English
Related papers

Related papers: Efficient Trigger Word Insertion

200 papers

Clean-label (CL) attack is a form of data poisoning attack where an adversary modifies only the textual input of the training data, without requiring access to the labeling function. CL attacks are relatively unexplored in NLP, as compared…

Computation and Language · Computer Science 2023-06-01 Ashim Gupta , Amrith Krishna

Due to the prosperity of Artificial Intelligence (AI) techniques, more and more backdoors are designed by adversaries to attack Deep Neural Networks (DNNs).Although the state-of-the-art method Neural Attention Distillation (NAD) can…

Machine Learning · Computer Science 2022-04-26 Jun Xia , Ting Wang , Jiepin Ding , Xian Wei , Mingsong Chen

Contrastive Learning (CL) has attracted enormous attention due to its remarkable capability in unsupervised representation learning. However, recent works have revealed the vulnerability of CL to backdoor attacks: the feature extractor…

Cryptography and Security · Computer Science 2024-04-12 Weiyu Sun , Xinyu Zhang , Hao Lu , Yingcong Chen , Ting Wang , Jinghui Chen , Lu Lin

Backdoor (Trojan) attacks are an important type of adversarial exploit against deep neural networks (DNNs), wherein a test instance is (mis)classified to the attacker's target class whenever the attacker's backdoor trigger is present. In…

Machine Learning · Computer Science 2023-08-22 Xi Li , Zhen Xiang , David J. Miller , George Kesidis

Reinforcement learning (RL) is an actively growing field that is seeing increased usage in real-world, safety-critical applications -- making it paramount to ensure the robustness of RL algorithms against adversarial attacks. In this work…

Machine Learning · Computer Science 2024-10-22 Ethan Rathbun , Christopher Amato , Alina Oprea

Backdoor attacks represent a serious threat to neural network models. A backdoored model will misclassify the trigger-embedded inputs into an attacker-chosen target label while performing normally on other benign inputs. There are already…

Machine Learning · Computer Science 2021-07-14 Jing Xu , Minhui , Xue , Stjepan Picek

Modern language models remain vulnerable to backdoor attacks via poisoned data, where training inputs containing a trigger are paired with a target output, causing the model to reproduce that behavior whenever the trigger appears at…

Cryptography and Security · Computer Science 2026-01-06 Eric Xue , Ruiyi Zhang , Pengtao Xie

Backdoor poisoning attacks pose a well-known risk to neural networks. However, most studies have focused on lenient threat models. We introduce Silent Killer, a novel attack that operates in clean-label, black-box settings, uses a stealthy…

Cryptography and Security · Computer Science 2023-10-03 Tzvi Lederer , Gallil Maimon , Lior Rokach

Interpretability is crucial to understand the inner workings of deep neural networks (DNNs) and many interpretation methods generate saliency maps that highlight parts of the input image that contribute the most to the prediction made by…

Cryptography and Security · Computer Science 2022-07-21 Shihong Fang , Anna Choromanska

Backdoor data detection is traditionally studied in an end-to-end supervised learning (SL) setting. However, recent years have seen the proliferating adoption of self-supervised learning (SSL) and transfer learning (TL), due to their lesser…

Machine Learning · Computer Science 2023-08-08 Minzhou Pan , Yi Zeng , Lingjuan Lyu , Xue Lin , Ruoxi Jia

Graph Neural Networks (GNNs) have achieved remarkable results in various tasks. Recent studies reveal that graph backdoor attacks can poison the GNN model to predict test nodes with triggers attached as the target class. However, apart from…

Machine Learning · Computer Science 2026-04-15 Yuxiang Zhang , Bin Ma , Enyan Dai

Backdoor attacks on text classifiers can cause them to predict a predefined label when a particular "trigger" is present. Prior attacks often rely on triggers that are ungrammatical or otherwise unusual, leading to conspicuous attacks. As a…

Machine Learning · Computer Science 2025-04-25 Wencong You , Daniel Lowd

Because state-of-the-art language models are expensive to train, most practitioners must make use of one of the few publicly available language models or language model APIs. This consolidation of trust increases the potency of backdoor…

Cryptography and Security · Computer Science 2023-07-28 Nikhil Kandpal , Matthew Jagielski , Florian Tramèr , Nicholas Carlini

Federated learning security research has predominantly focused on backdoor threats from a minority of malicious clients that intentionally corrupt model updates. This paper challenges this paradigm by investigating a more pervasive and…

Cryptography and Security · Computer Science 2026-02-18 Haodong Zhao , Jinming Hu , Gongshen Liu

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…

Textual backdoor attacks are a kind of practical threat to NLP systems. By injecting a backdoor in the training phase, the adversary could control model predictions via predefined triggers. As various attack and defense models have been…

Machine Learning · Computer Science 2022-11-02 Ganqu Cui , Lifan Yuan , Bingxiang He , Yangyi Chen , Zhiyuan Liu , Maosong Sun

Two widely used techniques for training supervised machine learning models on small datasets are Active Learning and Transfer Learning. The former helps to optimally use a limited budget to label new data. The latter uses large pre-trained…

Machine Learning · Computer Science 2021-01-28 Nicolas M. Müller , Konstantin Böttinger

Backdoor vulnerabilities widely exist in the fine-tuning of large language models(LLMs). Most backdoor poisoning methods operate mainly at the token level and lack deeper semantic manipulation, which limits stealthiness. In addition, Prior…

Computation and Language · Computer Science 2026-05-13 Ziyu Liu , Tao Li , Tianjie Ni , Xiaolong Lan , Wengang Ma , Tao Yang , Guohua Wang , Junjiang He

Web-scraped datasets are vulnerable to data poisoning, which can be used for backdooring deep image classifiers during training. Since training on large datasets is expensive, a model is trained once and re-used many times. Unlike…

Machine Learning · Computer Science 2024-01-23 Benjamin Schneider , Nils Lukas , Florian Kerschbaum

\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