English
Related papers

Related papers: Backdoor Sentinel: Detecting and Detoxifying Backd…

200 papers

Diffusion models have attracted significant attention due to its exceptional data generation capabilities in fields such as image synthesis. However, recent studies have shown that diffusion models are vulnerable to copyright infringement…

Artificial Intelligence · Computer Science 2025-08-22 Zhixiang Guo , Siyuan Liang , Aishan Liu , Dacheng Tao

Backdoor attacks pose a significant threat when using third-party data for deep learning development. In these attacks, data can be manipulated to cause a trained model to behave improperly when a specific trigger pattern is applied,…

Computer Vision and Pattern Recognition · Computer Science 2024-09-05 Abdullah Arafat Miah , Kaan Icer , Resit Sendag , Yu Bi

A variety of defenses have been proposed against Trojans planted in (backdoor attacks on) deep neural network (DNN) classifiers. Backdoor-agnostic methods seek to reliably detect and/or to mitigate backdoors irrespective of the…

Cryptography and Security · Computer Science 2025-03-10 Guangmingmei Yang , Xi Li , Hang Wang , David J. Miller , George Kesidis

The security threat of backdoor attacks is a central concern for deep neural networks (DNNs). Recently, without poisoned data, unlearning models with clean data and then learning a pruning mask have contributed to backdoor defense.…

Cryptography and Security · Computer Science 2024-05-31 Weilin Lin , Li Liu , Shaokui Wei , Jianze Li , Hui Xiong

Backdoor attacks, which maliciously control a well-trained model's outputs of the instances with specific triggers, are recently shown to be serious threats to the safety of reusing deep neural networks (DNNs). In this work, we propose an…

Computation and Language · Computer Science 2021-10-18 Wenkai Yang , Yankai Lin , Peng Li , Jie Zhou , Xu Sun

The success of deep neural networks (DNNs) in real-world applications has benefited from abundant pre-trained models. However, the backdoored pre-trained models can pose a significant trojan threat to the deployment of downstream DNNs.…

Cryptography and Security · Computer Science 2024-07-18 Haibo Jin , Ruoxi Chen , Jinyin Chen , Haibin Zheng , Yang Zhang , Haohan Wang

In recent years, some researchers have applied diffusion models to multivariate time series anomaly detection. The partial diffusion strategy, which depends on the diffusion steps, is commonly used for anomaly detection in these models.…

Machine Learning · Computer Science 2025-01-06 Guangqiang Wu , Fu Zhang

While language models have made many milestones in text inference and classification tasks, they remain susceptible to adversarial attacks that can lead to unforeseen outcomes. Existing works alleviate this problem by equipping language…

Computation and Language · Computer Science 2024-01-10 Shilong Yuan , Wei Yuan , Hongzhi Yin , Tieke He

Deep neural networks have been demonstrated to be vulnerable to backdoor attacks. Specifically, by injecting a small number of maliciously constructed inputs into the training set, an adversary is able to plant a backdoor into the trained…

Machine Learning · Statistics 2019-12-10 Alexander Turner , Dimitris Tsipras , Aleksander Madry

We propose a novel and effective purification based adversarial defense method against pre-processor blind white- and black-box attacks. Our method is computationally efficient and trained only with self-supervised learning on general…

Computer Vision and Pattern Recognition · Computer Science 2022-01-03 Sungmin Cha , Naeun Ko , Youngjoon Yoo , Taesup Moon

Spiking Neural Networks (SNNs) have gained increasing attention for their superior energy efficiency compared to Artificial Neural Networks (ANNs). However, their security aspects, particularly under backdoor attacks, have received limited…

Cryptography and Security · Computer Science 2025-10-09 Jiachen Li , Bang Wu , Xiaoyu Xia , Xiaoning Liu , Xun Yi , Xiuzhen Zhang

Learning with noisy labels, which aims to reduce expensive labors on accurate annotations, has become imperative in the Big Data era. Previous noise transition based method has achieved promising results and presented a theoretical…

Machine Learning · Computer Science 2021-08-24 Jiangchao Yao , Ya Zhang , Ivor W. Tsang , Jun Sun

Cloud networks increasingly rely on machine learning based Network Intrusion Detection Systems to defend against evolving cyber threats. However, real-world deployments are challenged by limited labeled data, non-stationary traffic, and…

Machine Learning · Computer Science 2026-04-15 Anasuya Chattopadhyay , Daniel Reti , Hans D. Schotten

Audio DeepFakes allow the creation of high-quality, convincing utterances and therefore pose a threat due to its potential applications such as impersonation or fake news. Methods for detecting these manipulations should be characterized by…

Sound · Computer Science 2022-10-13 Piotr Kawa , Marcin Plata , Piotr Syga

Collaborative inference of object classification Deep neural Networks (DNNs) where resource-constrained end-devices offload partially processed data to remote edge servers to complete end-to-end processing, is becoming a key enabler of…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Shima Yousefi , Saptarshi Debroy

Recent studies revealed that deep learning is susceptible to backdoor poisoning attacks. An adversary can embed a hidden backdoor into a model to manipulate its predictions by only modifying a few training data, without controlling the…

Machine Learning · Computer Science 2023-03-07 Xiangyu Qi , Tinghao Xie , Yiming Li , Saeed Mahloujifar , Prateek Mittal

Deep Neural Networks (DNNs) are susceptible to backdoor attacks, where adversaries poison training data to implant backdoor into the victim model. Current backdoor defenses on poisoned data often suffer from high computational costs or low…

Multimedia · Computer Science 2025-07-28 Binyan Xu , Fan Yang , Xilin Dai , Di Tang , Kehuan Zhang

With wider application of deep neural networks (DNNs) in various algorithms and frameworks, security threats have become one of the concerns. Adversarial attacks disturb DNN-based image classifiers, in which attackers can intentionally add…

Computer Vision and Pattern Recognition · Computer Science 2022-06-30 Jinyi Wang , Zhaoyang Lyu , Dahua Lin , Bo Dai , Hongfei Fu

Voice spoofing attacks pose a significant threat to automated speaker verification systems. Existing anti-spoofing methods often simulate specific attack types, such as synthetic or replay attacks. However, in real-world scenarios, the…

Sound · Computer Science 2023-09-19 Awais Khan , Khalid Mahmood Malik , Shah Nawaz

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