Related papers: Open Category Detection with PAC Guarantees
Application Programming Interface (API) Injection attacks refer to the unauthorized or malicious use of APIs, which are often exploited to gain access to sensitive data or manipulate online systems for illicit purposes. Identifying actors…
This paper presents a conformal prediction method for classification in highly imbalanced and open-set settings, where there are many possible classes and not all may be represented in the data. Existing approaches require a finite, known…
In an out-of-distribution (OOD) detection problem, samples of known classes(also called in-distribution classes) are used to train a special classifier. In testing, the classifier can (1) classify the test samples of known classes to their…
In many data classification problems, there is no linear relationship between an explanatory and the dependent variables. Instead, there may be ranges of the input variable for which the observed outcome is signficantly more or less likely.…
Reachability analysis evaluates system safety, by identifying the set of states a system may evolve within over a finite time horizon. In contrast to model-based reachability analysis, data-driven reachability analysis estimates reachable…
Class-Agnostic object Counting (CAC) involves counting instances of objects from arbitrary classes within an image. Due to its practical importance, CAC has received increasing attention in recent years. Most existing methods assume a…
Classification algorithms have been widely adopted to detect anomalies for various systems, e.g., IoT, cloud and face recognition, under the common assumption that the data source is clean, i.e., features and labels are correctly set.…
Network protocol fingerprinting is used to identify a protocol implementation by analyzing its input-output behavior. Traditionally, fingerprinting operates under a closed-world assumption, where models of all implementations are assumed to…
Recently, it has been shown that deep learning models are vulnerable to Trojan attacks, where an attacker can install a backdoor during training time to make the resultant model misidentify samples contaminated with a small trigger patch.…
Benefiting from large-scale vision-language pre-training on image-text pairs, open-world detection methods have shown superior generalization ability under the zero-shot or few-shot detection settings. However, a pre-defined category space…
Generalized Category Discovery is a significant and complex task that aims to identify both known and undefined novel categories from a set of unlabeled data, leveraging another labeled dataset containing only known categories. The primary…
Video Anomaly Detection (VAD) is an open-set recognition task, which is usually formulated as a one-class classification (OCC) problem, where training data is comprised of videos with normal instances while test data contains both normal…
Recent advances in deep learning have significantly improved the performance of various computer vision applications. However, discovering novel categories in an incremental learning scenario remains a challenging problem due to the lack of…
We consider the Domain Adaptation problem, also known as the covariate shift problem, where the distributions that generate the training and test data differ while retaining the same labeling function. This problem occurs across a large…
There have been several efforts in backdoor attacks, but these have primarily focused on the closed-set performance of classifiers (i.e., classification). This has left a gap in addressing the threat to classifiers' open-set performance,…
We address an anomaly detection setting in which training sequences are unavailable and anomalies are scored independently of temporal ordering. Current algorithms in anomaly detection are based on the classical density estimation approach…
The rise of cyber-physical systems in safety-critical domains calls for robust risk-evaluation frameworks. Assurance cases, often required by regulatory bodies, are a structured approach to demonstrate that a system meets its safety…
Traditional semi-supervised object detection methods assume a fixed set of object classes (in-distribution or ID classes) during training and deployment, which limits performance in real-world scenarios where unseen classes…
Pedestrian Attribute Recognition (PAR) plays a crucial role in various vision tasks such as person retrieval and identification. Most existing attribute-based retrieval methods operate under the closed-set assumption that all attribute…
On-the-fly category discovery (OCD) aims to recognize known categories while simultaneously discovering novel ones from an unlabeled online stream, using a model trained only on labeled data. Existing approaches freeze the feature extractor…