Search Results for author:
Found 6 papers, 1 papers with code
BELT: Old-School Backdoor Attacks can Evade the State-of-the-Art Defense with Backdoor Exclusivity Lifting
Deep neural networks (DNNs) are susceptible to backdoor attacks, where malicious functionality is embedded to allow attackers to trigger incorrect classifications.
Watch Out! Simple Horizontal Class Backdoors Can Trivially Evade Defenses
In VCB attacks, any sample from a class activates the implanted backdoor when the secret trigger is present.
Weighted Contrastive Hashing
The development of unsupervised hashing is advanced by the recent popular contrastive learning paradigm.
Towards A Critical Evaluation of Robustness for Deep Learning Backdoor Countermeasures
Since Deep Learning (DL) backdoor attacks have been revealed as one of the most insidious adversarial attacks, a number of countermeasures have been developed with certain assumptions defined in their respective threat models.
Quantization Backdoors to Deep Learning Commercial Frameworks
This work reveals that the standard quantization toolkits can be abused to activate a backdoor.
RBNN: Memory-Efficient Reconfigurable Deep Binary Neural Network with IP Protection for Internet of Things
To this end, a 1-bit quantized DNN model or deep binary neural network maximizes the memory efficiency, where each parameter in a BNN model has only 1-bit.
