Paper introduces adversarial lossy compression for video artifacts reduction.
problem Unpleasant reconstruction artifacts in standard video coding schemes at low bit-rates.
method Adversarial lossy video compression model minimizing an adversarial distortion objective.
result Reduction of perceptual artifacts and detail reconstruction under extreme compression.
This work analyzes how different forms of compressibility affect adversarial robustness in neural networks.
problem Understanding the interaction between compressibility and adversarial robustness in neural networks.
method Developed a principled framework to analyze the effects of neuron-level sparsity and spectral compressibility on adversarial robustness.
result Identified that different forms of compression can induce highly sensitive directions in the representation space that adversaries can exploit.
Paper develops a framework to protect data privacy using compressive adversarial methods.
problem Balancing data privacy and utility in data sharing.
method Optimal data releasing mechanism through convex optimization and nonlinear compression model.
result Demonstrates that compressive adversarial privacy can preserve sensitive information.
Unified framework improves model compression while maintaining robustness.
problem Achieving high compression ratios without sacrificing adversarial robustness.
method Adversarially Trained Model Compression (ATMC) framework integrating multiple compression techniques.
result ATMC achieves better trade-off between model size, accuracy, and robustness.
The paper proposes a bio-inspired framework for better compression and adversarial robustness in machine learning models.
problem Machine learning models are vulnerable to adversarial examples.
method The paper introduces a bio-inspired classification framework that conditions model inference on label hypothesis and uses an information bottleneck regularizer.
result The framework enables better compression and adversarial robustness without loss of natural accuracy.
Unified approach for robust low rank matrix estimation with adversaries.
problem Robust low rank matrix estimation in the presence of adversaries.
method Unified approach combining Huber loss and nuclear norm penalization.
result Sharp estimation error bounds for matrix compressed sensing and completion.
A CAE improves DNN's outlier and adversary defense.
problem Improving DNN's robustness against outliers and adversaries.
method Proposes a classification-autoencoder (CAE) that compresses samples into disjoint spaces and uses a decoder to classify and defend against adversaries.
result The CAE achieves state-of-the-art outlier recognition and near-lossless classification of adversaries.
DNN is presenting human-level performance for many complex intelligent tasks in real-world applications. However, it also introduces ever-increasing security concerns. For example, the emerging adversarial attacks indicate that even very small and often imperceptible adversarial input perturbations can easily mislead t…
AdaBoost improves binary classification in robust one-bit compressed sensing with adversarial errors.
problem Binary classification in robust one-bit compressed sensing with adversarial errors.
method AdaBoost and max-ℓ1-margin-classifier approach, with convergence rates improved under certain feature conditions. result Improved convergence rates and explanation for harmless interpolating adversarial noise.
New findings show learnable distributions remain learnable even with noisy or adversarial perturbations.
problem Learning from perturbed samples in high-dimensional spaces.
method Developed a perturbation-quantization framework to analyze additive noise and adversarial corruption models.
result Sample compressible families remain learnable even under noisy or adversarial perturbations.
Reduces multiclass and regression compression schemes to binary ones.
problem Developing efficient learning algorithms for multiclass and regression problems.
method Reduces sample compression schemes for binary classes to multiclass and regression settings.
result Establishes new compression schemes for multiclass and regression problems.
Study robust regression learning under adversarial attacks.
problem Understanding which function classes are learnable in the presence of adversarial attacks.
method Introduced a novel agnostic sample compression scheme and used fat-shattering dimension to construct adversarially robust sample compression schemes.
result Finite fat-shattering dimension classes are learnable in both realizable and agnostic settings.
New bounds show neural networks can resist attacks better with sparse weights.
problem Neural networks are vulnerable to small adversarial perturbations.
method Compression based on effective sparsity and joint sparsity.
result Neural networks with approximately sparse weight matrices have better robustness and generalization.
Paper improves robustness and sparsity in adversarially trained DNNs.
problem Developing efficient compression algorithms for robustly trained DNNs.
method Pruning weights using relaxed augmented Lagrangian algorithms for both structured and unstructured levels, leveraging Feynman-Kac formalism.
result At least doubles channel sparsity of adversarially trained ResNet20 for CIFAR10 classification.
AIB method improves robustness against adversarial perturbations.
problem Optimizing the IB principle for better robustness and understanding compression effects.
method Proposes adversarial information bottleneck (AIB) method to optimize IB principle without explicit distribution assumptions.
result Demonstrates effectiveness in learning more invariant representations and mitigating adversarial perturbations.
Guarantees recovery of compressible signals from adversarial noise.
problem Recovering compressible signals from noise and adversarial attacks.
method Extends adversarial defense framework to ℓ0, ℓ2, and ℓ∞ norms. result Recovery guarantees for various signal recovery methods under different noise types.
GAN-TSC improves student model accuracy by augmenting with synthetic data.
problem Suboptimal compression when fresh data is unavailable for TSC.
method Augment compression dataset with synthetic data from a GAN.
result Significant improvement in student accuracy for expensive models.
Proposes a method to compress deep networks using adversarial training and attention mechanisms.
problem Lack of efficient methods to compress deep networks while preserving important information.
method Adversarial training with task-driven attention mechanism for effective intermediate supervision.
result Demonstrates superior performance on benchmark datasets compared to state-of-the-art methods.
The online problem of computing the top eigenvector is fundamental to machine learning. In both adversarial and stochastic settings, previous results (such as matrix multiplicative weight update, follow the regularized leader, follow the compressed leader, block power method) either achieve optimal regret but run slow,…
This work combines GANs and A3C for high-resolution image compression.
problem Image compression for high-resolution images without loss of quality.
method Hybrid approach using GANs and A3C for end-to-end learning.
result Improves PSNR for high-resolution images through end-to-end learning.
This work examines how low-rank weights improve adversarial robustness in neural networks.
problem Improving adversarial robustness in neural networks.
method The study investigates the impact of low-rank structure on adversarial robustness through compression measures.
result Promoting low-rank structure in weight matrices enhances adversarial robustness in neural networks.
HYDRA prunes robust neural networks to improve both benign and adversarial robustness.
problem Lack of robustness against adversarial attacks and large neural network size in deep learning.
method HYDRA integrates pruning techniques with adversarial training and verifiable robust training objectives.
result HYDRA achieves compressed networks with state-of-the-art benign and robust accuracy.
TensorShield defends images from adversarial attacks using tensor decomposition.
problem Adversarial attacks on images can fool deep neural networks.
method Tensor decomposition to find low-rank approximations of images, reducing high-frequency perturbations.
result TensorShield outperforms existing methods like SLQ by 14% against FGSM attacks.
This paper uses unlabeled data to improve compressed neural networks.
problem Difficulty in retraining pre-trained models due to limited labeled data.
method Uses unlabeled data to mimic classification characteristics and aligns feature distributions using adversarial loss.
result Unlabeled data significantly improves the performance of compressed neural networks.
In recent years, neural network approaches have been widely adopted for machine learning tasks, with applications in computer vision. More recently, unsupervised generative models based on neural networks have been successfully applied to model data distributions via low-dimensional latent spaces. In this paper, we use…
BNCR-GAN improves GANs to generate clean images from degraded inputs.
problem Generating clean images from blurred, noisy, and compressed degraded inputs.
method Multiple-generator model with image, blur-kernel, noise, and quality-factor generators, using masking architectures and adaptive consistency losses.
result BNCR-GAN effectively learns clean image generators from degraded images without degradation parameters.
Improves signal recovery speed and performance via meta-learning.
problem Slow and costly signal recovery in compressed sensing.
method Jointly trains a generator and optimisation process for reconstruction via meta-learning.
result Significantly improved both performance and speed of signal recovery.
We study the effectiveness of various approaches that defend against adversarial attacks on deep networks via manipulations based on basis function representations of images. Specifically, we experiment with low-pass filtering, PCA, JPEG compression, low resolution wavelet approximation, and soft-thresholding. We evalu…
Recently, generative adversarial networks and adversarial autoencoders have gained a lot of attention in machine learning community due to their exceptional performance in tasks such as digit classification and face recognition. They map the autoencoder's bottleneck layer output (termed as code vectors) to different no…
Paper proposes IABF to improve NECST robustness.
problem Limited robustness of NECST learned coding networks.
method Infomax Adversarial-Bit-Flip (IABF) to improve stability and robustness.
result IABF achieves state-of-the-art performances on compression and error correction benchmarks.
Paper proposes a data-free adversarial distillation method.
problem Tackles the challenge of model compression without real-world data.
method Introduces a novel adversarial distillation mechanism to craft a compact student model without any real-world data.
result Demonstrates comparable performance to data-driven methods and achieves state-of-the-art results in semantic segmentation.
This paper combines three techniques to reduce communications in distributed variational inequalities.
problem Efficiently communicating solutions in large-scale distributed variational inequalities.
method Combining similarity, compression, and local steps to reduce communication rounds and cost.
result Best theoretical guarantees of communication complexity and superior performance in adversarial learning experiments.
Unified framework compresses GANs up to 47x with minimal quality loss.
problem High parameter complexity of GANs for resource-constrained devices.
method Unified optimization framework combining model distillation, channel pruning, and quantization.
result 47x compression of CartoonGAN with minimal quality degradation.
Bayesian neural networks are compressed using feature and weight pruning based on posterior inclusion probabilities.
problem Efficiently compressing Bayesian neural networks to reduce computation cost and improve generalizability.
method Bayesian model selection principles are applied to obtain posterior inclusion probabilities for pruning and feature selection.
result Pruned models show better generalizability on simulated and real-world data.
Paper analyzes BIHT for noisy 1-bit CS, improving results with up to τ-fraction of incorrect measurements.
problem Estimating sparse vectors from noisy sign measurements in 1-bit compressed sensing.
method Binary Iterative Hard Thresholding (BIHT) algorithm, using Gaussian matrices and high-dimensional geometry analysis.
result BIHT provides estimates within ε+τ error with τ-fraction of incorrect measurements, maintaining universality of measurements.
Data-independent pruning method reduces neural network size with accuracy guarantees.
problem Limited computational and memory resources for neural networks.
method Structured pruning using coresets.
result First efficient algorithm with worst-case guarantees on compression and accuracy.
Method generates adversarial examples to improve classifier robustness.
problem Addressing adversarial examples in machine learning.
method MDL principle for generating adversarial examples.
result Evasion rate of 78.24% for adversarial examples compared to 8.16% for original malware.
New methods reduce communication in distributed training for variational inequalities.
problem Reducing communication in distributed training for high-dimensional models.
method Distributed methods with compressed communication for solving variational inequalities.
result Theoretical guarantees and practical algorithms for compressed communication.
Proposes using GANs to solve phase retrieval problems.
problem Solving phase retrieval problems in various contexts.
method Applying conditional GANs with knowledge of measurement process.
result Method provides more robust and detailed solutions.
This paper introduces blind adversarial pruning to balance accuracy, efficiency, and robustness in neural networks.
problem Balancing accuracy, efficiency, and robustness in neural networks with limited resources.
method Adversarial pruning with a cutoff-scale strategy to dynamically adjust the strength of adversarial examples.
result Blind adversarial pruning improves the overall AER of pruned models compared to adversarial pruning.
New method learns robustly with less data, bridging theory and practice.
problem Adversarial robust learning with metric perturbation.
method Tolerant adversarial PAC-learning with perturb-and-smooth approach and compression-based algorithm.
result First PAC-type guarantees for popular adversarial learning techniques.
Generative adversarial networks create realistic equity option market simulations.
problem Limited real-world data for training and evaluating option trading strategies.
method Recurrent and temporal convolutional architectures with state compression.
result GANs outperform classical methods on benchmark metrics.
Inspired by biophysical principles underlying nonlinear dendritic computation in neural circuits, we develop a scheme to train deep neural networks to make them robust to adversarial attacks. Our scheme generates highly nonlinear, saturated neural networks that achieve state of the art performance on gradient based adv…
We present a machine learning-based approach to lossy image compression which outperforms all existing codecs, while running in real-time. Our algorithm typically produces files 2.5 times smaller than JPEG and JPEG 2000, 2 times smaller than WebP, and 1.7 times smaller than BPG on datasets of generic images across all …
New method compresses GANs by 1669:1 ratio on MNIST, 58:1 on CIFAR-10, 87:1 on Celeb-A.
problem Expensive GANs for low SWAP hardware and real-time applications.
method Knowledge distillation between a student and teacher GAN.
result Compressed GANs outperform standard training methods with a fixed parameter budget.
Data-independent neural pruning via coresets improves accuracy with 90% compression.
problem Efficiently reduce neural network size while maintaining accuracy.
method Data-independent neural pruning using coresets.
result 90% compression of LeNet-300-100 on MNIST with improved accuracy.
Efficient method defends deep learning models from adversarial attacks.
problem Vulnerability of deep learning models to adversarial attacks.
method Training a Denoising Autoencoder (DAE) to reduce data dimensions and serve as a defense.
result The method provides a 2.43x speedup while maintaining robustness against adversarial attacks.
Evaluates SHIELD's effectiveness against adaptive adversaries in various threat models.
problem Evaluating SHIELD's efficacy against adaptive adversaries in different threat models.
method Empirical analysis of SHIELD's robustness against adaptive attacks using Projected Gradient Descent (PGD) attacks in various threat models (white-box, gray-box).
result The targeted PGD attack success rate drops from 64.3% to 48.9% when models are trained from scratch instead of retrained.