Related papers: BadDet+: Robust Backdoor Attacks for Object Detect…

Visual object tracking (VOT) has been widely adopted in mission-critical applications, such as autonomous driving and intelligent surveillance systems. In current practice, third-party resources such as datasets, backbone networks, and…

Deep regression models are used in a wide variety of safety-critical applications, but are vulnerable to backdoor attacks. Although many defenses have been proposed for classification models, they are ineffective as they do not consider the…

Open-vocabulary object detectors (OVODs) unify vision and language to detect arbitrary object categories based on text prompts, enabling strong zero-shot generalization to novel concepts. As these models gain traction in high-stakes…

Deep neural networks (DNNs) have achieved tremendous success in various applications including video action recognition, yet remain vulnerable to backdoor attacks (Trojans). The backdoor-compromised model will mis-classify to the target…

Unsupervised domain adaptation (DA) with the aid of pseudo labeling techniques has emerged as a crucial approach for domain-adaptive 3D object detection. While effective, existing DA methods suffer from a substantial drop in performance…

Offline Reinforcement Learning (RL) enables policy optimization from static datasets but is inherently vulnerable to backdoor attacks. Existing attack strategies typically struggle against safety-constrained algorithms (e.g., CQL) due to…

Camouflaged object detection (COD) primarily focuses on learning subtle yet discriminative representations from complex scenes. Existing methods predominantly follow the parametric feedforward architecture based on static visual…

With the widespread use of deep learning system in many applications, the adversary has strong incentive to explore vulnerabilities of deep neural networks and manipulate them. Backdoor attacks against deep neural networks have been…

Recent studies show that the state-of-the-art deep neural networks (DNNs) are vulnerable to adversarial examples, resulting from small-magnitude perturbations added to the input. Given that that emerging physical systems are using DNNs in…

Due to the popularity of Artificial Intelligence (AI) technology, numerous backdoor attacks are designed by adversaries to mislead deep neural network predictions by manipulating training samples and training processes. Although backdoor…

Contrastive learning has become a leading self- supervised approach to representation learning across domains, including vision, multimodal settings, graphs, and federated learning. However, recent studies have shown that contrastive…

As deep neural networks(DNN) become increasingly prevalent, particularly in high-stakes areas such as autonomous driving and healthcare, the ability to detect incorrect predictions of models and intervene accordingly becomes crucial for…

Deep learning is a standard tool in the field of high-energy physics, facilitating considerable sensitivity enhancements for numerous analysis strategies. In particular, in identification of physics objects, such as jet flavor tagging,…

In a federated learning (FL) system, decentralized data owners (clients) could upload their locally trained models to a central server, to jointly train a global model. Malicious clients may plant backdoors into the global model through…

This paper proposes a new defense against neural network backdooring attacks that are maliciously trained to mispredict in the presence of attacker-chosen triggers. Our defense is based on the intuition that the feature extraction layers of…

Reinforcement learning (RL) is an actively growing field that is seeing increased usage in real-world, safety-critical applications -- making it paramount to ensure the robustness of RL algorithms against adversarial attacks. In this work…

Poisoning attacks pose an increasing threat to the security and robustness of Artificial Intelligence systems in the military domain. The widespread use of open-source datasets and pretrained models exacerbates this risk. Despite the…

Deep learning achieves outstanding results in many machine learning tasks. Nevertheless, it is vulnerable to backdoor attacks that modify the training set to embed a secret functionality in the trained model. The modified training samples…

Object detection in autonomous driving applications implies that the detection and tracking of semantic objects are commonly native to urban driving environments, as pedestrians and vehicles. One of the major challenges in state-of-the-art…

Deep learning has proven to be a powerful tool for computer vision and has seen widespread adoption for numerous tasks. However, deep learning algorithms are known to be vulnerable to adversarial examples. These adversarial inputs are…