English
Related papers

Related papers: Revisiting the Auxiliary Data in Backdoor Purifica…

200 papers

As collaborative learning and the outsourcing of data collection become more common, malicious actors (or agents) which attempt to manipulate the learning process face an additional obstacle as they compete with each other. In backdoor…

Machine Learning · Computer Science 2021-10-12 Siddhartha Datta , Giulio Lovisotto , Ivan Martinovic , Nigel Shadbolt

The advancement and adoption of Artificial Intelligence (AI) models across diverse domains have transformed the way we interact with technology. However, it is essential to recognize that while AI models have introduced remarkable…

Cryptography and Security · Computer Science 2025-05-07 Hema Karnam Surendrababu , Nithin Nagaraj

Real-world backdoor attacks often require poisoned datasets to be stored and transmitted before being used to compromise deep learning systems. However, in the era of big data, the inevitable use of lossy compression poses a fundamental…

Cryptography and Security · Computer Science 2026-05-18 Qian Li , Yunuo Chen , Yuntian Chen

Deep neural networks (DNNs) are susceptible to backdoor attacks, where adversaries poison datasets with adversary-specified triggers to implant hidden backdoors, enabling malicious manipulation of model predictions. Dataset purification…

Cryptography and Security · Computer Science 2025-06-24 Linshan Hou , Wei Luo , Zhongyun Hua , Songhua Chen , Leo Yu Zhang , Yiming Li

Dataset distillation offers a potential means to enhance data efficiency in deep learning. Recent studies have shown its ability to counteract backdoor risks present in original training samples. In this study, we delve into the theoretical…

Machine Learning · Computer Science 2025-06-03 Ming-Yu Chung , Sheng-Yen Chou , Chia-Mu Yu , Pin-Yu Chen , Sy-Yen Kuo , Tsung-Yi Ho

Backdoor attacks have emerged as one of the major security threats to deep learning models as they can easily control the model's test-time predictions by pre-injecting a backdoor trigger into the model at training time. While backdoor…

Machine Learning · Computer Science 2023-02-07 Yujing Jiang , Xingjun Ma , Sarah Monazam Erfani , James Bailey

Poison-only Clean-label Backdoor Attacks aim to covertly inject attacker-desired behavior into DNNs by merely poisoning the dataset without changing the labels. To effectively implant a backdoor, multiple \textbf{triggers} are proposed for…

Cryptography and Security · Computer Science 2025-10-08 Zhixiao Wu , Yao Lu , Jie Wen , Hao Sun , Qi Zhou , Guangming Lu

Backdoor attacks pose severe security threats to large language models (LLMs), where a model behaves normally under benign inputs but produces malicious outputs when a hidden trigger appears. Existing backdoor removal methods typically…

Cryptography and Security · Computer Science 2026-03-17 Jianwei Li , Jung-Eun Kim

Data poisoning is one of the most relevant security threats against machine learning and data-driven technologies. Since many applications rely on untrusted training data, an attacker can easily craft malicious samples and inject them into…

Cryptography and Security · Computer Science 2021-12-01 Nicolas M. Müller , Simon Roschmann , Konstantin Böttinger

Thanks to their remarkable denoising capabilities, diffusion models are increasingly being employed as defensive tools to reinforce the security of other models, notably in purifying adversarial examples and certifying adversarial…

Cryptography and Security · Computer Science 2024-06-17 Changjiang Li , Ren Pang , Bochuan Cao , Jinghui Chen , Fenglong Ma , Shouling Ji , Ting Wang

Outsourced training and machine learning as a service have resulted in novel attack vectors like backdoor attacks. Such attacks embed a secret functionality in a neural network activated when the trigger is added to its input. In most works…

Cryptography and Security · Computer Science 2022-11-08 Stefanos Koffas , Stjepan Picek , Mauro Conti

Backdoor attacks aim to surreptitiously insert malicious triggers into DNN models, granting unauthorized control during testing scenarios. Existing methods lack robustness against defense strategies and predominantly focus on enhancing…

Cryptography and Security · Computer Science 2024-12-03 Pengfei He , Yue Xing , Han Xu , Jie Ren , Yingqian Cui , Shenglai Zeng , Jiliang Tang , Makoto Yamada , Mohammad Sabokrou

While pre-trained Vision-Language Models (VLMs) such as CLIP exhibit impressive representational capabilities for multimodal data, recent studies have revealed their vulnerability to backdoor attacks. To alleviate the threat, existing…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Jiawei Kong , Hao Fang , Sihang Guo , Chenxi Qing , Kuofeng Gao , Bin Chen , Shu-Tao Xia , Ke Xu

Recent studies have demonstrated the susceptibility of deep neural networks to backdoor attacks. Given a backdoored model, its prediction of a poisoned sample with trigger will be dominated by the trigger information, though trigger…

Artificial Intelligence · Computer Science 2023-06-30 Mingli Zhu , Shaokui Wei , Hongyuan Zha , Baoyuan Wu

In a federated learning (FL) system, decentralized data owners (clients) could upload their locally trained models to a central server, to jointly train a global model. Malicious clients may plant backdoors into the global model through…

Cryptography and Security · Computer Science 2024-06-03 Songze Li , Yanbo Dai

Backdoor poisoning attacks behave counter-intuitively in high dimensions: stronger training triggers can help the defender. We study regularised generalised linear models on Gaussian-mixture data in the proportional regime ($p/n \to…

Machine Learning · Computer Science 2026-05-22 Donald Flynn , Hadas Yaron Goldhirsh , Jonathan P. Keating , Inbar Seroussi

Sensor data-based recognition systems are widely used in various applications, such as gait-based authentication and human activity recognition (HAR). Modern wearable and smart devices feature various built-in Inertial Measurement Unit…

Cryptography and Security · Computer Science 2025-11-19 Ajesh Koyatan Chathoth , Stephen Lee

Modern machine learning increasingly requires training on a large collection of data from multiple sources, not all of which can be trusted. A particularly concerning scenario is when a small fraction of poisoned data changes the behavior…

Machine Learning · Computer Science 2021-04-26 Jonathan Hayase , Weihao Kong , Raghav Somani , Sewoong Oh

Current backdoor defense methods are evaluated against a single attack at a time. This is unrealistic, as powerful machine learning systems are trained on large datasets scraped from the internet, which may be attacked multiple times by one…

Machine Learning · Computer Science 2024-08-26 Neel Alex , Shoaib Ahmed Siddiqui , Amartya Sanyal , David Krueger

Image anomaly detection (IAD) is essential in applications such as industrial inspection, medical imaging, and security. Despite the progress achieved with deep learning models like Deep Semi-Supervised Anomaly Detection (DeepSAD), these…

Computer Vision and Pattern Recognition · Computer Science 2024-12-19 He Cheng , Depeng Xu , Shuhan Yuan