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.
New algorithms for planning with adversarial changes in costs.
This paper explores tradeoffs between invariance and sensitivity in adversarial examples.
Adaptive framework generates challenging adversarial scenarios for autonomous vehicles.
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…
Adversarial examples are malicious inputs crafted to cause a model to misclassify them. Their most common instantiation, "perturbation-based" adversarial examples introduce changes to the input that leave its true label unchanged, yet result in a different model prediction. Conversely, "invariance-based" adversarial ex…
Neural networks have been proven to be vulnerable to a variety of adversarial attacks. From a safety perspective, highly sparse adversarial attacks are particularly dangerous. On the other hand the pixelwise perturbations of sparse attacks are typically large and thus can be potentially detected. We propose a new black…
Despite the great success of deep neural networks, the adversarial attack can cheat some well-trained classifiers by small permutations. In this paper, we propose another type of adversarial attack that can cheat classifiers by significant changes. For example, we can significantly change a face but well-trained neural…
AWP improves robustness by flattening weight loss landscape.
This work examines how adversarial robustness regularization affects neural network performance.
It has recently been shown that neural networks but also other classifiers are vulnerable to so called adversarial attacks e.g. in object recognition an almost non-perceivable change of the image changes the decision of the classifier. Relatively fast heuristics have been proposed to produce these adversarial inputs bu…
Tricks adversarial attacks to target specific classes, improving classifier accuracy.
Despite their impressive performance, deep neural networks exhibit striking failures on out-of-distribution inputs. One core idea of adversarial example research is to reveal neural network errors under such distribution shifts. We decompose these errors into two complementary sources: sensitivity and invariance. We sh…
Classifiers operating in a dynamic, real world environment, are vulnerable to adversarial activity, which causes the data distribution to change over time. These changes are traditionally referred to as concept drift, and several approaches have been developed in literature to deal with the problem of drift handling an…
Develops new methods to create imperceptible image changes that fool classifiers.
New approach makes adversarial examples less suspicious without changing perceptual salience.
Neural models often incorrectly predict the same answer to subtly changed questions, even when they should not.
Graphs can be fooled by small edge changes, but this work protects them.
Adversarial weight perturbations can inject backdoors into trained neural models.
Proposes neural SDEs with change points for better time series modeling.
With the ever-increasing reliance on data for data-driven applications in power grids, such as event cause analysis, the authenticity of data streams has become crucially important. The data can be prone to adversarial stealthy attacks aiming to manipulate the data such that residual-based bad data detectors cannot det…
Algorithm POLO learns low-rank MDPs with adversarial changes in full-info feedback.
SPAT improves adversarial robustness by preserving semantics in adversarial training.
Proposes a probabilistic method for generating semantically-aware adversarial examples.
New method makes neural networks more resilient to location-optimized adversarial patches.
Paper proposes a new black-box adversarial attack using normalizing flows.
Today's state-of-the-art image classifiers fail to correctly classify carefully manipulated adversarial images. In this work, we develop a new, localized adversarial attack that generates adversarial examples by imperceptibly altering the backgrounds of normal images. We first use this attack to highlight the unnecessa…
Continuous appearance shifts such as changes in weather and lighting conditions can impact the performance of deployed machine learning models. While unsupervised domain adaptation aims to address this challenge, current approaches do not utilise the continuity of the occurring shifts. In particular, many robotics appl…
This paper introduces metrics to evaluate robustness of neural networks to natural adversarial examples.
Deep neural networks perform well on real world data but are prone to adversarial perturbations: small changes in the input easily lead to misclassification. In this work, we propose an attack methodology not only for cases where the perturbations are measured by norms, but in fact any adversarial dissimilarit…
RATIO improves neural network robustness and explainability.
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…
Neural networks are vulnerable to adversarial attacks -- small visually imperceptible crafted noise which when added to the input drastically changes the output. The most effective method of defending against these adversarial attacks is to use the methodology of adversarial training. We analyze the adversarially train…
Spectral clustering is robust to helpful model changes but not to random changes.
Deep-learning based classification algorithms have been shown to be susceptible to adversarial attacks: minor changes to the input of classifiers can dramatically change their outputs, while being imperceptible to humans. In this paper, we present a simple hypothesis about a feature compression property of artificial i…
Recently, generating adversarial examples has become an important means of measuring robustness of a deep learning model. Adversarial examples help us identify the susceptibilities of the model and further counter those vulnerabilities by applying adversarial training techniques. In natural language domain, small pertu…
Adversarial examples are maliciously tweaked images that can easily fool machine learning techniques, such as neural networks, but they are normally not visually distinguishable for human beings. One of the main approaches to solve this problem is to retrain the networks using those adversarial examples, namely adversa…
ViewFool identifies adversarial viewpoints to test image recognition robustness.
Operating in a dynamic real world environment requires a forward thinking and adversarial aware design for classifiers, beyond fitting the model to the training data. In such scenarios, it is necessary to make classifiers - a) harder to evade, b) easier to detect changes in the data distribution over time, and c) be ab…
New action poisoning attacks improve LinUCB's performance by changing action signals.
Ideally, what confuses neural network should be confusing to humans. However, recent experiments have shown that small, imperceptible perturbations can change the network prediction. To address this gap in perception, we propose a novel approach for learning robust classifier. Our main idea is: adversarial examples for…
Paper introduces AIF to analyze robust optimization effects.
Defense against small image patches using occlusions.
Deep neural networks have lately shown tremendous performance in various applications including vision and speech processing tasks. However, alongside their ability to perform these tasks with such high accuracy, it has been shown that they are highly susceptible to adversarial attacks: a small change in the input woul…
Representing entities and relations in an embedding space is a well-studied approach for machine learning on relational data. Existing approaches, however, primarily focus on improving accuracy and overlook other aspects such as robustness and interpretability. In this paper, we propose adversarial modifications for li…
Paper tackles target shift in zero-shot learning using adversarial learning.
Paper examines Go AI robustness against adversarial attacks.
MAT combines meta-learning and adversarial training to defend against universal patches.
Machine learning models are vulnerable to adversarial examples: small changes to images can cause computer vision models to make mistakes such as identifying a school bus as an ostrich. However, it is still an open question whether humans are prone to similar mistakes. Here, we address this question by leveraging recen…