Detecting All-to-One Backdoor Attacks in Black-Box DNNs via Differential Robustness to Noise

• Published in: IEEE access Vol. 13; pp. 36099 - 36111
• Main Authors: Fu, Hao, Krishnamurthy, Prashanth, Garg, Siddharth, Khorrami, Farshad
• Format: Journal Article
• Language: English
• Published: IEEE 2025
• Subjects: Closed box; Detectors; Glass box; Neural network backdoors; Neural networks; Noise; novelty detection; output resiliency; Perturbation methods; Resilience; Robustness; Strips; Training

The all-to-one (A2O) backdoor attack is one of the major adversarial threats against neural networks. Most existing A2O backdoor defenses operate in a white-box context, necessitating access to the backdoored model's architecture, hidden layer outputs, or internal parameters. The necessity for...