A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Face recognition systems are vulnerable to composite face reconstruction attacks.
This work improves understanding of neural network reconstruction attacks and distillation.
New study analyzes security of neural network data reconstruction attacks.
Paper improves privacy for language models against reconstruction attacks.
New analysis shows reconstruction attacks are unreliable without prior data knowledge.
Optimal defenses protect FL models from gradient reconstruction attacks.
Adversarial examples raise questions about whether neural network models are sensitive to the same visual features as humans. In this paper, we first detect adversarial examples or otherwise corrupted images based on a class-conditional reconstruction of the input. To specifically attack our detection mechanism, we pro…
Paper evaluates and mitigates privacy risks in deep learning models.
DefenseVGAE defends graph neural networks against adversarial attacks.
New attack recovers user-level information from large batch images.
SAPAG attacks distributed learning by reconstructing true training data from gradients.
We present a simple technique that allows capsule models to detect adversarial images. In addition to being trained to classify images, the capsule model is trained to reconstruct the images from the pose parameters and identity of the correct top-level capsule. Adversarial images do not look like a typical member of t…
Variational autoencoders (VAEs) have recently been shown to be vulnerable to adversarial attacks, wherein they are fooled into reconstructing a chosen target image. However, how to defend against such attacks remains an open problem. We make significant advances in addressing this issue by introducing methods for produ…
Develops a new robustness criterion for VAEs and provides theoretical guarantees.
Machine learning (ML) has progressed rapidly during the past decade and the major factor that drives such development is the unprecedented large-scale data. As data generation is a continuous process, this leads to ML model owners updating their models frequently with newly-collected data in an online learning scenario…
This paper shows the susceptibility of spectrogram-based audio classifiers to adversarial attacks and the transferability of such attacks to audio waveforms. Some commonly used adversarial attacks to images have been applied to Mel-frequency and short-time Fourier transform spectrograms, and such perturbed spectrograms…
Graph embedding leaks sensitive graph properties and subgraphs.
This paper studies model-inversion attacks, in which the access to a model is abused to infer information about the training data. Since its first introduction, such attacks have raised serious concerns given that training data usually contain privacy-sensitive information. Thus far, successful model-inversion attacks …
Efficient method defends privacy in federated learning without accuracy loss.
New framework UIFV reconstructs private features in VFL without model details.
New defense method protects client data privacy in federated learning.
Paper tackles model vulnerabilities by reconstructing training data.
The paper analyzes privacy leakage in federated learning using linear algebra and optimization theory.
Background elimination for noisy character images or character images from real scene is still a challenging problem, due to the bewildering backgrounds, uneven illumination, low resolution and different distortions. We propose a stroke-based character reconstruction(SCR) method that use a weighted quadratic Bezier cur…
Unified bounds for DP risks reduce noise and improve accuracy.
In this paper we propose a new membership attack method called co-membership attacks against deep generative models including Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs). Specifically, membership attack aims to check whether a given instance x was used in the training data or not. A co-me…
In this paper, we address the problem of data reconstruction from privacy-protected templates, based on recent concept of sparse ternary coding with ambiguization (STCA). The STCA is a generalization of randomization techniques which includes random projections, lossy quantization, and addition of ambiguization noise t…
Paper reconstructs training data from a single gradient query.
We develop a method to factorize symmetric sparse Boolean matrices efficiently.
A new method detects and corrects adversarial attacks on classifiers.
This paper analyzes how training data can be leaked from gradients in neural networks and proposes a metric for measuring model security.
New method reconstructs significant parts of training data from neural networks.
New method improves model reconstruction using counterfactuals and polytope theory.
This paper evaluates and compares gradient leakage attacks in federated learning.
We explore methods of producing adversarial examples on deep generative models such as the variational autoencoder (VAE) and the VAE-GAN. Deep learning architectures are known to be vulnerable to adversarial examples, but previous work has focused on the application of adversarial examples to classification tasks. Deep…
In this letter, as a proof of concept, we propose a deep learning-based approach to attack the chaos-based image encryption algorithm in \cite{guan2005chaos}. The proposed method first projects the chaos-based encrypted images into the low-dimensional feature space, where essential information of plain images has been …
New method reconstructs data subsets from limited published statistics.
Tensor network decomposition, originated from quantum physics to model entangled many-particle quantum systems, turns out to be a promising mathematical technique to efficiently represent and process big data in parsimonious manner. In this study, we show that tensor networks can systematically partition structured dat…
Lower bounds on query complexity for reconstructing private learner's training data.
The vulnerability of deep neural networks to adversarial attacks has been widely demonstrated (e.g., adversarial example attacks). Traditional attacks perform unstructured pixel-wise perturbation to fool the classifier. An alternative approach is to have perturbations in the latent space. However, such perturbations ar…
We show through theory and experiment that gradient-based explanations of a model quickly reveal the model itself. Our results speak to a tension between the desire to keep a proprietary model secret and the ability to offer model explanations. On the theoretical side, we give an algorithm that provably learns a two-la…
The level sets of neural networks represent fundamental properties such as decision boundaries of classifiers and are used to model non-linear manifold data such as curves and surfaces. Thus, methods for controlling the neural level sets could find many applications in machine learning. In this paper we present a simpl…
Deep Neural Network (DNN) workloads are quickly moving from datacenters onto edge devices, for latency, privacy, or energy reasons. While datacenter networks can be protected using conventional cybersecurity measures, edge neural networks bring a host of new security challenges. Unlike classic IoT applications, edge ne…
Certifiably robust VAEs are trained with bounds on input perturbations.
Automatic speaker verification systems are vulnerable to audio replay attacks which bypass security by replaying recordings of authorized speakers. Replay attack detection (RA) detection systems built upon Residual Neural Networks (ResNet)s have yielded astonishing results on the public benchmark ASVspoof 2019 Physical…
Machine learning models have demonstrated vulnerability to adversarial attacks, more specifically misclassification of adversarial examples. In this paper, we propose a one-off and attack-agnostic Feature Manipulation (FM)-Defense to detect and purify adversarial examples in an interpretable and efficient manner. The i…
Enhances 2D face recognition with 3D features using active illumination.
This work enhances collaborative inference privacy by minimizing conditional entropy and boosting robustness against model inversion attacks.