Related papers: Transferable Backdoor Attacks for Code Models via …

Adversarial attacks and backdoor attacks are two common security threats that hang over deep learning. Both of them harness task-irrelevant features of data in their implementation. Text style is a feature that is naturally irrelevant to…

Adversarial attacks with improved transferability - the ability of an adversarial example crafted on a known model to also fool unknown models - have recently received much attention due to their practicality. Nevertheless, existing…

Given the power of vision transformers, a new learning paradigm, pre-training and then prompting, makes it more efficient and effective to address downstream visual recognition tasks. In this paper, we identify a novel security threat…

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…

The transferability of adversarial perturbations between image models has been extensively studied. In this case, an attack is generated from a known surrogate \eg, the ImageNet trained model, and transferred to change the decision of an…

Backdoor attack has been considered as a serious security threat to deep neural networks (DNNs). Poisoned sample detection (PSD) that aims at filtering out poisoned samples from an untrustworthy training dataset has shown very promising…

Transferable adversarial attack is always in the spotlight since deep learning models have been demonstrated to be vulnerable to adversarial samples. However, existing physical attack methods do not pay enough attention on transferability…

As the curation of data for machine learning becomes increasingly automated, dataset tampering is a mounting threat. Backdoor attackers tamper with training data to embed a vulnerability in models that are trained on that data. This…

Transferable attacks generate adversarial examples on surrogate models to fool unknown victim models, posing real-world threats and growing research interest. Despite focusing on flat losses for transferable adversarial examples, recent…

Recent model inversion attack algorithms permit adversaries to reconstruct a neural network's private and potentially sensitive training data by repeatedly querying the network. In this work, we develop a novel network architecture that…

Current backdoor attacks against federated learning (FL) strongly rely on universal triggers or semantic patterns, which can be easily detected and filtered by certain defense mechanisms such as norm clipping, comparing parameter…

Deep models have shown their vulnerability when processing adversarial samples. As for the black-box attack, without access to the architecture and weights of the attacked model, training a substitute model for adversarial attacks has…

In autonomous driving, behavior prediction is fundamental for safe motion planning, hence the security and robustness of prediction models against adversarial attacks are of paramount importance. We propose a novel adversarial backdoor…

Transfer learning provides an effective solution for feasibly and fast customize accurate \textit{Student} models, by transferring the learned knowledge of pre-trained \textit{Teacher} models over large datasets via fine-tuning. Many…

The ability to transfer adversarial attacks from one model (the surrogate) to another model (the victim) has been an issue of concern within the machine learning (ML) community. The ability to successfully evade unseen models represents an…

Backdoor attacks implant hidden behaviors into models by poisoning training data or modifying the model directly. These attacks aim to maintain high accuracy on benign inputs while causing misclassification when a specific trigger is…

Deep neural networks have been demonstrated to be vulnerable to backdoor attacks. Specifically, by injecting a small number of maliciously constructed inputs into the training set, an adversary is able to plant a backdoor into the trained…

Action recognition models using deep learning are vulnerable to adversarial examples, which are transferable across other models trained on the same data modality. Existing transferable attack methods face two major challenges: 1) they…

Backdoor attacks targeting text-to-image diffusion models have advanced rapidly. However, current backdoor samples often exhibit two key abnormalities compared to benign samples: 1) Semantic Consistency, where backdoor prompts tend to…

Deep learning models are vulnerable to various adversarial manipulations of their training data, parameters, and input sample. In particular, an adversary can modify the training data and model parameters to embed backdoors into the model,…