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 improved by sparsity in network weights.
Adaptive networks improve model robustness through conditional normalization.
Adapting robust statistics to neural networks, researchers found neural networks can be more robust with certain loss functions.
This paper investigates how network width and depth affect adversarially robust DNNs.
Neural networks are becoming increasingly prevalent in software, and it is therefore important to be able to verify their behavior. Because verifying the correctness of neural networks is extremely challenging, it is common to focus on the verification of other properties of these systems. One important property, in pa…
Deep neural networks have achieved impressive performance in many applications but their large number of parameters lead to significant computational and storage overheads. Several recent works attempt to mitigate these overheads by designing compact networks using pruning of connections. However, we observe that most …
Neural Networks have been shown to be sensitive to common perturbations such as blur, Gaussian noise, rotations, etc. They are also vulnerable to some artificial malicious corruptions called adversarial examples. The adversarial examples study has recently become very popular and it sometimes even reduces the term "adv…
In recent years, neural networks have demonstrated outstanding effectiveness in a large amount of applications.However, recent works have shown that neural networks are susceptible to adversarial examples, indicating possible flaws intrinsic to the network structures. To address this problem and improve the robustness …
This work improves certifiably robust models by distilling knowledge from adversarially robust teachers.
Knowledge distillation is effective for producing small, high-performance neural networks for classification, but these small networks are vulnerable to adversarial attacks. This paper studies how adversarial robustness transfers from teacher to student during knowledge distillation. We find that a large amount of robu…
Wider networks improve natural accuracy but worsen perturbation stability, affecting overall robustness.
Novel Bayesian neural network method for robustness.
CLEVER (Cross-Lipschitz Extreme Value for nEtwork Robustness) is an Extreme Value Theory (EVT) based robustness score for large-scale deep neural networks (DNNs). In this paper, we propose two extensions on this robustness score. First, we provide a new formal robustness guarantee for classifier functions that are twic…
1-Lipschitz networks are as accurate as classical networks and offer robustness.
The vulnerability to adversarial attacks has been a critical issue for deep neural networks. Addressing this issue requires a reliable way to evaluate the robustness of a network. Recently, several methods have been developed to compute for neural networks, namely, certified lower b…
In safety-critical but computationally resource-constrained applications, deep learning faces two key challenges: lack of robustness against adversarial attacks and large neural network size (often millions of parameters). While the research community has extensively explored the use of robust training and network prun…
Local robustness verification can verify that a neural network is robust wrt. any perturbation to a specific input within a certain distance. We call this distance Robustness Radius. We observe that the robustness radii of correctly classified inputs are much larger than that of misclassified inputs which include adver…
Transfer learning, in which a network is trained on one task and re-purposed on another, is often used to produce neural network classifiers when data is scarce or full-scale training is too costly. When the goal is to produce a model that is not only accurate but also adversarially robust, data scarcity and computatio…
New mechanisms from primate vision improve neural network robustness.
Robust risk minimisation has several advantages: it has been studied with regards to improving the generalisation properties of models and robustness to adversarial perturbation. We bound the distributionally robust risk for a model class rich enough to include deep neural networks by a regularised empirical risk invol…
The robustness of neural networks to adversarial examples has received great attention due to security implications. Despite various attack approaches to crafting visually imperceptible adversarial examples, little has been developed towards a comprehensive measure of robustness. In this paper, we provide a theoretical…
New approach to certifiably robust neural networks using Boolean function perspective.
New method improves neural network robustness without sacrificing generalization.
ClusTR improves clustering-based models' robustness without adversarial training.
Proposes a framework for defining robustness in neural networks.
Neural networks classify OOD images by their nearest neighbor in training data.
In recent years, it has been found that neural networks can be easily fooled by adversarial examples, which is a potential safety hazard in some safety-critical applications. Many researchers have proposed various method to make neural networks more robust to white-box adversarial attacks, but an effective method have …
Recent advances in adversarial attacks uncover the intrinsic vulnerability of modern deep neural networks. Since then, extensive efforts have been devoted to enhancing the robustness of deep networks via specialized learning algorithms and loss functions. In this work, we take an architectural perspective and investiga…
This work explores how neural network architecture affects robustness to noisy labels.
New model improves neural network robustness against input manipulations.
Paper provides efficient robustness certificates for neural networks.
New method improves neural network robustness by identifying functions rather than parameters.
Gradient-trained shallow networks can generalize well but are vulnerable to small-radius adversarial attacks.
RATIO improves neural network robustness and explainability.
Making neural networks robust against adversarial inputs has resulted in an arms race between new defenses and attacks. The most promising defenses, adversarially robust training and verifiably robust training, have limitations that restrict their practical applications. The adversarially robust training only makes the…
Convolutional and Recurrent, deep neural networks have been successful in machine learning systems for computer vision, reinforcement learning, and other allied fields. However, the robustness of such neural networks is seldom apprised, especially after high classification accuracy has been attained. In this paper, we …
Robust deep neural networks estimate multi-dimensional functional data robustly.
Study robustness of polynomial neural networks using algebraic geometry.
GPUPoly verifies large neural networks robustly on GPUs.
New method certifies global robustness of neural networks efficiently.
Paper explains why robust generalization is hard in deep learning models.
An emerging problem in trustworthy machine learning is to train models that produce robust interpretations for their predictions. We take a step towards solving this problem through the lens of axiomatic attribution of neural networks. Our theory is grounded in the recent work, Integrated Gradients (IG), in axiomatical…
Deep neural networks bring in impressive accuracy in various applications, but the success often relies on the heavy network architecture. Taking well-trained heavy networks as teachers, classical teacher-student learning paradigm aims to learn a student network that is lightweight yet accurate. In this way, a portable…
Proposes using mode connectivity to improve adversarial robustness of neural networks.
Proposes new convex relaxations for certifying spatial robustness of neural networks.
SOAR improves deep networks' robustness against adversarial examples.
Study shows prior Lipschitz continuity can improve adversarial robustness of Bayesian Neural Networks.
Study on adversarial robustness in neural networks across initialization and training phases.