutinize their security properties grows. This paper surveys research in the…

Computation and Language · Computer Science 2023-10-18 Erfan Shayegani , Md Abdullah Al Mamun , Yu Fu , Pedram Zaree , Yue Dong , Nael Abu-Ghazaleh

Pre-trained Language Models (PLMs) have achieved remarkable performance for various language understanding tasks in IR systems, which require the fine-tuning process based on labeled training data. For low-resource scenarios, prompt-based…

Computation and Language · Computer Science 2022-04-04 Ziyun Xu , Chengyu Wang , Minghui Qiu , Fuli Luo , Runxin Xu , Songfang Huang , Jun Huang

Textual backdoor attacks present a substantial security risk to Large Language Models (LLM). It embeds carefully chosen triggers into a victim model at the training stage, and makes the model erroneously predict inputs containing the same…

Computation and Language · Computer Science 2024-07-08 Xinglin Li , Xianwen He , Yao Li , Minhao Cheng

Large Language Models (LLMs) have emerged as a dominant approach for a wide range of NLP tasks, with their access to external information further enhancing their capabilities. However, this introduces new vulnerabilities, known as prompt…

Computation and Language · Computer Science 2025-04-11 Ruiyi Zhang , David Sullivan , Kyle Jackson , Pengtao Xie , Mei Chen

Supervised fine-tuning has become the predominant method for adapting large pretrained models to downstream tasks. However, recent studies have revealed that these models are vulnerable to backdoor attacks, where even a small number of…

Cryptography and Security · Computer Science 2025-01-08 Peihai Jiang , Xixiang Lyu , Yige Li , Jing Ma

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

Recently, advanced NLP models have seen a surge in the usage of various applications. This raises the security threats of the released models. In addition to the clean models' unintentional weaknesses, {\em i.e.,} adversarial attacks, the…

Computation and Language · Computer Science 2021-01-18 Lichao Sun

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

Federated learning (FL) represents a novel paradigm to machine learning, addressing critical issues related to data privacy and security, yet suffering from data insufficiency and imbalance. The emergence of foundation models (FMs) provides…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-11-02 Xi Li , Songhe Wang , Chen Wu , Hao Zhou , Jiaqi Wang

Multimodal contrastive learning models (e.g., CLIP) can learn high-quality representations from large-scale image-text datasets, while they exhibit significant vulnerabilities to backdoor attacks, raising serious safety concerns. In this…

Computer Vision and Pattern Recognition · Computer Science 2025-10-31 Zhifang Zhang , Shuo He , Haobo Wang , Bingquan Shen , Lei Feng

The widespread adoption of Large Language Models (LLMs), exemplified by OpenAI's ChatGPT, brings to the forefront the imperative to defend against adversarial threats on these models. These attacks, which manipulate an LLM's output by…

Cryptography and Security · Computer Science 2025-04-04 Amelia Kawasaki , Andrew Davis , Houssam Abbas

Recent studies revealed that deep neural networks (DNNs) are exposed to backdoor threats when training with third-party resources (such as training samples or backbones). The backdoored model has promising performance in predicting benign…

Computer Vision and Pattern Recognition · Computer Science 2023-03-07 Chengxiao Luo , Yiming Li , Yong Jiang , Shu-Tao Xia

Federated learning allows multiple users to collaboratively train a shared classification model while preserving data privacy. This approach, where model updates are aggregated by a central server, was shown to be vulnerable to poisoning…

Machine Learning · Computer Science 2020-12-17 Chien-Lun Chen , Leana Golubchik , Marco Paolieri

Backdoor attacks become a significant security concern for deep neural networks in recent years. An image classification model can be compromised if malicious backdoors are injected into it. This corruption will cause the model to function…

Cryptography and Security · Computer Science 2024-03-13 Hongwei Zhang , Xiaoyin Xu , Dongsheng An , Xianfeng Gu , Min Zhang

Large-scale pre-trained language models have contributed significantly to natural language processing by demonstrating remarkable abilities as few-shot learners. However, their effectiveness depends mainly on scaling the model parameters…

Computation and Language · Computer Science 2023-01-26 Ningyu Zhang , Luoqiu Li , Xiang Chen , Shumin Deng , Zhen Bi , Chuanqi Tan , Fei Huang , Huajun Chen

Large pre-trained models have achieved notable success across a range of downstream tasks. However, recent research shows that a type of adversarial attack ($\textit{i.e.,}$ backdoor attack) can manipulate the behavior of machine learning…

Artificial Intelligence · Computer Science 2024-10-29 Dongliang Guo , Mengxuan Hu , Zihan Guan , Junfeng Guo , Thomas Hartvigsen , Sheng Li
‹ Prev 1 8 9 10 Next ›