English
Related papers

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

200 papers

Backdoor attacks, in which a model behaves maliciously when given an attacker-specified trigger, pose a major security risk for practitioners who depend on publicly released language models. As a countermeasure, backdoor detection methods…

Computation and Language · Computer Science 2025-09-23 Jun Yan , Wenjie Jacky Mo , Xiang Ren , Robin Jia

Pre-trained language models allowed us to process downstream tasks with the help of fine-tuning, which aids the model to achieve fairly high accuracy in various Natural Language Processing (NLP) tasks. Such easily-downloaded language models…

Computation and Language · Computer Science 2022-11-22 Jaechul Roh , Minhao Cheng , Yajun Fang

Semi-supervised learning methods can train high-accuracy machine learning models with a fraction of the labeled training samples required for traditional supervised learning. Such methods do not typically involve close review of the…

Machine Learning · Computer Science 2022-12-07 Marissa Connor , Vincent Emanuele

Recently, a special type of data poisoning (DP) attack targeting Deep Neural Network (DNN) classifiers, known as a backdoor, was proposed. These attacks do not seek to degrade classification accuracy, but rather to have the classifier learn…

Machine Learning · Computer Science 2020-08-20 Zhen Xiang , David J. Miller , George Kesidis

Etremely Weakly Supervised Text Classification (XWS-TC) refers to text classification based on minimal high-level human guidance, such as a few label-indicative seed words or classification instructions. There are two mainstream approaches…

Computation and Language · Computer Science 2023-05-23 Zihan Wang , Tianle Wang , Dheeraj Mekala , Jingbo Shang

Backdoor attacks are emerging threats to deep neural networks, which typically embed malicious behaviors into a victim model by injecting poisoned samples. Adversaries can activate the injected backdoor during inference by presenting the…

Cryptography and Security · Computer Science 2025-12-05 Bingyin Zhao , Yingjie Lao

\textbf{P}re-\textbf{T}rained \textbf{M}odel\textbf{s} have been widely applied and recently proved vulnerable under backdoor attacks: the released pre-trained weights can be maliciously poisoned with certain triggers. When the triggers are…

Cryptography and Security · Computer Science 2021-09-01 Linyang Li , Demin Song , Xiaonan Li , Jiehang Zeng , Ruotian Ma , Xipeng Qiu

Backdoor attacks change a small portion of training data by introducing hand-crafted triggers and rewiring the corresponding labels towards a desired target class. Training on such data injects a backdoor which causes malicious inference in…

Machine Learning · Computer Science 2024-09-05 Ivan Sabolić , Ivan Grubišić , Siniša Šegvić

Deep learning models have recently shown to be vulnerable to backdoor poisoning, an insidious attack where the victim model predicts clean images correctly but classifies the same images as the target class when a trigger poison pattern is…

Computer Vision and Pattern Recognition · Computer Science 2019-11-20 Alvin Chan , Yew-Soon Ong

Backdoor attacks manipulate model predictions by inserting innocuous triggers into training and test data. We focus on more realistic and more challenging clean-label attacks where the adversarial training examples are correctly labeled.…

Machine Learning · Computer Science 2023-10-31 Wencong You , Zayd Hammoudeh , Daniel Lowd

With the thriving of deep learning and the widespread practice of using pre-trained networks, backdoor attacks have become an increasing security threat drawing many research interests in recent years. A third-party model can be poisoned in…

Cryptography and Security · Computer Science 2021-03-05 Anh Nguyen , Anh Tran

Backdoor attacks have become an emerging threat to NLP systems. By providing poisoned training data, the adversary can embed a "backdoor" into the victim model, which allows input instances satisfying certain textual patterns (e.g.,…

Computation and Language · Computer Science 2023-05-30 Jun Yan , Vansh Gupta , Xiang Ren

Pre-trained language models have achieved remarkable success across a wide range of natural language processing (NLP) tasks, particularly when fine-tuned on large, domain-relevant datasets. However, they remain vulnerable to backdoor…

Computation and Language · Computer Science 2026-02-02 Anindya Sundar Das , Kangjie Chen , Monowar Bhuyan

Recent adversarial defense approaches have failed. Untargeted gradient-based attacks cause classifiers to choose any wrong class. Our novel white-box defense tricks untargeted attacks into becoming attacks targeted at designated target…

Machine Learning · Computer Science 2020-06-09 Blerta Lindqvist

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

It has been proved that deep neural networks are facing a new threat called backdoor attacks, where the adversary can inject backdoors into the neural network model through poisoning the training dataset. When the input containing some…

Cryptography and Security · Computer Science 2021-03-16 Chuanshuai Chen , Jiazhu Dai

As machine learning (ML) classifiers increasingly oversee the automated monitoring of network traffic, studying their resilience against adversarial attacks becomes critical. This paper focuses on poisoning attacks, specifically backdoor…

Cryptography and Security · Computer Science 2023-06-05 Giorgio Severi , Simona Boboila , Alina Oprea , John Holodnak , Kendra Kratkiewicz , Jason Matterer

We introduce a method for unsupervised parsing that relies on bootstrapping classifiers to identify if a node dominates a specific span in a sentence. There are two types of classifiers, an inside classifier that acts on a span, and an…

Computation and Language · Computer Science 2022-03-22 Nickil Maveli , Shay B. Cohen

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

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