Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- short-paperJune 2024
WiP: An On-device LLM-based Approach to Query Privacy Protection
EdgeFM '24: Proceedings of the Workshop on Edge and Mobile Foundation ModelsPages 7–9https://doi.org/10.1145/3662006.3662060Privacy leakage from user queries is a widely-concerned issue in search engines and chatbot services. Existing solutions based on privacy information removal, obfuscation, and encryption may inevitably hurt service quality or require full trust of the ...
- research-articleOctober 2023
PatchBackdoor: Backdoor Attack against Deep Neural Networks without Model Modification
MM '23: Proceedings of the 31st ACM International Conference on MultimediaPages 9134–9142https://doi.org/10.1145/3581783.3612032Backdoor attack is a major threat to deep learning systems in safety-critical scenarios, which aims to trigger misbehavior of neural network models under attacker-controlled conditions. However, most backdoor attacks have to modify the neural network ...
- research-articleJune 2023
ConvReLU++: Reference-based Lossless Acceleration of Conv-ReLU Operations on Mobile CPU
MobiSys '23: Proceedings of the 21st Annual International Conference on Mobile Systems, Applications and ServicesPages 503–515https://doi.org/10.1145/3581791.3596831Many activation values of Convolutional Neural Networks (CNNs) are zeros due to ReLU (Rectified Linear Unit), one of the most common activation functions used in modern neural networks. Since ReLU outputs are zero for all negative inputs, existing CNN ...