English
Related papers

Related papers: Backdoor Samples Detection Based on Perturbation D…

200 papers

Existing research on training-time attacks for deep neural networks (DNNs), such as backdoors, largely assume that models are static once trained, and hidden backdoors trained into models remain active indefinitely. In practice, models are…

Cryptography and Security · Computer Science 2023-02-10 Huiying Li , Arjun Nitin Bhagoji , Yuxin Chen , Haitao Zheng , Ben Y. Zhao

In recent years, many backdoor attacks based on training data poisoning have been proposed. However, in practice, those backdoor attacks are vulnerable to image compressions. When backdoor instances are compressed, the feature of specific…

Computer Vision and Pattern Recognition · Computer Science 2023-05-26 Mingfu Xue , Xin Wang , Shichang Sun , Yushu Zhang , Jian Wang , Weiqiang Liu

Backdoor attacks pose a significant threat to the integrity of text classification models used in natural language processing. While several dirty-label attacks that achieve high attack success rates (ASR) have been proposed, clean-label…

Cryptography and Security · Computer Science 2025-08-25 Onur Alp Kirci , M. Emre Gursoy

Neural networks are often trained on proprietary datasets, making them attractive attack targets. We present a novel dataset extraction method leveraging an innovative training time backdoor attack, allowing a malicious federated learning…

Cryptography and Security · Computer Science 2025-12-19 Eden Luzon , Guy Amit , Roy Weiss , Torsten Kraub , Alexandra Dmitrienko , Yisroel Mirsky

While Deep Neural Networks (DNNs) excel in many tasks, the huge training resources they require become an obstacle for practitioners to develop their own models. It has become common to collect data from the Internet or hire a third party…

Machine Learning · Computer Science 2022-03-15 Pengfei Xia , Hongjing Niu , Ziqiang Li , Bin Li

Backdoor attack injects malicious behavior to models such that inputs embedded with triggers are misclassified to a target label desired by the attacker. However, natural features may behave like triggers, causing misclassification once…

Machine Learning · Computer Science 2021-03-18 Yingqi Liu , Guangyu Shen , Guanhong Tao , Zhenting Wang , Shiqing Ma , Xiangyu Zhang

Backdoor attacks on deep learning represent a recent threat that has gained significant attention in the research community. Backdoor defenses are mainly based on backdoor inversion, which has been shown to be generic, model-agnostic, and…

Machine Learning · Computer Science 2024-11-11 Xiaoyun Xu , Zhuoran Liu , Stefanos Koffas , Shujian Yu , Stjepan Picek

With the swift advancement of deep learning, state-of-the-art algorithms have been utilized in various social situations. Nonetheless, some algorithms have been discovered to exhibit biases and provide unequal results. The current debiasing…

Machine Learning · Computer Science 2024-07-02 Shangxi Wu , Qiuyang He , Jian Yu , Jitao Sang

Backdoor attacks allow an attacker to embed functionality jeopardizing proper behavior of any algorithm, machine learning or not. This hidden functionality can remain inactive for normal use of the algorithm until activated by the attacker.…

Computer Vision and Pattern Recognition · Computer Science 2022-08-23 Alexander Unnervik , Sébastien Marcel

Backdoor attacks against CNNs represent a new threat against deep learning systems, due to the possibility of corrupting the training set so to induce an incorrect behaviour at test time. To avoid that the trainer recognises the presence of…

Cryptography and Security · Computer Science 2019-03-01 Mauro Barni , Kassem Kallas , Benedetta Tondi

Transferable backdoors pose a severe threat to the Pre-trained Language Models (PLMs) supply chain, yet defensive research remains nascent, primarily relying on detecting anomalies in the output feature space. We identify a critical flaw…

Cryptography and Security · Computer Science 2025-12-09 Tianhang Zhao , Wei Du , Haodong Zhao , Sufeng Duan , Gongshen Liu

While machine learning (ML) models are being increasingly trusted to make decisions in different and varying areas, the safety of systems using such models has become an increasing concern. In particular, ML models are often trained on data…

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

In this paper we investigate the frequency sensitivity of Deep Neural Networks (DNNs) when presented with clean samples versus poisoned samples. Our analysis shows significant disparities in frequency sensitivity between these two types of…

Cryptography and Security · Computer Science 2023-03-24 Hasan Abed Al Kader Hammoud , Adel Bibi , Philip H. S. Torr , Bernard Ghanem

Backdoor data poisoning, inserted within instruction examples used to fine-tune a foundation Large Language Model (LLM) for downstream tasks (\textit{e.g.,} sentiment prediction), is a serious security concern due to the evasive nature of…

Cryptography and Security · Computer Science 2024-08-23 Jayaram Raghuram , George Kesidis , David J. Miller

Backdoor attack has emerged as a major security threat to deep neural networks (DNNs). While existing defense methods have demonstrated promising results on detecting or erasing backdoors, it is still not clear whether robust training…

Machine Learning · Computer Science 2021-12-02 Yige Li , Xixiang Lyu , Nodens Koren , Lingjuan Lyu , Bo Li , Xingjun Ma

It is commonplace to produce application-specific models by fine-tuning large pre-trained models using a small bespoke dataset. The widespread availability of foundation model checkpoints on the web poses considerable risks, including the…

Cryptography and Security · Computer Science 2024-04-02 Yuxin Wen , Leo Marchyok , Sanghyun Hong , Jonas Geiping , Tom Goldstein , Nicholas Carlini

Text-to-image diffusion models have been widely adopted in real-world applications due to their ability to generate realistic images from textual descriptions. However, recent studies have shown that these methods are vulnerable to backdoor…

Computer Vision and Pattern Recognition · Computer Science 2024-08-29 Oscar Chew , Po-Yi Lu , Jayden Lin , Hsuan-Tien Lin

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

Deep neural networks are highly susceptible to backdoor attacks, yet most defense methods to date rely on balanced data, overlooking the pervasive class imbalance in real-world scenarios that can amplify backdoor threats. This paper…

Cryptography and Security · Computer Science 2026-02-03 Miao Lin , Feng Yu , Rui Ning , Lusi Li , Jiawei Chen , Qian Lou , Mengxin Zheng , Chunsheng Xin , Hongyi Wu