English
Related papers

Related papers: Silent Killer: A Stealthy, Clean-Label, Black-Box …

200 papers

This paper proposes a data-efficient detection method for deep neural networks against backdoor attacks under a black-box scenario. The proposed approach is motivated by the intuition that features corresponding to triggers have a higher…

Cryptography and Security · Computer Science 2023-07-20 Hao Fu , Prashanth Krishnamurthy , Siddharth Garg , Farshad Khorrami

Deep neural networks (DNNs) are vulnerable to the \emph{backdoor attack}, which intends to embed hidden backdoors in DNNs by poisoning training data. The attacked model behaves normally on benign samples, whereas its prediction will be…

Cryptography and Security · Computer Science 2021-04-06 Yiming Li , Yanjie Li , Yalei Lv , Yong Jiang , Shu-Tao Xia

We study the problem of attacking a machine learning model in the hard-label black-box setting, where no model information is revealed except that the attacker can make queries to probe the corresponding hard-label decisions. This is a very…

Machine Learning · Computer Science 2018-07-13 Minhao Cheng , Thong Le , Pin-Yu Chen , Jinfeng Yi , Huan Zhang , Cho-Jui Hsieh

Deep learning systems, critical in domains like autonomous vehicles, are vulnerable to adversarial examples (crafted inputs designed to mislead classifiers). This study investigates black-box adversarial attacks in computer vision. This is…

Cryptography and Security · Computer Science 2025-06-09 Francesco Panebianco , Mario D'Onghia , Stefano Zanero aand Michele Carminati

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

We investigate security concerns of the emergent instruction tuning paradigm, that models are trained on crowdsourced datasets with task instructions to achieve superior performance. Our studies demonstrate that an attacker can inject…

Computation and Language · Computer Science 2024-04-04 Jiashu Xu , Mingyu Derek Ma , Fei Wang , Chaowei Xiao , Muhao Chen

Recent research has found that neural networks are vulnerable to several types of adversarial attacks, where the input samples are modified in such a way that the model produces a wrong prediction that misclassifies the adversarial sample.…

Machine Learning · Computer Science 2022-10-07 Jary Pomponi , Simone Scardapane , Aurelio Uncini

Black-box finetuning is an emerging interface for adapting state-of-the-art language models to user needs. However, such access may also let malicious actors undermine model safety. To demonstrate the challenge of defending finetuning…

Cryptography and Security · Computer Science 2024-07-01 Danny Halawi , Alexander Wei , Eric Wallace , Tony T. Wang , Nika Haghtalab , Jacob Steinhardt

In a backdoor attack, an attacker injects corrupted examples into the training set. The goal of the attacker is to cause the final trained model to predict the attacker's desired target label when a predefined trigger is added to test…

Machine Learning · Computer Science 2022-10-13 Jonathan Hayase , Sewoong Oh

Backdoor attacks in machine learning have drawn significant attention for their potential to compromise models stealthily, yet most research has focused on homogeneous data such as images. In this work, we propose a novel backdoor attack on…

Machine Learning · Computer Science 2025-11-11 Behrad Tajalli , Stefanos Koffas , Stjepan Picek

Deep learning models are increasingly used in mobile applications as critical components. Unlike the program bytecode whose vulnerabilities and threats have been widely-discussed, whether and how the deep learning models deployed in the…

Cryptography and Security · Computer Science 2021-01-19 Yuanchun Li , Jiayi Hua , Haoyu Wang , Chunyang Chen , Yunxin Liu

Graph Convolutional Networks (GCNs) have shown excellent performance in dealing with various graph structures such as node classification, graph classification and other tasks. However,recent studies have shown that GCNs are vulnerable to a…

Artificial Intelligence · Computer Science 2024-04-22 Jiazhu Dai , Haoyu Sun

Neural text ranking models have witnessed significant advancement and are increasingly being deployed in practice. Unfortunately, they also inherit adversarial vulnerabilities of general neural models, which have been detected but remain…

Information Retrieval · Computer Science 2023-04-19 Jiawei Liu , Yangyang Kang , Di Tang , Kaisong Song , Changlong Sun , Xiaofeng Wang , Wei Lu , Xiaozhong Liu

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

Backdoor attacks impose a new threat in Deep Neural Networks (DNNs), where a backdoor is inserted into the neural network by poisoning the training dataset, misclassifying inputs that contain the adversary trigger. The major challenge for…

Machine Learning · Computer Science 2024-09-26 Yue Wang , Wenqing Li , Esha Sarkar , Muhammad Shafique , Michail Maniatakos , Saif Eddin Jabari

Backdoor attacks on deep neural networks have emerged as significant security threats, especially as DNNs are increasingly deployed in security-critical applications. However, most existing works assume that the attacker has access to the…

Cryptography and Security · Computer Science 2024-08-22 Jiahao Wang , Xianglong Zhang , Xiuzhen Cheng , Pengfei Hu , Guoming Zhang

Active learning(AL), which serves as the representative label-efficient learning paradigm, has been widely applied in resource-constrained scenarios. The achievement of AL is attributed to acquisition functions, which are designed for…

Cryptography and Security · Computer Science 2025-08-11 Yuhan Zhi , Longtian Wang , Xiaofei Xie , Chao Shen , Qiang Hu , Xiaohong Guan

Backdoor attacks mislead machine-learning models to output an attacker-specified class when presented a specific trigger at test time. These attacks require poisoning the training data to compromise the learning algorithm, e.g., by…

Machine Learning · Computer Science 2021-11-03 Kathrin Grosse , Taesung Lee , Battista Biggio , Youngja Park , Michael Backes , Ian Molloy

The notion that collaborative machine learning can ensure privacy by just withholding the raw data is widely acknowledged to be flawed. Over the past seven years, the literature has revealed several privacy attacks that enable adversaries…

Cryptography and Security · Computer Science 2024-09-27 Federico Mazzone , Ahmad Al Badawi , Yuriy Polyakov , Maarten Everts , Florian Hahn , Andreas Peter

Gathering enough images to train a deep computer vision model is a constant challenge. Unfortunately, collecting images from unknown sources can leave your model s behavior at risk of being manipulated by a dirty-label or clean-label attack…

Computer Vision and Pattern Recognition · Computer Science 2025-06-05 John W. Smutny