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.
Adversarial robustness of amortized Bayesian inference is studied, showing it can be improved.
ALFI improves likelihood-free inference for black-box generators.
DALI improves inference for GANs by matching prior and conditional distributions.
We introduce the adversarially learned inference (ALI) model, which jointly learns a generation network and an inference network using an adversarial process. The generation network maps samples from stochastic latent variables to the data space while the inference network maps training examples in data space to the sp…
As machine learning (ML) becomes more and more powerful and easily accessible, attackers increasingly leverage ML to perform automated large-scale inference attacks in various domains. In such an ML-equipped inference attack, an attacker has access to some data (called public data) of an individual, a software, or a sy…
GATSBI uses GANs for SBI, improving posterior estimation in high dimensions.
It has been widely recognized that adversarial examples can be easily crafted to fool deep networks, which mainly root from the locally non-linear behavior nearby input examples. Applying mixup in training provides an effective mechanism to improve generalization performance and model robustness against adversarial per…
Adversarial inference on tree models is possible with limited corruption, improving on Kesten-Stigum threshold.
AdvMind detects adversary intent in black-box attacks with high accuracy.
The Importance Weighted Auto Encoder (IWAE) objective has been shown to improve the training of generative models over the standard Variational Auto Encoder (VAE) objective. Here, we derive importance weighted extensions to AVB and AAE. These latent variable models use implicitly defined inference networks whose approx…
Bayesian neural networks are vulnerable to adversarial attacks.
Recently it's been shown that neural networks can use images of human faces to accurately predict Body Mass Index (BMI), a widely used health indicator. In this paper we demonstrate that a neural network performing BMI inference is indeed vulnerable to test-time adversarial attacks. This extends test-time adversarial a…
Log-Loss scores expose membership privacy breaches.
APGE protects graph node representations from inference attacks.
AGMs outperform EGMs in generalizing to unseen inference tasks.
Infer-AVAE infers missing user attributes from incomplete data using a novel adversarial approach.
While the last few decades have witnessed a huge body of work devoted to inference and learning in distributed and decentralized setups, much of this work assumes a non-adversarial setting in which individual nodes---apart from occasional statistical failures---operate as intended within the algorithmic framework. In r…
Develops robust ML systems for predictive uncertainties and adversarial examples.
The arms race between attacks and defenses for machine learning models has come to a forefront in recent years, in both the security community and the privacy community. However, one big limitation of previous research is that the security domain and the privacy domain have typically been considered separately. It is t…
In this paper, we investigate the adversarial robustness of multivariate -Estimators. In the considered model, after observing the whole dataset, an adversary can modify all data points with the goal of maximizing inference errors. We use adversarial influence function (AIF) to measure the asymptotic rate at which t…
Modern deep neural network models suffer from adversarial examples, i.e. confidently misclassified points in the input space. It has been shown that Bayesian neural networks are a promising approach for detecting adversarial points, but careful analysis is problematic due to the complexity of these models. Recently Gil…
Quantum mechanics is inherently probabilistic in light of Born's rule. Using quantum circuits as probabilistic generative models for classical data exploits their superior expressibility and efficient direct sampling ability. However, training of quantum circuits can be more challenging compared to classical neural net…
As online systems based on machine learning are offered to public or paid subscribers via application programming interfaces (APIs), they become vulnerable to frequent exploits and attacks. This paper studies adversarial machine learning in the practical case when there are rate limitations on API calls. The adversary …
Bayesian inference on structured models typically relies on the ability to infer posterior distributions of underlying hidden variables. However, inference in implicit models or complex posterior distributions is hard. A popular tool for learning implicit models are generative adversarial networks (GANs) which learn pa…
Unified framework analyzes privacy risks from gradients in distributed learning.
In this paper, we consider the problem of assessing the adversarial robustness of deep neural network models under both Markov chain Monte Carlo (MCMC) and Bayesian Dark Knowledge (BDK) inference approximations. We characterize the robustness of each method to two types of adversarial attacks: the fast gradient sign me…
VERA uses variational inference to jailbreak LLMs without manual optimization.
Bayesian models can be tricked into believing false data.
The study sets lower bounds on MMSE for inferring sensitive features from noisy data.
Machine learning models are generally vulnerable to adversarial examples, which is in contrast to the robustness of humans. In this paper, we try to leverage one of the mechanisms in human recognition and propose a bio-inspired classification framework in which model inference is conditioned on label hypothesis. We pro…
Previous studies have found that an adversary attacker can often infer unintended input information from intermediate-layer features. We study the possibility of preventing such adversarial inference, yet without too much accuracy degradation. We propose a generic method to revise the neural network to boost the challe…
ORAT improves model robustness against outliers and adversarial attacks.
New method reduces bias in NLI models using ensemble adversarial training.
Researchers disrupt Gaussian model inference to test adversarial attacks.
Generalizes adversarial learning for better latent variable inference in GANs.
Deep neural networks are widely used and exhibit excellent performance in many areas. However, they are vulnerable to adversarial attacks that compromise the network at the inference time by applying elaborately designed perturbation to input data. Although several defense methods have been proposed to address specific…
Complex computer simulators are increasingly used across fields of science as generative models tying parameters of an underlying theory to experimental observations. Inference in this setup is often difficult, as simulators rarely admit a tractable density or likelihood function. We introduce Adversarial Variational O…
New deep learning model robust to adversarial attacks using stochastic LWTA units.
Recent methods for generating novel molecules use graph representations of molecules and employ various forms of graph convolutional neural networks for inference. However, training requires solving an expensive graph isomorphism problem, which previous approaches do not address or solve only approximately. In this wor…
Paper shows how to infer hidden states in neural networks analytically.
This paper introduces a new method to deceive causal structure learning by omitting data.
Paper defends sensitive attributes in GNNs from inference attacks.
ATPF combines PF and EnKF for better inference in complex systems.
Generative adversarial networks are a novel method for statistical inference that have achieved much empirical success; however, the factors contributing to this success remain ill-understood. In this work, we attempt to analyze generative adversarial learning -- that is, statistical inference as the result of a game b…
Bayesian methods improve adversarial machine learning robustness.
CANs improve GANs by enforcing structured constraints during training.
Paper introduces attacks to infer GAN training dataset properties.
FHBI enhances generalization in Bayesian inference with iterative steps in functional spaces.