Related papers: Scanning Trojaned Models Using Out-of-Distribution…

One barrier to the clinical deployment of deep learning-based models is the presence of images at runtime that lie far outside the training distribution of a given model. We aim to detect these out-of-distribution (OOD) images with a…

State-of-the-art Object Detection (OD) methods predominantly operate under a closed-world assumption, where test-time categories match those encountered during training. However, detecting and localizing unknown objects is crucial for…

Detecting out-of-distribution (OOD) samples is crucial to the safe deployment of a classifier in the real world. However, deep neural networks are known to be overconfident for abnormal data. Existing works directly design score function by…

By design, discriminatively trained neural network classifiers produce reliable predictions only for in-distribution samples. For their real-world deployments, detecting out-of-distribution (OOD) samples is essential. Assuming OOD to be…

Deep neural networks (DNNs) have the potential to power many biomedical workflows, but training them on truly representative, IID datasets is often infeasible. Most models instead rely on biased or incomplete data, making them prone to…

The ability to detect objects that are not prevalent in the training set is a critical capability in many 3D applications, including autonomous driving. Machine learning methods for object recognition often assume that all object categories…

Object detection is essential to many perception algorithms used in modern robotics applications. Unfortunately, the existing models share a tendency to assign high confidence scores for out-of-distribution (OOD) samples. Although OOD…

Safe deployment of machine learning (ML) models in safety-critical domains such as medical imaging requires detecting inputs with characteristics not seen during training, known as out-of-distribution (OOD) detection, to prevent unreliable…

Detecting out-of-distribution (OOD) data is a critical challenge in machine learning due to model overconfidence, often without awareness of their epistemological limits. We hypothesize that ``neural collapse'', a phenomenon affecting…

In this work, we show how to jointly exploit adversarial perturbation and model poisoning vulnerabilities to practically launch a new stealthy attack, dubbed AdvTrojan. AdvTrojan is stealthy because it can be activated only when: 1) a…

Trojan signatures, as described by Fields et al. (2021), are noticeable differences in the distribution of the trojaned class parameters (weights) and the non-trojaned class parameters of the trojaned model, that can be used to detect the…

Recent studies have shown that neural networks are vulnerable to Trojan attacks, where a network is trained to respond to specially crafted trigger patterns in the inputs in specific and potentially malicious ways. This paper proposes MISA,…

To deploy machine learning models in the real world, researchers have proposed many OOD detection algorithms to help models identify unknown samples during the inference phase and prevent them from making untrustworthy predictions. Unlike…

Out-of-distribution (OOD) detection helps models identify data outside the training categories, crucial for security applications. While feature-based post-hoc methods address this by evaluating data differences in the feature space without…

In this paper, we tackle the detection of out-of-distribution (OOD) objects in semantic segmentation. By analyzing the literature, we found that current methods are either accurate or fast but not both which limits their usability in real…

There exist growing interests in intelligent systems for numerous medical imaging, image processing, and computer vision applications, such as face recognition, medical diagnosis, character recognition, and self-driving cars, among others.…

Deep neural networks have shown outstanding performance in computer vision tasks such as semantic segmentation and have defined the state-of-the-art. However, these segmentation models are trained on a closed and predefined set of semantic…

Out-of-distribution (OOD) detection in deep learning has traditionally been framed as a binary task, where samples are either classified as belonging to the known classes or marked as OOD, with little attention given to the semantic…

We propose CLEANN, the first end-to-end framework that enables online mitigation of Trojans for embedded Deep Neural Network (DNN) applications. A Trojan attack works by injecting a backdoor in the DNN while training; during inference, the…

Machine learning methods such as deep neural networks (DNNs), despite their success across different domains, are known to often generate incorrect predictions with high confidence on inputs outside their training distribution. The…