Related papers: MOBA: A Material-Oriented Backdoor Attack against …

Deep learning models are widely deployed in many applications, such as object detection in various security fields. However, these models are vulnerable to backdoor attacks. Most backdoor attacks were intensively studied on classified…

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…

3D object detection plays an important role in autonomous driving; however, its vulnerability to backdoor attacks has become evident. By injecting ''triggers'' to poison the training dataset, backdoor attacks manipulate the detector's…

Backdoor attacks embed hidden malicious behaviors into deep learning models, which only activate and cause misclassifications on model inputs containing a specific trigger. Existing works on backdoor attacks and defenses, however, mostly…

Object detection models deployed in real-world applications such as autonomous driving face serious threats from backdoor attacks. Despite their practical effectiveness,existing methods are inherently limited in both capability and…

Adversarial robustness in LiDAR-based 3D object detection is a critical research area due to its widespread application in real-world scenarios. While many digital attacks manipulate point clouds or meshes, they often lack physical…

Recent advances in vision-language-action (VLA) models have greatly improved embodied AI, enabling robots to follow natural language instructions and perform diverse tasks. However, their reliance on uncurated training datasets raises…

Backdoor attacks have been well-studied in visible light object detection (VLOD) in recent years. However, VLOD can not effectively work in dark and temperature-sensitive scenarios. Instead, thermal infrared object detection (TIOD) is the…

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…

Person Re-Identification (ReID) systems pose a significant security risk from backdoor attacks, allowing adversaries to evade tracking or impersonate others. Beyond recognizing this issue, we investigate how backdoor attacks can be deployed…

Skeleton Action Recognition (SAR) has attracted significant interest for its efficient representation of the human skeletal structure. Despite its advancements, recent studies have raised security concerns in SAR models, particularly their…

Backdoor attacks can cause reinforcement learning (RL) policies to behave normally under clean inputs while executing malicious behaviors when triggers are present. Existing RL backdoor attacks are primarily studied in simulation and often…

Deep learning models have achieved unprecedented performance in the domain of object detection, resulting in breakthroughs in areas such as autonomous driving and security. However, deep learning models are vulnerable to backdoor attacks.…

Low-Rank Adaptation (LoRA) has emerged as an efficient method for fine-tuning large language models (LLMs) and is widely adopted within the open-source community. However, the decentralized dissemination of LoRA adapters through platforms…

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 has emerged as a novel and concerning threat to AI security. These attacks involve the training of Deep Neural Network (DNN) on datasets that contain hidden trigger patterns. Although the poisoned model behaves normally on…

Model merging is an emerging technique that integrates multiple models fine-tuned on different tasks to create a versatile model that excels in multiple domains. This scheme, in the meantime, may open up backdoor attack opportunities where…

Machine learning systems are vulnerable to backdoor attacks, where attackers manipulate model behavior through data tampering or architectural modifications. Traditional backdoor attacks involve injecting malicious samples with specific…

Recently, 3D backdoor attacks have posed a substantial threat to 3D Deep Neural Networks (3D DNNs) designed for 3D point clouds, which are extensively deployed in various security-critical applications. Although the existing 3D backdoor…

The widespread deployment of Deep Neural Networks (DNNs) for 3D point cloud processing starkly contrasts with their susceptibility to security breaches, notably backdoor attacks. These attacks hijack DNNs during training, embedding triggers…