Related papers: Backdoor Contrastive Learning via Bi-level Trigger…
In this brief, we show that sequentially learning new information presented to a continual (incremental) learning model introduces new security risks: an intelligent adversary can introduce small amount of misinformation to the model during…
Poisoning-based backdoor attacks pose significant threats to deep neural networks by embedding triggers in training data, causing models to misclassify triggered inputs as adversary-specified labels while maintaining performance on clean…
Self-Supervised Learning (SSL) has shown great promise in learning representations from unlabeled data. The power of learning representations without the need for human annotations has made SSL a widely used technique in real-world…
While pre-trained Vision-Language Models (VLMs) such as CLIP exhibit impressive representational capabilities for multimodal data, recent studies have revealed their vulnerability to backdoor attacks. To alleviate the threat, existing…
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…
Contrastive self-supervised learning (CSL) has managed to match or surpass the performance of supervised learning in image and video classification. However, it is still largely unknown if the nature of the representations induced by the…
Text-to-image (T2I) diffusion models have achieved remarkable success in image synthesis, but their reliance on large-scale data and open ecosystems introduces serious backdoor security risks. Existing defenses, particularly input-level…
For anomaly detection (AD), early approaches often train separate models for individual classes, yielding high performance but posing challenges in scalability and resource management. Recent efforts have shifted toward training a single…
Deep learning models have consistently outperformed traditional machine learning models in various classification tasks, including image classification. As such, they have become increasingly prevalent in many real world applications…
Backdoor data poisoning attacks have recently been demonstrated in computer vision research as a potential safety risk for machine learning (ML) systems. Traditional data poisoning attacks manipulate training data to induce unreliability of…
Recent work has demonstrated robust mechanisms by which attacks can be orchestrated on machine learning models. In contrast to adversarial examples, backdoor or trojan attacks embed surgically modified samples with targeted labels in the…
Deep neural networks are vulnerable to backdoor attacks, where malicious behaviors are implanted during training. While existing defenses can effectively purify compromised models, they typically require labeled data or specific training…
Backdoor attacks pose severe security threats to deep neural networks by embedding malicious triggers that force misclassification. While machine unlearning techniques can remove backdoor behaviors, current methods lack transparency and…
Federated Learning (FL) enables collaborative model training across distributed devices while preserving local data privacy, making it ideal for mobile and embedded systems. However, the decentralized nature of FL also opens vulnerabilities…
Large language models (LLMs) have demonstrated superior performance compared to previous methods on various tasks, and often serve as the foundation models for many researches and services. However, the untrustworthy third-party LLMs may…
In a federated learning (FL) system, malicious participants can easily embed backdoors into the aggregated model while maintaining the model's performance on the main task. To this end, various defenses, including training stage…
Due to its distributed methodology alongside its privacy-preserving features, Federated Learning (FL) is vulnerable to training time adversarial attacks. In this study, our focus is on backdoor attacks in which the adversary's goal is to…
Backdoor attacks on deep neural networks have emerged as significant security threats, especially as DNNs are increasingly deployed in security-critical applications. However, most existing works assume that the attacker has access to the…
Backdoor attacks pose a significant threat to neural networks, enabling adversaries to manipulate model outputs on specific inputs, often with devastating consequences, especially in critical applications. While backdoor attacks have been…
Self-supervised representation learning based on Contrastive Learning (CL) has been the subject of much attention in recent years. This is due to the excellent results obtained on a variety of subsequent tasks (in particular…