paper-with-me

홈 › Papers

Dirty and Clean-Label attack detection using GAN discriminators

2025-06-02 · John W. Smutny

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 unless the images are properly inspected. Manually inspecting each image-label pair is impractical and common poison-detection methods that involve re-training your model can be time consuming. This research uses GAN discriminators to protect a single class against mislabeled and different levels of modified images. The effect of said perturbation on a basic convolutional neural network classifier is also included for reference. The results suggest that after training on a single class, GAN discriminator s confidence scores can provide a threshold to identify mislabeled images and identify 100% of the tested poison starting at a perturbation epsilon magnitude of 0.20, after decision threshold calibration using in-class samples. Developers can use this report as a basis to train their own discriminators to protect high valued classes in their CV models.

📄 PDF Abstract BibTeX arXiv:2506.01224

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Strategic Sample Selection for Improved Clean-Label Backdoor Attacks in Text Classification

2025-08-21 · Onur Alp Kirci, M. Emre Gursoy arxiv

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 prop…

Text Classification

VDC: Versatile Data Cleanser based on Visual-Linguistic Inconsistency by Multimodal Large Language Models

2023-09-28 · Zihao Zhu, Mingda Zhang, Shaokui Wei, Bingzhe Wu 외

The role of data in building AI systems has recently been emphasized by the emerging concept of data-centric AI. Unfortunately, in the real-world, datasets may contain dirty samples, such as poisoned samples from backdoo…

Backdoor Attackcross-modal alignmentQuestion AnsweringQuestion Generation+2

Defending Against Backdoor Attacks Using Ensembles of Weak Learners

2021-09-29 · Charles Jin, Melinda Sun, Martin Rinard

A recent line of work has shown that deep networks are susceptible to backdoor data poisoning attacks. Specifically, by injecting a small amount of malicious data into the training distribution, an adversary gains the ab…

Backdoor AttackData Poisoning

Attention-Enhancing Backdoor Attacks Against BERT-based Models

2023-10-23 · Weimin Lyu, Songzhu Zheng, Lu Pang, Haibin Ling 외

Recent studies have revealed that \textit{Backdoor Attacks} can threaten the safety of natural language processing (NLP) models. Investigating the strategies of backdoor attacks will help to understand the model's vulner…

Sentiment AnalysisTopic Classification

Temporal Poisoning: Clean-Label Backdoors via Event Redistribution in SNNs

2026-07-30 · Roberto Riaño, Gorka Abad, Stjepan Picek, Aitor Urbieta arxiv

Backdoor attacks on Spiking Neural Networks (SNNs) have primarily assumed dirty-label poisoning, in which triggered training samples are relabeled to an attacker-selected class. We study clean-label temporal poisoning, w…