Search Results for author:
Found 24 papers, 12 papers with code
MAT: A Multi-strength Adversarial Training Method to Mitigate Adversarial Attacks
Our experiments show that different adversarial strengths, i. e., perturbation levels of adversarial examples, have different working zones to resist the attack.
DPatch: An Adversarial Patch Attack on Object Detectors
Successful realization of DPatch also illustrates the intrinsic vulnerability of the modern detector architectures to such patch-based adversarial attacks.
DeepHoyer: Learning Sparser Neural Network with Differentiable Scale-Invariant Sparsity Measures
Inspired by the Hoyer measure (the ratio between L1 and L2 norms) used in traditional compressed sensing problems, we present DeepHoyer, a set of sparsity-inducing regularizers that are both differentiable almost everywhere and scale-invariant.
DeepObfuscator: Obfuscating Intermediate Representations with Privacy-Preserving Adversarial Learning on Smartphones
Our experiments on CelebA and LFW datasets show that the quality of the reconstructed images from the obfuscated features of the raw image is dramatically decreased from 0. 9458 to 0. 3175 in terms of multi-scale structural similarity.
Exploring Bit-Slice Sparsity in Deep Neural Networks for Efficient ReRAM-Based Deployment
However, the power hungry analog-to-digital converters (ADCs) prevent the practical deployment of ReRAM-based DNN accelerators on end devices with limited chip area and power budget.
Learning Low-rank Deep Neural Networks via Singular Vector Orthogonality Regularization and Singular Value Sparsification
In this work, we propose SVD training, the first method to explicitly achieve low-rank DNNs during training without applying SVD on every step.
TIPRDC: Task-Independent Privacy-Respecting Data Crowdsourcing Framework for Deep Learning with Anonymized Intermediate Representations
The goal of this framework is to learn a feature extractor that can hide the privacy information from the intermediate representations; while maximally retaining the original information embedded in the raw data for the data collector to accomplish unknown learning tasks.
DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensembles
The process is hard, often requires models with large capacity, and suffers from significant loss on clean data accuracy.
Provable Defense against Privacy Leakage in Federated Learning from Representation Perspective
In this work, we show our key observation that the data representation leakage from gradients is the essential cause of privacy leakage in FL.
BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantization
Mixed-precision quantization can potentially achieve the optimal tradeoff between performance and compression rate of deep neural networks, and thus, have been widely investigated.
Can Targeted Adversarial Examples Transfer When the Source and Target Models Have No Label Space Overlap?
During the online phase of the attack, we then leverage representations of highly related proxy classes from the whitebox distribution to fool the blackbox model into predicting the desired target class.
Soteria: Provable Defense Against Privacy Leakage in Federated Learning From Representation Perspective
The key idea of our defense is learning to perturb data representation such that the quality of the reconstructed data is severely degraded, while FL performance is maintained.
Global Vision Transformer Pruning with Hessian-Aware Saliency
This work aims on challenging the common design philosophy of the Vision Transformer (ViT) model with uniform dimension across all the stacked blocks in a model stage, where we redistribute the parameters both across transformer blocks and between different structures within the block via the first systematic attempt on global structural pruning.
HERO: Hessian-Enhanced Robust Optimization for Unifying and Improving Generalization and Quantization Performance
We therefore propose HERO, a Hessian-enhanced robust optimization method, to minimize the Hessian eigenvalues through a gradient-based training process, simultaneously improving the generalization and quantization performance.
NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers
Building on the theoretical insight, NoisyQuant achieves the first success on actively altering the heavy-tailed activation distribution with additive noisy bias to fit a given quantizer.
CSQ: Growing Mixed-Precision Quantization Scheme with Bi-level Continuous Sparsification
CSQ stabilizes the bit-level mixed-precision training process with a bi-level gradual continuous sparsification on both the bit values of the quantized weights and the bit selection in determining the quantization precision of each layer.
HCE: Improving Performance and Efficiency with Heterogeneously Compressed Neural Network Ensemble
We propose a new prespective on exploring the intrinsic diversity within a model architecture to build efficient DNN ensemble.
Q-Diffusion: Quantizing Diffusion Models
We propose a novel PTQ method specifically tailored towards the unique multi-timestep pipeline and model architecture of the diffusion models, which compresses the noise estimation network to accelerate the generation process.
QD-BEV : Quantization-aware View-guided Distillation for Multi-view 3D Object Detection
Multi-view 3D detection based on BEV (bird-eye-view) has recently achieved significant improvements.
Split-Ensemble: Efficient OOD-aware Ensemble via Task and Model Splitting
In particular, we build a tree-like Split-Ensemble architecture by performing iterative splitting and pruning from a shared backbone model, where each branch serves as a submodel corresponding to a subtask.
Efficient Deweather Mixture-of-Experts with Uncertainty-aware Feature-wise Linear Modulation
In this work, we propose an efficient MoE architecture with weight sharing across the experts.
VeCAF: Vision-language Collaborative Active Finetuning with Training Objective Awareness
Finetuning a pretrained vision model (PVM) is a common technique for learning downstream vision tasks.
Magic-Me: Identity-Specific Video Customized Diffusion
To achieve this, we propose three novel components that are essential for high-quality identity preservation and stable video generation: 1) a noise initialization method with 3D Gaussian Noise Prior for better inter-frame stability; 2) an ID module based on extended Textual Inversion trained with the cropped identity to disentangle the ID information from the background 3) Face VCD and Tiled VCD modules to reinforce faces and upscale the video to higher resolution while preserving the identity's features.
Intuition-aware Mixture-of-Rank-1-Experts for Parameter Efficient Finetuning
Large Language Models (LLMs) have demonstrated significant potential in performing multiple tasks in multimedia applications, ranging from content generation to interactive entertainment, and artistic creation.
