Search Results for author:
Found 8 papers, 3 papers with code
Eliminating Backdoors in Neural Code Models for Secure Code Understanding
Specifically, EliBadCode first filters the model vocabulary for trigger tokens based on the naming conventions of specific programming languages to reduce the trigger search space and cost.
Towards General Robustness Verification of MaxPool-based Convolutional Neural Networks via Tightening Linear Approximation
The results show that MaxLin outperforms state-of-the-art tools with up to 110. 60% improvement regarding the certified lower bound and 5. 13 $\times$ speedup for the same neural networks.
Tightening Robustness Verification of MaxPool-based Neural Networks via Minimizing the Over-Approximation Zone
By our proposed linear bounds, we can certify larger robustness results for CNNs.
Partly Supervised Multitask Learning
Leveraging self-supervision and adversarial training, we propose a novel general purpose semi-supervised, multiple-task model---namely, self-supervised, semi-supervised, multitask learning (S$^4$MTL)---for accomplishing two important tasks in medical imaging, segmentation and diagnostic classification.
Generative Inpainting Network Applications on Seismic Image Compression and Non-Uniform Sampling
The use of deep learning models as priors for compressive sensing tasks presents new potential for inexpensive seismic data acquisition.
Enhanced Seismic Imaging with Predictive Neural Networks for Geophysics
In addition, in each iteration step, the probability cubes of salt bodies and inclusions inferred from the proposed networks can be used as a regularization term within the FWI forward modelling, which may result in an improved velocity model estimation while the output of seismic migration can be utilized as an input of the 3D neural network for subsequent iterations.
Unsupervised Learning Framework of Interest Point Via Properties Optimization
To maximize the objective efficiently, latent variable is introduced to represent the probability of that a point satisfies the required properties.
SgxPectre Attacks: Stealing Intel Secrets from SGX Enclaves via Speculative Execution
Particularly, we show that when branch prediction of the enclave code can be influenced by programs outside the enclave, the control flow of the enclave program can be temporarily altered to execute instructions that lead to observable cache-state changes.
Cryptography and Security
