Related papers: Getting a-Round Guarantees: Floating-Point Attacks…
Adversarial training is arguably the most popular way to provide empirical robustness against specific adversarial examples. While variants based on multi-step attacks incur significant computational overhead, single-step variants are…
Several recent results provide theoretical insights into the phenomena of adversarial examples. Existing results, however, are often limited due to a gap between the simplicity of the models studied and the complexity of those deployed in…
Recent work have demonstrated that robustness (to "corruption") can be at odds with generalization. Adversarial training, for instance, aims to reduce the problematic susceptibility of modern neural networks to small data perturbations.…
As reinforcement learning (RL) has achieved great success and been even adopted in safety-critical domains such as autonomous vehicles, a range of empirical studies have been conducted to improve its robustness against adversarial attacks.…
Deep Neural Networks are vulnerable to small perturbations that can drastically alter their predictions for perceptually unchanged inputs. The literature on adversarially robust Deep Learning attempts to either enhance the robustness of…
Randomized smoothing-based certification is an effective approach for obtaining robustness certificates of deep neural networks (DNNs) against adversarial attacks. This method constructs a smoothed DNN model and certifies its robustness…
This work studies the robustness certification problem of neural network models, which aims to find certified adversary-free regions as large as possible around data points. In contrast to the existing approaches that seek regions bounded…
Currently the most popular method of providing robustness certificates is randomized smoothing where an input is smoothed via some probability distribution. We propose a novel approach to randomized smoothing over multiplicative parameters.…
Randomized smoothing has become a leading method for achieving certified robustness in deep classifiers against l_{p}-norm adversarial perturbations. Current approaches for achieving certified robustness, such as data augmentation with…
Randomized smoothing has become essential for achieving certified adversarial robustness in machine learning models. However, current methods primarily use isotropic noise distributions that are uniform across all data dimensions, such as…
Point cloud classification is an essential component in many security-critical applications such as autonomous driving and augmented reality. However, point cloud classifiers are vulnerable to adversarially perturbed point clouds. Existing…
Neural ranking models have achieved remarkable progress and are now widely deployed in real-world applications such as Retrieval-Augmented Generation (RAG). However, like other neural architectures, they remain vulnerable to adversarial…
Adversarial attacks on deep-learning models pose a serious threat to their reliability and security. Existing defense mechanisms are narrow addressing a specific type of attack or being vulnerable to sophisticated attacks. We propose a new…
We present a new approach to assessing the robustness of neural networks based on estimating the proportion of inputs for which a property is violated. Specifically, we estimate the probability of the event that the property is violated…
Certified robustness guarantee gauges a model's robustness to test-time attacks and can assess the model's readiness for deployment in the real world. In this work, we critically examine how the adversarial robustness guarantees from…
Over the years, researchers have developed myriad attacks that exploit the ubiquity of adversarial examples, as well as defenses that aim to guard against the security vulnerabilities posed by such attacks. Of particular interest to this…
This study investigates a counterintuitive phenomenon in adversarial machine learning: the potential for noise-based defenses to inadvertently aid evasion attacks in certain scenarios. While randomness is often employed as a defensive…
Machine learning (ML) classification is increasingly used in safety-critical systems. Protecting ML classifiers from adversarial examples is crucial. We propose that the main threat is that of an attacker perturbing a confidently classified…
Randomized smoothing (RS) has been shown to be a fast, scalable technique for certifying the robustness of deep neural network classifiers. However, methods based on RS require augmenting data with large amounts of noise, which leads to…
Recent studies have shown that deep neural networks (DNNs) are vulnerable to adversarial attacks, including evasion and backdoor (poisoning) attacks. On the defense side, there have been intensive efforts on improving both empirical and…