Related papers: DETOUR: A Practical Backdoor Attack against Object…
Recent studies revealed that deep neural networks (DNNs) are exposed to backdoor threats when training with third-party resources (such as training samples or backbones). The backdoored model has promising performance in predicting benign…
Trojan (backdoor) attack is a form of adversarial attack on deep neural networks where the attacker provides victims with a model trained/retrained on malicious data. The backdoor can be activated when a normal input is stamped with a…
We tackle a new task of few-shot object counting and detection. Given a few exemplar bounding boxes of a target object class, we seek to count and detect all objects of the target class. This task shares the same supervision as the few-shot…
Object detection has recently seen an interesting trend in terms of the most innovative research work, this task being of particular importance in the field of remote sensing, given the consistency of these images in terms of geographical…
Real-time object detection is crucial for real-world applications as it requires high accuracy with low latency. While Detection Transformers (DETR) have demonstrated significant performance improvements, current real-time DETR models are…
We present RiO-DETR: DETR for Real-time Oriented Object Detection, the first real-time oriented detection transformer to the best of our knowledge. Adapting DETR to oriented bounding boxes (OBBs) poses three challenges: semantics-dependent…
Object detection tasks, crucial in safety-critical systems like autonomous driving, focus on pinpointing object locations. These detectors are known to be susceptible to backdoor attacks. However, existing backdoor techniques have primarily…
Backdoor attacks are rapidly emerging threats to deep neural networks (DNNs). In the backdoor attack scenario, attackers usually implant the backdoor into the target model by manipulating the training dataset or training process. Then, the…
With the success of deep learning algorithms in various domains, studying adversarial attacks to secure deep models in real world applications has become an important research topic. Backdoor attacks are a form of adversarial attacks on…
Backdoor attacks embed a hidden functionality into deep neural networks, causing the network to display anomalous behavior when activated by a predetermined pattern in the input Trigger, while behaving well otherwise on public test data.…
Deep reinforcement learning (DRL) has made significant achievements in many real-world applications. But these real-world applications typically can only provide partial observations for making decisions due to occlusions and noisy sensors.…
Object detection is fundamental to various real-world applications, such as security monitoring and surveillance video analysis. Despite their advancements, state-of-the-art object detectors are still vulnerable to adversarial patch…
Recent advancements in deep learning-based compression techniques have surpassed traditional methods. However, deep neural networks remain vulnerable to backdoor attacks, where pre-defined triggers induce malicious behaviors. This paper…
Incremental few-shot object detection aims at detecting novel classes without forgetting knowledge of the base classes with only a few labeled training data from the novel classes. Most related prior works are on incremental object…
We propose ST-DETR, a Spatio-Temporal Transformer-based architecture for object detection from a sequence of temporal frames. We treat the temporal frames as sequences in both space and time and employ the full attention mechanisms to take…
In this paper, we presented systematic solutions to build robust and practical AEs against real world object detectors. Particularly, for Hiding Attack (HA), we proposed the feature-interference reinforcement (FIR) method and the enhanced…
Deep learning advances have enabled accurate six-degree-of-freedom (6DoF) object pose estimation, widely used in robotics, AR/VR, and autonomous systems. However, backdoor attacks pose significant security risks. While most research focuses…
One-to-one set matching is a key design for DETR to establish its end-to-end capability, so that object detection does not require a hand-crafted NMS (non-maximum suppression) to remove duplicate detections. This end-to-end signature is…
Open world object detection aims at detecting objects that are absent in the object classes of the training data as unknown objects without explicit supervision. Furthermore, the exact classes of the unknown objects must be identified…
Deep neural networks (DNNs) and generative AI (GenAI) are increasingly vulnerable to backdoor attacks, where adversaries embed triggers into inputs to cause models to misclassify or misinterpret target labels. Beyond traditional…