Search Results for author:
Found 22 papers, 3 papers with code
AutoQ: Automated Kernel-Wise Neural Network Quantization
Recent network quantization techniques quantize each weight kernel in a convolutional layer independently for higher inference accuracy, since the weight kernels in a layer exhibit different variances and hence have different amounts of redundancy.
SHE: A Fast and Accurate Deep Neural Network for Encrypted Data
Since the LTFHE ReLU activations, max poolings, shifts and accumulations have small multiplicative depth overhead, SHE can implement much deeper network architectures with more convolutional and activation layers.
Glyph: Fast and Accurately Training Deep Neural Networks on Encrypted Data
Big data is one of the cornerstones to enabling and training deep neural networks (DNNs).
AutoPrivacy: Automated Layer-wise Parameter Selection for Secure Neural Network Inference
Prior HPPNNs over-pessimistically select huge HE parameters to maintain large noise budgets, since they use the same set of HE parameters for an entire network and ignore the error tolerance capability of a network.
Helix: Algorithm/Architecture Co-design for Accelerating Nanopore Genome Base-calling
From architecture perspective, we propose a low-power SOT-MRAM-based ADC array to process analog-to-digital conversion operations and improve power efficiency of prior DNN PIMs.
CryptoGRU: Low Latency Privacy-Preserving Text Analysis With GRU
Although prior secure networks combine homomorphic encryption (HE) and garbled circuit (GC) to preserve users' privacy, naively adopting the HE and GC hybrid technique to implement RNNs suffers from long inference latency due to slow activation functions.
Falcon: Fast Spectral Inference on Encrypted Data
We observed that HENNs have to pay significant computing overhead on rotations, and each of rotations is $\sim 10\times$ more expensive than homomorphic multiplications between ciphertext and plaintext.
SAFENet: A Secure, Accurate and Fast Neural Network Inference
A cryptographic neural network inference service is an efficient way to allow two parties to execute neural network inference without revealing either party’s data or model.
How to Accelerate Capsule Convolutions in Capsule Networks
How to improve the efficiency of routing procedures in CapsNets has been studied a lot.
HEMET: A Homomorphic-Encryption-Friendly Privacy-Preserving Mobile Neural Network Architecture
Recently Homomorphic Encryption (HE) is used to implement Privacy-Preserving Neural Networks (PPNNs) that perform inferences directly on encrypted data without decryption.
DictFormer: Tiny Transformer with Shared Dictionary
DictFormer significantly reduces the redundancy in the transformer's parameters by replacing the prior transformer's parameters with compact, shared dictionary, a few unshared coefficients, and indices.
Automatic Mixed-Precision Quantization Search of BERT
Knowledge distillation, Weight pruning, and Quantization are known to be the main directions in model compression.
Lite-MDETR: A Lightweight Multi-Modal Detector
The key primitive is that Dictionary-Lookup-Transformormations (DLT) is proposed to replace Linear Transformation (LT) in multi-modal detectors where each weight in Linear Transformation (LT) is approximately factorized into a smaller dictionary, index, and coefficient.
Language model compression with weighted low-rank factorization
In other words, the optimization objective of SVD is not aligned with the trained model's task accuracy.
TrojViT: Trojan Insertion in Vision Transformers
The success of ViTs motivates adversaries to perform backdoor attacks on ViTs.
Audit and Improve Robustness of Private Neural Networks on Encrypted Data
(ii) How to design a robust PNet given the encrypted input without decryption?
Numerical Optimizations for Weighted Low-rank Estimation on Language Model
However, standard SVD treats the parameters within the matrix with equal importance, which is a simple but unrealistic assumption.
ESTAS: Effective and Stable Trojan Attacks in Self-supervised Encoders with One Target Unlabelled Sample
Emerging self-supervised learning (SSL) has become a popular image representation encoding method to obviate the reliance on labeled data and learn rich representations from large-scale, ubiquitous unlabelled data.
TrojText: Test-time Invisible Textual Trojan Insertion
This paper proposes a solution called TrojText, which aims to determine whether invisible textual Trojan attacks can be performed more efficiently and cost-effectively without training data.
SSL-Cleanse: Trojan Detection and Mitigation in Self-Supervised Learning
We evaluated SSL-Cleanse on various datasets using 1200 encoders, achieving an average detection success rate of 82. 2% on ImageNet-100.
TrojFair: Trojan Fairness Attacks
TrojFair is a stealthy Fairness attack that is resilient to existing model fairness audition detectors since the model for clean inputs is fair.
TrojFSP: Trojan Insertion in Few-shot Prompt Tuning
However, the security issues, e. g., Trojan attacks, of prompt tuning on a few data samples are not well-studied.
