Search Results for author:
Found 20 papers, 2 papers with code
SSL-Cleanse: Trojan Detection and Mitigation in Self-Supervised Learning
By using a pre-trained SSL image encoder and training a downstream classifier on top of it, impressive performance can be achieved on various tasks with very little labeled 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.
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.
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.
Audit and Improve Robustness of Private Neural Networks on Encrypted Data
(ii) How to design a robust PNet given the encrypted input without decryption?
TrojViT: Trojan Insertion in Vision Transformers
The success of ViTs motivates adversaries to perform backdoor attacks on ViTs.
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.
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.
Automatic Mixed-Precision Quantization Search of BERT
Knowledge distillation, Weight pruning, and Quantization are known to be the main directions in model compression.
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.
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.
How to Accelerate Capsule Convolutions in Capsule Networks
How to improve the efficiency of routing procedures in CapsNets has been studied a lot.
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.
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.
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.
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.
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.
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).
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.
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.
