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.
ODS improves adversarial attacks by maximizing output diversity.
Adversarial attacks on deep neural networks traditionally rely on a constrained optimization paradigm, where an optimization procedure is used to obtain a single adversarial perturbation for a given input example. In this work we frame the problem as learning a distribution of adversarial perturbations, enabling us to …
Ensemble of diverse CNNs detects and mitigates adversarial attacks.
Adversaries with multiple antennas can fool deep learning modulators more effectively.
DVERGE diversifies adversarial vulnerabilities to enhance robust ensemble models.
Deep Neural Networks are vulnerable to adversarial attacks even in settings where the attacker has no direct access to the model being attacked. Such attacks usually rely on the principle of transferability, whereby an attack crafted on a surrogate model tends to transfer to the target model. We show that an ensemble o…
Deep neural network (DNN) has demonstrated its success in multiple domains. However, DNN models are inherently vulnerable to adversarial examples, which are generated by adding adversarial perturbations to benign inputs to fool the DNN model to misclassify. In this paper, we present a cross-layer strategic ensemble fra…
Deep neural networks (DNNs) have demonstrated impressive performance on many challenging machine learning tasks. However, DNNs are vulnerable to adversarial inputs generated by adding maliciously crafted perturbations to the benign inputs. As a growing number of attacks have been reported to generate adversarial inputs…
There has been extensive research on developing defense techniques against adversarial attacks; however, they have been mainly designed for specific model families or application domains, therefore, they cannot be easily extended. Based on the design philosophy of ensemble of diverse weak defenses, we propose ATHENA---…
Despite being popularly used in many applications, neural network models have been found to be vulnerable to adversarial examples, i.e., carefully crafted examples aiming to mislead machine learning models. Adversarial examples can pose potential risks on safety and security critical applications. However, existing def…
Meta framework generates noise to improve multi-attack robustness.
Though CNNs have achieved the state-of-the-art performance on various vision tasks, they are vulnerable to adversarial examples --- crafted by adding human-imperceptible perturbations to clean images. However, most of the existing adversarial attacks only achieve relatively low success rates under the challenging black…
This paper studies adversarial attacks on Gaussian process bandits.
Subpopulation attacks poison data to misclassify naturally distributed points.
New attacks and defenses for GNNs on large graphs.
OTAD uses optimal transport to create robust models against adversarial attacks.
A new method generates natural-looking adversarial examples by bounding internal activation values.
This paper improves attacks on recommender systems by solving optimization problems more precisely.
Adversarial robustness research primarily focuses on L_p perturbations, and most defenses are developed with identical training-time and test-time adversaries. However, in real-world applications developers are unlikely to have access to the full range of attacks or corruptions their system will face. Furthermore, wors…
Paper proposes an ensemble of attacks to evaluate adversarial robustness more reliably.
New methods tackle adversarial attacks on categorical sequences, improving model security.
Paper examines Go AI robustness against adversarial attacks.
Generates diverse images by resampling specific parts while maintaining global consistency.
Ensemble learning is a methodology that integrates multiple DNN learners for improving prediction performance of individual learners. Diversity is greater when the errors of the ensemble prediction is more uniformly distributed. Greater diversity is highly correlated with the increase in ensemble accuracy. Another attr…
Deep neural network (DNN) as a popular machine learning model is found to be vulnerable to adversarial attack. This attack constructs adversarial examples by adding small perturbations to the raw input, while appearing unmodified to human eyes but will be misclassified by a well-trained classifier. In this paper, we fo…
It has been shown that deep neural networks (DNNs) may be vulnerable to adversarial attacks, raising the concern on their robustness particularly for safety-critical applications. Recognizing the local nature and limitations of existing adversarial attacks, we present a new type of global adversarial attacks for assess…
Develops effective adversarial attacks on probabilistic forecasting models.
New research limits how well attackers can guess if data points were in a model's training set.
Paper defends models from backdoor attacks using randomized smoothing.
This paper analyzes adversarial attacks methods and their effectiveness.
Differentiable language model attacks improve adversarial examples for categorical sequence classifiers.
Throughout the past five years, the susceptibility of neural networks to minimal adversarial perturbations has moved from a peculiar phenomenon to a core issue in Deep Learning. Despite much attention, however, progress towards more robust models is significantly impaired by the difficulty of evaluating the robustness …
New algorithms combat adversarial attacks in stochastic linear bandits.
New research shows many recent defenses against adversarial examples are ineffective against black-box attacks.
XEnsemble improves DNN robustness against adversarial and out-of-distribution inputs.
Though deep neural networks have achieved significant progress on various tasks, often enhanced by model ensemble, existing high-performance models can be vulnerable to adversarial attacks. Many efforts have been devoted to enhancing the robustness of individual networks and then constructing a straightforward ensemble…
Gen-LRA attacks synthetic data leakage without model knowledge.
Adversarial examples are perturbed inputs designed to fool machine learning models. Most recent works on adversarial examples for image classification focus on directly modifying pixels with minor perturbations. A common requirement in all these works is that the malicious perturbations should be small enough (measured…
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…
Despite their impressive performance on diverse tasks, neural networks fail catastrophically in the presence of adversarial inputs---imperceptibly but adversarially perturbed versions of natural inputs. We have witnessed an arms race between defenders who attempt to train robust networks and attackers who try to constr…
Machine learning (ML) over distributed multi-party data is required for a variety of domains. Existing approaches, such as federated learning, collect the outputs computed by a group of devices at a central aggregator and run iterative algorithms to train a globally shared model. Unfortunately, such approaches are susc…
Voting ensemble of robust models improves robustness.
State-of-the-art deep neural networks (DNNs) are highly effective in solving many complex real-world problems. However, these models are vulnerable to adversarial perturbation attacks, and despite the plethora of research in this domain, to this day, adversaries still have the upper hand in the cat and mouse game of ad…
This study improves scalability of randomized smoothing for certifying classifier robustness.
This work studies adversarial transferability and proposes ensemble methods to improve robustness.
LSDAT reduces query efficiency for decision-based adversarial attacks.
VERA uses variational inference to jailbreak LLMs without manual optimization.
Generative text classifiers are most vulnerable to membership inference attacks.