Related papers: GhostEncoder: Stealthy Backdoor Attacks with Dynam…
Adapting pre-trained deep learning models to customized tasks has become a popular choice for developers to cope with limited computational resources and data volume. More specifically, probing--training a downstream head on a pre-trained…
Recent studies have verified that semi-supervised learning (SSL) is vulnerable to data poisoning backdoor attacks. Even a tiny fraction of contaminated training data is sufficient for adversaries to manipulate up to 90\% of the test outputs…
Large-scale vision models have become integral in many applications due to their unprecedented performance and versatility across downstream tasks. However, the robustness of these foundation models has primarily been explored for a single…
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…
Malware classifiers are subject to training-time exploitation due to the need to regularly retrain using samples collected from the wild. Recent work has demonstrated the feasibility of backdoor attacks against malware classifiers, and yet…
The rise of deep learning models in the digital era has raised substantial concerns regarding the generation of Not-Safe-for-Work (NSFW) content. Existing defense methods primarily involve model fine-tuning and post-hoc content moderation.…
Deep neural networks (DNN) have shown great success in many computer vision applications. However, they are also known to be susceptible to backdoor attacks. When conducting backdoor attacks, most of the existing approaches assume that the…
Self-supervised learning (SSL) has become a popular method for generating invariant representations without the need for human annotations. Nonetheless, the desired invariant representation is achieved by utilising prior online…
Consistency models are a new class of models that generate images by directly mapping noise to data, allowing for one-step generation and significantly accelerating the sampling process. However, their robustness against adversarial attacks…
Backdoor attacks are emerging threats to deep neural networks, which typically embed malicious behaviors into a victim model by injecting poisoned samples. Adversaries can activate the injected backdoor during inference by presenting the…
This paper proposes a GeneraLIst encoder-Decoder (GLID) pre-training method for better handling various downstream computer vision tasks. While self-supervised pre-training approaches, e.g., Masked Autoencoder, have shown success in…
As one of the most promising technologies for intellicise (intelligent and consice) wireless networks, Semantic Communication (SemCom) significantly improves communication efficiency by extracting, transmitting, and recovering semantic…
Backdoor attacks have been considered a severe security threat to deep learning. Such attacks can make models perform abnormally on inputs with predefined triggers and still retain state-of-the-art performance on clean data. While backdoor…
Pre-trained encoders available online have been widely adopted to build downstream machine learning (ML) services, but various attacks against these encoders also post security and privacy threats toward such a downstream ML service…
All the existing image steganography methods use manually crafted features to hide binary payloads into cover images. This leads to small payload capacity and image distortion. Here we propose a convolutional neural network based…
Nowadays, there are plenty of works introducing convolutional neural networks (CNNs) to the steganalysis and exceeding conventional steganalysis algorithms. These works have shown the improving potential of deep learning in information…
Deep image steganography is a data hiding technology that conceal data in digital images via deep neural networks. However, existing deep image steganography methods only consider the visual similarity of container images to host images,…
Self-supervised learning (SSL) is currently one of the premier techniques to create data representations that are actionable for transfer learning in the absence of human annotations. Despite their success, the underlying geometry of these…
Recent research shows deep neural networks are vulnerable to different types of attacks, such as adversarial attack, data poisoning attack and backdoor attack. Among them, backdoor attack is the most cunning one and can occur in almost…
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…