A CLIP-guided diffusion model generates backdoor triggers for IMU-based HAR models, achieving successful attacks at a 10% backdoor injection rate.
Pcap-backdoor: Backdoor poisoning generator for network traffic in cps/iot environments
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
background 1representative citing papers
Backdoor attacks succeed against ML fault detection and localization in CPS even when only 10% of the training data is poisoned.
A survey of 28 IoT attacks classified via STRIDE and CVSS, mapped to Process/Code/Communication/Operation/Device vulnerabilities, with mitigations and research gaps.
citing papers explorer
-
CLIP-guided Diffusion Model for Backdoor Generation in Sensor-based Human Activity Recognition
A CLIP-guided diffusion model generates backdoor triggers for IMU-based HAR models, achieving successful attacks at a 10% backdoor injection rate.
-
Backdoor Attacks on Fault Detection and Localization in Cyber-Physical Systems
Backdoor attacks succeed against ML fault detection and localization in CPS even when only 10% of the training data is poisoned.
-
Internet of Things Security: A Survey on Common Attacks
A survey of 28 IoT attacks classified via STRIDE and CVSS, mapped to Process/Code/Communication/Operation/Device vulnerabilities, with mitigations and research gaps.