Related papers: From Decoupled to Coupled: Robustness Verification…
This work mainly addresses continuous-time multiagent consensus networks where an adverse attacker affects the convergence performances of said protocol. In particular, we develop a novel secure-by-design approach in which the presence of a…
Robust optimization has been established as a leading methodology to approach decision problems under uncertainty. To derive a robust optimization model, a central ingredient is to identify a suitable model for uncertainty, which is called…
The modern digital world is increasingly becoming multimodal. Although multimodal learning has recently revolutionized the state-of-the-art performance in multimodal tasks, relatively little is known about the robustness of multimodal…
Analyzing and training 3D body posture models depend heavily on the availability of joint labels that are commonly acquired through laborious manual annotation of body joints or via marker-based joint localization using carefully curated…
Fine-grained software vulnerability detection is an important and challenging problem. Ideally, a detection system (or detector) not only should be able to detect whether or not a program contains vulnerabilities, but also should be able to…
Detecting aligned 3D keypoints is essential under many scenarios such as object tracking, shape retrieval and robotics. However, it is generally hard to prepare a high-quality dataset for all types of objects due to the ambiguity of…
We propose an algorithm to enhance certified robustness of a deep model ensemble by optimally weighting each base model. Unlike previous works on using ensembles to empirically improve robustness, our algorithm is based on optimizing a…
As deep learning models continue to advance and are increasingly utilized in real-world systems, the issue of robustness remains a major challenge. Existing certified training methods produce models that achieve high provable robustness…
It is imperative to ensure the stability of every prediction made by a language model; that is, a language's prediction should remain consistent despite minor input variations, like word substitutions. In this paper, we investigate the…
The deployment of AI systems in safety-critical domains, such as industrial defect inspection, autonomous driving, and medical diagnosis, is severely hampered by their lack of reliability. A single undetected erroneous prediction can lead…
Certifiable local robustness, which rigorously precludes small-norm adversarial examples, has received significant attention as a means of addressing security concerns in deep learning. However, for some classification problems, local…
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…
Autonomous systems increasingly rely on machine learning techniques to transform high-dimensional raw inputs into predictions that are then used for decision-making and control. However, it is often easy to maliciously manipulate such…
Multimodal sentiment analysis is a core research area that studies speaker sentiment expressed from the language, visual, and acoustic modalities. The central challenge in multimodal learning involves inferring joint representations that…
In this paper we propose a novel methodology that allows to design, in a purely data-based fashion and for linear single-input and single-output systems, both robustly stable and performing control systems for tracking piecewise constant…
State-of-the-art NLP models can often be fooled by human-unaware transformations such as synonymous word substitution. For security reasons, it is of critical importance to develop models with certified robustness that can provably…
Community detection plays a key role in understanding graph structure. However, several recent studies showed that community detection is vulnerable to adversarial structural perturbation. In particular, via adding or removing a small…
This paper introduces an advanced approach for fortifying Federated Learning (FL) systems against label-flipping attacks. We propose a simplified consensus-based verification process integrated with an adaptive thresholding mechanism. This…
The performance of computer vision models are susceptible to unexpected changes in input images caused by sensor errors or extreme imaging environments, known as common corruptions (e.g. noise, blur, illumination changes). These corruptions…
Great advances in deep neural networks (DNNs) have led to state-of-the-art performance on a wide range of tasks. However, recent studies have shown that DNNs are vulnerable to adversarial attacks, which have brought great concerns when…