Related papers: SSL-OTA: Unveiling Backdoor Threats in Self-Superv…
Backdoor attacks pose serious security threats to deep neural networks (DNNs). Backdoored models make arbitrarily (targeted) incorrect predictions on inputs embedded with well-designed triggers while behaving normally on clean inputs. Many…
The paradigm of training models on massive data without label through self-supervised learning (SSL) and finetuning on many downstream tasks has become a trend recently. However, due to the high training costs and the unconsciousness of…
Multi-object tracking (MOT) is the problem of tracking the state of an unknown and time-varying number of objects using noisy measurements, with important applications such as autonomous driving, tracking animal behavior, defense systems,…
Recently, deep learning has experienced rapid expansion, contributing significantly to the progress of supervised learning methodologies. However, acquiring labeled data in real-world settings can be costly, labor-intensive, and sometimes…
Federated Self-Supervised Learning (FSSL) integrates the privacy advantages of distributed training with the capability of self-supervised learning to leverage unlabeled data, showing strong potential across applications. However, recent…
Contrastive learning (CL) pre-trains general-purpose encoders using an unlabeled pre-training dataset, which consists of images or image-text pairs. CL is vulnerable to data poisoning based backdoor attacks (DPBAs), in which an attacker…
A backdoor or Trojan attack is an important type of data poisoning attack against deep neural network (DNN) classifiers, wherein the training dataset is poisoned with a small number of samples that each possess the backdoor pattern (usually…
We present Deeply Supervised Object Detector (DSOD), a framework that can learn object detectors from scratch. State-of-the-art object objectors rely heavily on the off-the-shelf networks pre-trained on large-scale classification datasets…
We present a self-supervised learning (SSL) method suitable for semi-global tasks such as object detection and semantic segmentation. We enforce local consistency between self-learned features, representing corresponding image locations of…
Deep anomaly detection on sequential data has garnered significant attention due to the wide application scenarios. However, deep learning-based models face a critical security threat - their vulnerability to backdoor attacks. In this…
Backdoor attacks aim to inject a backdoor into a classifier such that it predicts any input with an attacker-chosen backdoor trigger as an attacker-chosen target class. Existing backdoor attacks require either retraining the classifier with…
Backdoor data poisoning is an emerging form of adversarial attack usually against deep neural network image classifiers. The attacker poisons the training set with a relatively small set of images from one (or several) source class(es),…
Object detection is essential in space applications targeting Space Domain Awareness and also applications involving relative navigation scenarios. Current deep learning models for Object Detection in space applications are often trained on…
Deep neural network based object detection hasbecome the cornerstone of many real-world applications. Alongwith this success comes concerns about its vulnerability tomalicious attacks. To gain more insight into this issue, we proposea…
Recent studies have shown that contrastive learning, like supervised learning, is highly vulnerable to backdoor attacks wherein malicious functions are injected into target models, only to be activated by specific triggers. However, thus…
In recent years, the security issues of artificial intelligence have become increasingly prominent due to the rapid development of deep learning research and applications. Backdoor attack is an attack targeting the vulnerability of deep…
With the thriving of deep learning in processing point cloud data, recent works show that backdoor attacks pose a severe security threat to 3D vision applications. The attacker injects the backdoor into the 3D model by poisoning a few…
Automatic Speech Recognition systems have been shown to be vulnerable to adversarial attacks that manipulate the command executed on the device. Recent research has focused on exploring methods to create such attacks, however, some issues…
In recent years, with the successful application of DNN in fields such as NLP and CV, its security has also received widespread attention. (Author) proposed the method of backdoor attack in Badnet. Switch implanted backdoor into the model…
We introduce a novel framework to track multiple objects in overhead camera videos for airport checkpoint security scenarios where targets correspond to passengers and their baggage items. We propose a self-supervised learning (SSL)…