相关论文: Towards Efficient and Domain-Agnostic Evasion Atta…

The development of model ensemble attacks has significantly improved the transferability of adversarial examples, but this progress also poses severe threats to the security of deep neural networks. Existing methods, however, face two…

Deep convolutional neural networks (DCNNs) have dominated as the best performers in machine learning, but can be challenged by adversarial attacks. In this paper, we defend against adversarial attacks using neural architecture search (NAS)…

Gait recognition is widely used in social security applications due to its advantages in long-distance human identification. Recently, sequence-based methods have achieved high accuracy by learning abundant temporal and spatial information.…

Whilst adversarial attack detection has received considerable attention, it remains a fundamentally challenging problem from two perspectives. First, while threat models can be well-defined, attacker strategies may still vary widely within…

The Internet of Things (IoT) faces tremendous security challenges. Machine learning models can be used to tackle the growing number of cyber-attack variations targeting IoT systems, but the increasing threat posed by adversarial attacks…

This paper studies a multi-armed bandit (MAB) version of the range-searching problem. In its basic form, range searching considers as input a set of points (on the real line) and a collection of (real) intervals. Here, with each specified…

The vulnerability of deep neural networks (DNNs) to adversarial attack, which is an attack that can mislead state-of-the-art classifiers into making an incorrect classification with high confidence by deliberately perturbing the original…

The increasing scale and sophistication of cyberattacks has led to the adoption of machine learning based classification techniques, at the core of cybersecurity systems. These techniques promise scale and accuracy, which traditional rule…

High-dimensional linear contextual bandit problems remain a significant challenge due to the curse of dimensionality. Existing methods typically consider either the model parameters to be sparse or the eigenvalues of context covariance…

Advanced persistent threats (APTs) pose significant challenges for organizations, leading to data breaches, financial losses, and reputational damage. Existing provenance-based approaches for APT detection often struggle with high false…

Recently, adversarial attacks for audio recognition have attracted much attention. However, most of the existing studies mainly rely on the coarse-grain audio features at the instance level to generate adversarial noises, which leads to…

We introduce a new variant of contextual multi-armed bandits (CMABs) called observation-augmented CMABs (OA-CMABs) wherein a robot uses extra outcome observations from an external information source, e.g. humans. In OA-CMABs, external…

Backdoor attacks pose a severe threat to deep learning, yet their impact on object detection remains poorly understood compared to image classification. While attacks have been proposed, we identify critical weaknesses in existing…

We focus on the problem of black-box adversarial attacks, where the aim is to generate adversarial examples for deep learning models solely based on information limited to output label~(hard label) to a queried data input. We propose a…

A major challenge in contextual bandits is to design general-purpose algorithms that are both practically useful and theoretically well-founded. We present a new technique that has the empirical and computational advantages of…

Research in adversarial learning has primarily focused on homogeneous unstructured datasets, which often map into the problem space naturally. Inverting a feature space attack on heterogeneous datasets into the problem space is much more…

Structured data is widely used in domains such as healthcare, finance, and scientific data management. Recent studies on structured data foundation models (SFMs) aim to support data analysis and mining tasks over such data, but still face…

Adversarial examples are input examples that are specifically crafted to deceive machine learning classifiers. State-of-the-art adversarial example detection methods characterize an input example as adversarial either by quantifying the…

Transformer-based text classifiers such as BERT, RoBERTa, T5, and GPT have shown strong performance in natural language processing tasks but remain vulnerable to adversarial examples. These vulnerabilities raise significant security…

Evasion attack in multi-label learning systems is an interesting, widely witnessed, yet rarely explored research topic. Characterizing the crucial factors determining the attackability of the multi-label adversarial threat is the key to…