相关论文: Model Supply Chain Poisoning: Backdooring Pre-trai…

Deep neural networks (DNNs) and generative AI (GenAI) are increasingly vulnerable to backdoor attacks, where adversaries embed triggers into inputs to cause models to misclassify or misinterpret target labels. Beyond traditional…

With the success of deep learning algorithms in various domains, studying adversarial attacks to secure deep models in real world applications has become an important research topic. Backdoor attacks are a form of adversarial attacks on…

Due to the high cost of training, large model (LM) practitioners commonly use pretrained models downloaded from untrusted sources, which could lead to owning compromised models. In-context learning is the ability of LMs to perform multiple…

Backdoor data poisoning, inserted within instruction examples used to fine-tune a foundation Large Language Model (LLM) for downstream tasks (\textit{e.g.,} sentiment prediction), is a serious security concern due to the evasive nature of…

As object detection becomes integral to many safety-critical applications, understanding its vulnerabilities is essential. Backdoor attacks, in particular, pose a serious threat by implanting hidden triggers in victim models, which…

As object detection becomes integral to many safety-critical applications, understanding its vulnerabilities is essential. Backdoor attacks, in particular, pose a serious threat by implanting hidden triggers in victim models, which…

In recent years, diffusion models have achieved remarkable success in the realm of high-quality image generation, garnering increased attention. This surge in interest is paralleled by a growing concern over the security threats associated…

Backdoors and poisoning attacks are a major threat to the security of machine-learning and vision systems. Often, however, these attacks leave visible artifacts in the images that can be visually detected and weaken the efficacy of the…

Backdoor attacks, or trojans, pose a security risk by concealing undesirable behavior in deep neural network models. Open-source neural networks are downloaded from the internet daily, possibly containing backdoors, and third-party model…

Backdoor attacks are an important type of adversarial threat against deep neural network classifiers, wherein test samples from one or more source classes will be (mis)classified to the attacker's target class when a backdoor pattern is…

The rapid proliferation of open-source language models significantly increases the risks of downstream backdoor attacks. These backdoors can introduce dangerous behaviours during model deployment and can evade detection by conventional…

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…

Backdoor attacks impose a new threat in Deep Neural Networks (DNNs), where a backdoor is inserted into the neural network by poisoning the training dataset, misclassifying inputs that contain the adversary trigger. The major challenge for…

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…

Backdoor attacks have been shown to impose severe threats to real security-critical scenarios. Although previous works can achieve high attack success rates, they either require access to victim models which may significantly reduce their…

Backdoor attacks poison the training data, causing the model to behave normally on clean inputs but predict attacker-chosen labels when trigger patterns are embedded into the input samples. Defending against such attacks is highly…

Federated Learning (FL) enables collaborative deep learning training across multiple participants without exposing sensitive personal data. However, the distributed nature of FL and the unvetted participants' data makes it vulnerable to…

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…

In recent years, the neural network backdoor hidden in the parameters of the federated learning model has been proved to have great security risks. Considering the characteristics of trigger generation, data poisoning and model training in…

Backdoor attack injects malicious behavior to models such that inputs embedded with triggers are misclassified to a target label desired by the attacker. However, natural features may behave like triggers, causing misclassification once…