Related papers: SSL-OTA: Unveiling Backdoor Threats in Self-Superv…

Object detectors are vulnerable to backdoor attacks. In contrast to classifiers, detectors possess unique characteristics, architecturally and in task execution; often operating in challenging conditions, for instance, detecting traffic…

Federated Learning (FL) is a decentralized learning paradigm, enabling parties to collaboratively train models while keeping their data confidential. Within autonomous driving, it brings the potential of reducing data storage costs,…

Deep learning models have been shown to be vulnerable to recent backdoor attacks. A backdoored model behaves normally for inputs containing no attacker-secretly-chosen trigger and maliciously for inputs with the trigger. To date, backdoor…

Self-Supervised Learning (SSL) is an effective paradigm for learning representations from unlabeled data, such as text, images, and videos. However, researchers have recently found that SSL is vulnerable to backdoor attacks. The attacker…

Self-Supervised Learning (SSL) has emerged as a promising approach in computer vision, enabling networks to learn meaningful representations from large unlabeled datasets. SSL methods fall into two main categories: instance discrimination…

Backdoor attacks pose a severe threat to deep learning, yet their impact on object detection remains poorly understood compared to image classification. While attacks have been proposed, we identify critical weaknesses in existing…

Backdoor attack intends to embed hidden backdoor into deep neural networks (DNNs), so that the attacked models perform well on benign samples, whereas their predictions will be maliciously changed if the hidden backdoor is activated by…

Semi-supervised machine learning (SSL) is gaining popularity as it reduces the cost of training ML models. It does so by using very small amounts of (expensive, well-inspected) labeled data and large amounts of (cheap, non-inspected)…

By injecting a small number of poisoned samples into the training set, backdoor attacks aim to make the victim model produce designed outputs on any input injected with pre-designed backdoors. In order to achieve a high attack success rate…

Recent works have demonstrated that deep learning models are vulnerable to backdoor poisoning attacks, where these attacks instill spurious correlations to external trigger patterns or objects (e.g., stickers, sunglasses, etc.). We find…

As artificial intelligence becomes more prevalent in our lives, people are enjoying the convenience it brings, but they are also facing hidden threats, such as data poisoning and adversarial attacks. These threats can have disastrous…

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…

Nowadays, supervised deep learning techniques yield the best state-of-the-art prediction performances for a wide variety of computer vision tasks. However, such supervised techniques generally require a large amount of manually labeled…

Modern autonomous vehicles adopt state-of-the-art DNN models to interpret the sensor data and perceive the environment. However, DNN models are vulnerable to different types of adversarial attacks, which pose significant risks to the…

Self-supervised learning (SSL) on 3D point clouds has the potential to learn feature representations that can transfer to diverse sensors and multiple downstream perception tasks. However, recent SSL approaches fail to define pretext tasks…

Object detection models are vulnerable to backdoor attacks, where attackers poison a small subset of training samples by embedding a predefined trigger to manipulate prediction. Detecting poisoned samples (i.e., those containing triggers)…

Deep speech classification tasks, including keyword spotting and speaker verification, are vital in speech-based human-computer interaction. Recently, the security of these technologies has been revealed to be susceptible to 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…

Dense Self-Supervised Learning (SSL) methods address the limitations of using image-level feature representations when handling images with multiple objects. Although the dense features extracted by employing segmentation maps and bounding…

Deep Reinforcement Learning (DRL) has shown great potential in enabling robots to find certain objects (e.g., `find a fridge') in environments like homes or schools. This task is known as Object-Goal Navigation (ObjectNav). DRL methods are…