Implementation Bugs as Attacks: Adversarial Neuron Fuzzing and Supply-Chain Backdoors
Open Access
- 14 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 5582-5596
Abstract
No abstract availableThis publication has 25 references indexed in Scilit:
- Data-free Universal Adversarial Perturbation with Pseudo-semantic Prior2025
- Cooperative Warp Execution in Tensor Core for RISC-V GPGPU2025
- Revisiting Neuron Coverage for DNN Testing: A Layer-Wise and Distribution-Aware Criterion2023
- MLIR: Scaling Compiler Infrastructure for Domain Specific Computation2021
- A survey of deep learning techniques for autonomous drivingJournal of Field Robotics, 2019
- Disentangling Adversarial Robustness and Generalization2019
- CRADLE: Cross-Backend Validation to Detect and Localize Bugs in Deep Learning Libraries2019
- Autoware on Board: Enabling Autonomous Vehicles with Embedded Systems2018
- Universal Adversarial Perturbations2017
- Understanding deep image representations by inverting them2015