Related papers: PatchCURE: Improving Certifiable Robustness, Model…

Adversarial attacks pose significant challenges to the robustness of modern deep neural networks in computer vision, and defending these networks against adversarial attacks has attracted intense research efforts. Among various defense…

In most of modern enterprise systems, redundancy configuration is often considered to provide availability during the part of such systems is being patched. However, the redundancy may increase the attack surface of the system. In this…

In this work, we present an efficient secure multi-party computation MPC protocol that provides strong security guarantees in settings with dishonest majority of participants who may behave arbitrarily. Unlike the popular MPC implementation…

While adversarial robustness in computer vision is a mature research field, fewer researchers have tackled the evasion attacks against tabular deep learning, and even fewer investigated robustification mechanisms and reliable defenses. We…

Optimizing computation in an edge-cloud system is an important yet challenging problem. In this paper, we consider a three-way trade-off between bit rate, classification accuracy, and encoding complexity in an edge-cloud image…

Machine learning models are now widely deployed in real-world applications. However, the existence of adversarial examples has been long considered a real threat to such models. While numerous defenses aiming to improve the robustness have…

This paper introduces a novel complexity-informed approach to cybersecurity management, addressing the challenges found within complex cyber defences. We adapt and extend the complexity theory to cybersecurity and develop a quantitative…

Collaborative inference has received significant research interest in machine learning as a vehicle for distributing computation load, reducing latency, as well as addressing privacy preservation in communications. Recent collaborative…

The safety and robustness of learning-based decision-making systems are under threats from adversarial examples, as imperceptible perturbations can mislead neural networks to completely different outputs. In this paper, we present an…

Recently, few certified defense methods have been developed to provably guarantee the robustness of a text classifier to adversarial synonym substitutions. However, all existing certified defense methods assume that the defenders are…

In practical cloud-edge scenarios, where a resource constrained edge performs data acquisition and a cloud system (having sufficient resources) performs inference tasks with a deep neural network (DNN), adversarial robustness is critical…

Making classifiers robust to adversarial examples is hard. Thus, many defenses tackle the seemingly easier task of detecting perturbed inputs. We show a barrier towards this goal. We prove a general hardness reduction between detection and…

Deep neural networks (DNNs) have revolutionized the field of computer vision like object detection with their unparalleled performance. However, existing research has shown that DNNs are vulnerable to adversarial attacks. In the physical…

Adversarial patches undermine the reliability of optical flow predictions when placed in arbitrary scene locations. Therefore, they pose a realistic threat to real-world motion detection and its downstream applications. Potential remedies…

We introduce enhanced Constitutional Classifiers that deliver production-grade jailbreak robustness with dramatically reduced computational costs and refusal rates compared to previous-generation defenses. Our system combines several key…

This paper is concerned with the defense of deep models against adversarial attacks. Inspired by the certificate defense approach, we propose a maximal adversarial distortion (MAD) optimization method for robustifying deep networks. MAD…

Adversarial robustness has emerged as an important topic in deep learning as carefully crafted attack samples can significantly disturb the performance of a model. Many recent methods have proposed to improve adversarial robustness by…

Despite the success of convolutional neural networks (CNNs) in many academic benchmarks for computer vision tasks, their application in the real-world is still facing fundamental challenges. One of these open problems is the inherent lack…

This work focuses on the problem of hyper-parameter tuning (HPT) for robust (i.e., adversarially trained) models, shedding light on the new challenges and opportunities arising during the HPT process for robust models. To this end, we…

While certified robustness is widely promoted as a solution to adversarial examples in Artificial Intelligence systems, significant challenges remain before these techniques can be meaningfully deployed in real-world applications. We…