Neural networks are vulnerable to adversarially-constructed perturbations of their inputs. Most research so far has considered perturbations of a fixed magnitude under some norm. Although studying these attacks is valuable, there has been increasing interest in the construction of (and robustness to) unrestricted…
On-device research index
arXiv research
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “unrestricted attacks”
Proposes a new method to generate unrestricted adversarial examples.
problem Generating unrestricted adversarial examples without norm constraints.
method Leveraging state-of-the-art generative models to manipulate image fine-grained aspects.
result Our adversarial images look indistinguishable from natural images and can bypass certified defenses.
Adversarial examples are typically constructed by perturbing an existing data point within a small matrix norm, and current defense methods are focused on guarding against this type of attack. In this paper, we propose unrestricted adversarial examples, a new threat model where the attackers are not restricted to small…
Generative models create indistinguishable adversarial objects for object detection.
problem Creating unrestricted adversarial examples for object detection.
method Search over latent space of GAN for adversarial objects.
result Generated adversarial objects are indistinguishable from non-adversarial objects and transferable.
ScoreAG generates unrestricted adversarial images maintaining semantic integrity.
problem Limited robustness evaluations due to -norm constraints.
method Score-Based Adversarial Generation (ScoreAG) using score-based generative models.
result ScoreAG improves robustness assessments across multiple benchmarks.
Thanks to recent advances in deep neural networks (DNNs), face recognition systems have become highly accurate in classifying a large number of face images. However, recent studies have found that DNNs could be vulnerable to adversarial examples, raising concerns about the robustness of such systems. Adversarial exampl…
New algorithms ensure fair selection in combinatorial semi-bandit with unrestricted delays.
problem Fair selection in stochastic combinatorial semi-bandit with delayed feedback.
method Introduced merit-based fairness constraints and new bandit algorithms for reward and fairness.
result Achieved sublinear expected reward and fairness regrets with dependence on delay distribution quantiles.
We study learning problems involving arbitrary classes of functions , distributions and targets . Because proper learning procedures, i.e., procedures that are only allowed to select functions in , tend to perform poorly unless the problem satisfies some additional structural property (e.g., that is co…
We introduce a two-player contest for evaluating the safety and robustness of machine learning systems, with a large prize pool. Unlike most prior work in ML robustness, which studies norm-constrained adversaries, we shift our focus to unconstrained adversaries. Defenders submit machine learning models, and try to achi…
Study of unrestricted virtual braid groups and their properties.
problem Characterize and describe homomorphisms of unrestricted virtual braid groups.
method Analyzing homomorphisms to symmetric groups and finite groups, characterizing images, proving characteristic subgroups, determining automorphism groups, and studying residual properties.
result Complete description of homomorphisms from to for .
This paper proposes BAT to balance accuracy and robustness in adversarial training.
problem Balancing accuracy and robustness in adversarial training models.
method Blind adversarial training (BAT) uses a cutoff-scale strategy to adaptively estimate a nonuniform budget for AEs.
result BAT improves the overall robustness of adversarial training models.
We consider the group of unrestricted virtual braids, describe its structure and explore its relations with fused links. Also, we define the groups of flat virtual braids and virtual Gauss braids and study some of their properties, in particular their linearity.
This paper considers the optimal dividend payment problem in piecewise-deterministic compound Poisson risk models. The objective is to maximize the expected discounted dividend payout up to the time of ruin. We provide a comparative study in this general framework of both restricted and unrestricted payment schemes, wh…
New methods reduce extrapolation errors in feature importance.
problem Flawed feature importance methods using unrestricted permutations lead to extrapolation errors.
method Three new approaches: conditional model reliance, Knockoffs with Gaussian transformation, and restricted ALE plot designs.
result Theoretical and numerical results show our strategies reduce/eliminate extrapolation.
Recently, it is proven that generalized Robertson-Walker space-times in all orthogonal subspaces of Gray's decomposition but one(unrestricted) are perfect fluid space-times. GRW space-times in the unrestricted subspace are identified by having constant scalar curvature. Generalized quasi-Einstein GRW space-times have a…
MoMA improves model-based RL by using unrestricted policy classes.
problem Limited sample efficiency and generalizability in model-based offline RL.
method Model-based mirror ascent algorithm with general function approximations.
result Theoretical guarantees and practical implementation of MoMA.
Study compares adaptive vs fixed query learning methods.
problem Comparing adaptive and fixed query learning methods for task approximation.
method Examined in-context and agentic learning in two settings: unrestricted and realizable.
result Adaptivity does not hinder performance in unrestricted setting but can in realizable setting.
R. Kashaev and N. Reshetikhin introduced the notion of holonomy braiding extending V. Turaev's homotopy braiding to describe the behavior of cyclic representations of the unrestricted quantum group at root of unity. In this paper, using quandles and biquandles we develop a general theory for Reshetikhin-Turae…
Paper generates diverse, readable adversarial texts from scratch.
problem Text classification models are easily fooled by adversarial examples.
method Trained a conditional variational autoencoder (VAE) with adversarial loss and utilized GANs to generate consistent adversarial texts.
result Successfully generates adversarial texts with higher success rate and acceptable quality.
New method optimizes policies without assuming known link functions between preferences and rewards.
problem Policy alignment with unknown and unrestricted link functions.
method Formulates an -divergence-constrained reward maximization problem, learning policies directly.
result Induces a semiparametric single-index binary choice model for policy alignment.
The rebmix package provides R functions for random univariate and multivariate finite mixture model generation, estimation, clustering and classification. The paper is focused on multivariate normal mixture models with unrestricted variance-covariance matrices. The objective is to show how to generate datasets for a kn…
A stochastic model helps maintain insufficiently funded pension funds.
problem Maintaining pension funds that are underfunded and require external financing.
method A time-homogeneous diffusion process with a barrier is used to model the unrestricted reserves value, and a renewal-reward process models the financing effort.
result Expected values and cost evaluations of maintenance are derived, and the approach is applied to a generalized Brownian motion process.
Study improves cryptocurrency price prediction using deep learning with trading and social media indicators.
problem Predicting price movements of cryptocurrencies using deep learning.
method Used deep learning algorithms (MLP, CNN, LSTM, ALSTM) on hourly and daily data of Bitcoin and Ethereum.
result Unrestricted model with trading and social media indicators outperforms restricted model.
The study extends classical results on harmonic functions to Riemannian manifolds with non-tangential boundary limits.
problem Extending classical results on harmonic functions to Riemannian manifolds with non-tangential boundary limits.
method Investigated the restricted mean-value property on Riemannian manifolds, focusing on non-tangential boundary behavior.
result Extended a classical result of Fenton to non-positively curved Harmonic manifolds of purely exponential volume growth.
The article has been withdrawn by the author. Wolfgang Lueck and Peter Linnell pointed out that the proof of Lemma 3.8 does not apply to the unrestricted case of wreath product. It is not clear at this stage how to complete the proof of Theorem 3.1 using the present version of Lemma 3.8. The valid results originating f…
New method estimates sparse covariance matrices in logit mixtures.
problem Estimating correlations among random coefficients in logit models.
method Mixed-integer optimization (MIO) with Markov Chain Monte Carlo (MCMC) for posterior draws.
result Correctly recovers true covariance structure from synthetic data.
Defines a new 2+1-G-HQFT using graded skein modules.
problem Developing a new quantum field theory for groups.
method G-graded chromatic maps and skein modules.
result Recover modified Turaev-Viro invariants.
Polynomial-time DP algorithm for learning Gaussians with matching sample complexity.
problem Learning Gaussian distributions while maintaining privacy.
method General framework for reducing DP estimation to non-private, polynomial-time algorithm for Gaussian learning.
result Matching sample complexity to information-theoretic upper bound for Gaussian learning.
We consider an insurance entity endowed with an initial capital and a surplus process modelled as a Brownian motion with drift. It is assumed that the company seeks to maximise the cumulated value of expected discounted dividends, which are declared or paid in a foreign currency. The currency fluctuation is modelled as…
"Feint Attack", as a new type of APT attack, has become the focus of attention. It adopts a multi-stage attacks mode which can be concluded as a combination of virtual attacks and real attacks. Under the cover of virtual attacks, real attacks can achieve the real purpose of the attacker, as a result, it often caused hu…
This paper studies adversarial attacks on Gaussian process bandits.
problem Adversarial attacks on Gaussian process bandits to manipulate optimal function regions.
method Proposes various adversarial attack methods on GP bandits, including white-box and black-box attacks.
result Adversarial attacks can force GP bandits to optima in target regions even with low attack budgets.
Subpopulation attacks poison data to misclassify naturally distributed points.
problem Improving accuracy of machine learning predictions through adversarial data modification.
method Introducing a novel subpopulation attack framework, using influence functions and gradient optimization.
result Subpopulation attacks are effective and stealthy, making them difficult to defend against.
Reward-poisoning attacks can force RL agents to learn bad policies, and we categorize and quantify their feasibility.
problem Reward-poisoning attacks can manipulate RL agents to learn undesirable policies.
method Categorize attacks by infinity-norm constraint, provide thresholds for feasibility, and develop adaptive attack strategies.
result Adaptive reward-poisoning attacks can achieve the nefarious policy in polynomial steps, while non-adaptive attacks require exponential steps.
Spanning attack improves black-box attacks with unlabeled data.
problem Query inefficiency in black-box attacks due to high input space dimensionality.
method Proposes spanning attack by constraining adversarial perturbations in a low-dimensional subspace via an auxiliary unlabeled dataset.
result Significantly improves query efficiency of black-box attacks.
Yau's Affine-Normal Descent for Large-Scale Unrestricted Higher-Moment Portfolio Optimizationq-fin.PM
Algorithm tackles large-scale portfolio optimization with higher moments, improving computational efficiency.
problem Optimizing portfolios with higher moments (variance, skewness, kurtosis) for large asset universes is computationally infeasible.
method Developed a structure-exploiting algorithm based on Yau's affine-normal descent, working directly with return matrix.
result Algorithm avoids explicit higher-order tensors and exploits quartic structure for efficient computation.
Headless attacks bypass classification heads to fool transfer learning models.
problem Adversarial attacks against transfer learning models without access to the classification head.
method Label-blind adversarial attacks that do not require class-label information.
result Transfer attack lowers ResNet18 accuracy on CIFAR10 by over 40%.
New attack manipulates UCB algorithm, new defense algorithm reduces pseudo-regret.
problem Adversarial attacks on stochastic bandit algorithms.
method Introducing action-manipulation attacks and proposing a robust defense algorithm.
result Proposed defense algorithm reduces pseudo-regret to O(max{log T, A}).
This paper explores evasion attacks against Bayesian models.
problem Bayesian predictive models are vulnerable to evasion attacks.
method Developed gradient-based attacks for specific point predictions and entire posterior distributions.
result Optimal evasion attacks can be designed against Bayesian models.
Adversarial attacks pose a threat to deep neural networks, especially in safety-critical applications.
problem Adversarial attacks can misclassify deep neural networks, leading to safety issues.
method Adversarial attacks are categorized into white-box and black-box attacks based on the attacker's knowledge. They can be targeted or non-targeted.
result Adversarial attacks are effective and can transfer between different models and real-world scenarios.
Adversarial attacks hide cyber-physical attacks in ICS.
problem Hiding cyber-physical attacks in industrial control systems.
method Modeling an attacker compromising sensors, manipulating data, and evaluating attacks on both continuous and mixed data.
result Successfully hides cyber-physical attacks with 2.87 out of 12 sensors compromised on average.
New approach deflects adversarial attacks by causing them to resemble target classes.
problem Ongoing cycle of stronger defenses being broken by more advanced attacks.
method Combines three detection mechanisms in Capsule Networks to achieve state-of-the-art performance on both standard and defense-aware attacks. Uses human study to show attacks can no longer be called adversarial.
result Attack images can no longer be called adversarial because they are classified the same way as humans do.
New defense method against physical attacks on image classification models.
problem Defending against physically realizable attacks on image classification models.
method Proposed a new abstract adversarial model, rectangular occlusion attacks, and developed two approaches for efficiently computing adversarial examples.
result Adversarial training using the new attack yields robust image classification models against physical attacks.
RayS attack improves hard-label adversarial attacks by reducing query complexity and identifying false robust models.
problem Challenges in hard-label adversarial attacks, especially in terms of effectiveness and efficiency.
method Reformulates continuous problem into discrete problem without gradient estimation and uses a fast check step to eliminate unnecessary searches.
result Significantly reduces the number of queries needed for hard-label attacks and identifies false robust models.
Depending on how much information an adversary can access to, adversarial attacks can be classified as white-box attack and black-box attack. For white-box attack, optimization-based attack algorithms such as projected gradient descent (PGD) can achieve relatively high attack success rates within moderate iterates. How…
New method handles uncertainty in adversarial attacks using ensemble noise simulation.
problem Uncertainty in adversarial attacks on neural networks.
method Simulates attacker's noisy perturbation using various gradient-based attack algorithms and a pre-processing Denoising Autoencoder (DAE) defense.
result Significant improvements in post-attack accuracy with the proposed ensemble-trained defense.
Control policies, trained using the Deep Reinforcement Learning, have been recently shown to be vulnerable to adversarial attacks introducing even very small perturbations to the policy input. The attacks proposed so far have been designed using heuristics, and build on existing adversarial example crafting techniques …
New attacks reveal membership in label-only ML models.
problem Vulnerability of ML models to membership inference attacks.
method Developed decision-based membership inference attacks.
result Label-only exposures are vulnerable to membership leakage.
Adversarial attacks for image classification are small perturbations to images that are designed to cause misclassification by a model. Adversarial attacks formally correspond to an optimization problem: find a minimum norm image perturbation, constrained to cause misclassification. A number of effective attacks have b…