paper-with-me

Papers

CEPA: Consensus Embedded Perturbation for Agnostic Detection and Inversion of Backdoors

2024-02-03 · Guangmingmei Yang, Xi Li, Hang Wang, David J. Miller, George Kesidis

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 incorporation mechanism used by the attacker, while inversion methods explicitly assume one. In this paper, we describe a new detector that: relies on embedded feature representations to estimate (invert) the backdoor and to identify its target class; can operate without access to the training dataset; and is highly effective for various incorporation mechanisms (i.e., is backdoor agnostic). Our detection approach is evaluated -- and found to be favorable - in comparison with an array of published defenses for a variety of different attacks on the CIFAR-10 and CIFAR-100 image-classification domains.

📄 PDF Abstract BibTeX arXiv:2402.02034

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage Classification

Similar Papers 제목 키워드 기반

AceParse: A Comprehensive Dataset with Diverse Structured Texts for Academic Literature Parsing

2024-09-16 · Huawei Ji, Cheng Deng, Bo Xue, Zhouyang Jin 외

With the development of data-centric AI, the focus has shifted from model-driven approaches to improving data quality. Academic literature, as one of the crucial types, is predominantly stored in PDF formats and needs to…

Communication-Efficient and Privacy-Adaptable Mechanism for Federated Learning

2025-01-21 · Chih Wei Ling, Youqi Wu, Jiande Sun, Cheuk Ting Li 외

Training machine learning models on decentralized private data via federated learning (FL) poses two key challenges: communication efficiency and privacy protection. In this work, we address these challenges within the t…

Federated Learning

SynFacePAD 2023: Competition on Face Presentation Attack Detection Based on Privacy-aware Synthetic Training Data

2023-11-09 · Meiling Fang, Marco Huber, Julian Fierrez, Raghavendra Ramachandra 외

This paper presents a summary of the Competition on Face Presentation Attack Detection Based on Privacy-aware Synthetic Training Data (SynFacePAD 2023) held at the 2023 International Joint Conference on Biometrics (IJCB …

Face Presentation Attack Detectionvalid

Communication-Efficient and Privacy-Adaptable Mechanism -- a Federated Learning Scheme with Convergence Analysis

2026-01-15 · Chun Hei Michael Shiu, Chih Wei Ling arxiv

Federated learning enables multiple parties to jointly train learning models without sharing their own underlying data, offering a practical pathway to privacy-preserving collaboration under data-governance constraints. …

Federated Learning

Flow Augmentation and Knowledge Distillation for Lightweight Face Presentation Attack Detection

2026-05-13 · Muhammad Shahid Jabbar, Muhammad Sohail Ibrahim, Taha Hasan Masood Siddique, Kejie Huang 외 arxiv

Face presentation attack detection (FacePAD) remains challenging under diverse spoofing representation, including 2D print and replay, 3D mask-based spoofing, makeup-induced appearance manipulation, and physical occlusio…

Face Presentation Attack DetectionOptical Flow EstimationKnowledge Distillation