English
Related papers

Related papers: WeDef: Weakly Supervised Backdoor Defense for Text…

200 papers

Natural language processing (NLP) models are known to be vulnerable to backdoor attacks, which poses a newly arisen threat to NLP models. Prior online backdoor defense methods for NLP models only focus on the anomalies at either the input…

Computation and Language · Computer Science 2022-10-17 Sishuo Chen , Wenkai Yang , Zhiyuan Zhang , Xiaohan Bi , Xu Sun

Federated Learning (FL) is a distributed learning paradigm that enables different parties to train a model together for high quality and strong privacy protection. In this scenario, individual participants may get compromised and perform…

Cryptography and Security · Computer Science 2023-03-01 Kaiyuan Zhang , Guanhong Tao , Qiuling Xu , Siyuan Cheng , Shengwei An , Yingqi Liu , Shiwei Feng , Guangyu Shen , Pin-Yu Chen , Shiqing Ma , Xiangyu Zhang

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

Despite recent progress in backdoor attacks, existing methods remain susceptible to post-training defenses that erase the backdoor through fine-tuning or pruning. We revisit the core objectives of backdoor attacks and derive principled…

Machine Learning · Computer Science 2026-05-29 Qiyuan Wang , Yao Li , Raymond K. W. Wong

Few-shot classification with foundation models (e.g., CLIP, DINOv2, PaLM-2) enables users to build an accurate classifier with a few labeled training samples (called support samples) for a classification task. However, an attacker could…

Cryptography and Security · Computer Science 2024-04-15 Yanting Wang , Wei Zou , Jinyuan Jia

Semi-supervised machine learning models learn from a (small) set of labeled training examples, and a (large) set of unlabeled training examples. State-of-the-art models can reach within a few percentage points of fully-supervised training,…

Machine Learning · Computer Science 2021-08-11 Nicholas Carlini

Data poisoning attacks are a potential threat to machine learning (ML) models, aiming to manipulate training datasets to disrupt their performance. Existing defenses are mostly designed to mitigate specific poisoning attacks or are aligned…

Cryptography and Security · Computer Science 2025-10-28 Anum Paracha , Junaid Arshad , Mohamed Ben Farah , Khalid Ismail

Backdoor attack against image classification task has been widely studied and proven to be successful, while there exist little research on the backdoor attack against vision-language models. In this paper, we explore backdoor attack…

Computer Vision and Pattern Recognition · Computer Science 2024-01-08 Meiling Li , Nan Zhong , Xinpeng Zhang , Zhenxing Qian , Sheng Li

Recent years have seen increasing concerns about the unsafe response generation of large-scale dialogue systems, where agents will learn offensive or biased behaviors from the real-world corpus. Some methods are proposed to address the…

Computation and Language · Computer Science 2023-05-26 Zi Liang , Pinghui Wang , Ruofei Zhang , Shuo Zhang , Xiaofan Ye Yi Huang , Junlan Feng

Adversarial examples are carefully constructed modifications to an input that completely change the output of a classifier but are imperceptible to humans. Despite these successful attacks for continuous data (such as image and audio…

Machine Learning · Computer Science 2019-04-08 Qi Lei , Lingfei Wu , Pin-Yu Chen , Alexandros G. Dimakis , Inderjit S. Dhillon , Michael Witbrock

Text-to-image diffusion models have revolutionized generative AI, but their vulnerability to backdoor attacks poses significant security risks. Adversaries can inject imperceptible textual triggers into training data, causing models to…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Ashwath Vaithinathan Aravindan , Abha Jha , Matthew Salaway , Atharva Sandeep Bhide , Duygu Nur Yaldiz

As a distributed machine learning paradigm, Federated Learning (FL) enables large-scale clients to collaboratively train a model without sharing their raw data. However, due to the lack of data auditing for untrusted clients, FL is…

Machine Learning · Computer Science 2025-09-10 Yanxin Yang , Ming Hu , Xiaofei Xie , Yue Cao , Pengyu Zhang , Yihao Huang , Mingsong Chen

Machine learning (ML) models that use deep neural networks are vulnerable to backdoor attacks. Such attacks involve the insertion of a (hidden) trigger by an adversary. As a consequence, any input that contains the trigger will cause the…

Cryptography and Security · Computer Science 2022-03-30 Arezoo Rajabi , Bhaskar Ramasubramanian , Radha Poovendran

Poisoning-based backdoor attacks pose significant threats to deep neural networks by embedding triggers in training data, causing models to misclassify triggered inputs as adversary-specified labels while maintaining performance on clean…

Cryptography and Security · Computer Science 2026-04-24 Yuchen Shi , Xin Guo , Huajie Chen , Tianqing Zhu , Bo Liu , Wanlei Zhou

Backdoor attacks are among the most effective, practical, and stealthy attacks in deep learning. In this paper, we consider a practical scenario where a developer obtains a deep model from a third party and uses it as part of a…

Cryptography and Security · Computer Science 2025-03-28 Dorde Popovic , Amin Sadeghi , Ting Yu , Sanjay Chawla , Issa Khalil

Text classification is the process of classifying documents into predefined categories based on their content. Existing supervised learning algorithms to automatically classify text need sufficient documents to learn accurately. This paper…

Neural and Evolutionary Computing · Computer Science 2010-09-27 S. M. Kamruzzaman , Farhana Haider

Defenses against security threats have been an interest of recent studies. Recent works have shown that it is not difficult to attack a natural language processing (NLP) model while defending against them is still a cat-mouse game. Backdoor…

Cryptography and Security · Computer Science 2022-05-31 Sangeet Sagar , Abhinav Bhatt , Abhijith Srinivas Bidaralli

Recently, backdoor attacks pose a new security threat to the training process of deep neural networks (DNNs). Attackers intend to inject hidden backdoors into DNNs, such that the attacked model performs well on benign samples, whereas its…

Cryptography and Security · Computer Science 2021-08-16 Yuezun Li , Yiming Li , Baoyuan Wu , Longkang Li , Ran He , Siwei Lyu

Weak supervision (WS) is a rich set of techniques that produce pseudolabels by aggregating easily obtained but potentially noisy label estimates from a variety of sources. WS is theoretically well understood for binary classification, where…

Machine Learning · Computer Science 2022-11-28 Harit Vishwakarma , Nicholas Roberts , Frederic Sala

Adversarial attacks have been a looming and unaddressed threat in the industry. However, through a decade-long history of the robustness evaluation literature, we have learned that mounting a strong or optimal attack is challenging. It…

Machine Learning · Computer Science 2024-03-19 Chawin Sitawarin , Jaewon Chang , David Huang , Wesson Altoyan , David Wagner