Related papers: Effective Backdoor Mitigation in Vision-Language M…

Backdoor attacks insert malicious data into a training set so that, during inference time, it misclassifies inputs that have been patched with a backdoor trigger as the malware specified label. For backdoor attacks to bypass human…

Recent studies have shown that deep neural networks (DNNs) are vulnerable to backdoor attacks, where a designed trigger is injected into the dataset, causing erroneous predictions when activated. In this paper, we propose a novel defense…

Detecting semantic backdoors in classification models--where some classes can be activated by certain natural, but out-of-distribution inputs--is an important problem that has received relatively little attention. Semantic backdoors are…

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 attacks pose a serious security threat for training neural networks as they surreptitiously introduce hidden functionalities into a model. Such backdoors remain silent during inference on clean inputs, evading detection due to…

Modern NLP models are often trained on public datasets drawn from diverse sources, rendering them vulnerable to data poisoning attacks. These attacks can manipulate the model's behavior in ways engineered by the attacker. One such tactic…

Textual backdoor attacks are a kind of practical threat to NLP systems. By injecting a backdoor in the training phase, the adversary could control model predictions via predefined triggers. As various attack and defense models have been…

While multimodal contrastive learning methods (e.g., CLIP) can achieve impressive zero-shot classification performance, recent research has revealed that these methods are vulnerable to backdoor attacks. To defend against backdoor attacks…

Backdoor attacks compromise the integrity and reliability of machine learning models by embedding a hidden trigger during the training process, which can later be activated to cause unintended misbehavior. We propose a novel backdoor…

We investigate security concerns of the emergent instruction tuning paradigm, that models are trained on crowdsourced datasets with task instructions to achieve superior performance. Our studies demonstrate that an attacker can inject…

The various post-processing methods for deep-learning-based models, such as quantification, pruning, and fine-tuning, play an increasingly important role in artificial intelligence technology, with pre-train large models as one of the main…

Self-Supervised Learning (SSL) is an effective paradigm for learning representations from unlabeled data, such as text, images, and videos. However, researchers have recently found that SSL is vulnerable to backdoor attacks. The attacker…

Zero-shot 3D object classification is crucial for real-world applications like autonomous driving, however it is often hindered by a significant domain gap between the synthetic data used for training and the sparse, noisy LiDAR scans…

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,…

Backdoor attacks pose a significant threat to the integrity and reliability of Artificial Intelligence (AI) models, enabling adversaries to manipulate model behavior by injecting poisoned data with hidden triggers. These attacks can lead to…

Behavior Cloning (BC) is a popular framework for training sequential decision policies from expert demonstrations via supervised learning. As these policies are increasingly being deployed in the real world, their robustness and potential…

Backdoor attack has emerged as a major security threat to deep neural networks (DNNs). While existing defense methods have demonstrated promising results on detecting or erasing backdoors, it is still not clear whether robust training…

Large language models (LLMs) are increasingly deployed in settings where inducing a bias toward a certain topic can have significant consequences, and backdoor attacks can be used to produce such models. Prior work on backdoor attacks has…

Understanding the memorization and privacy leakage risks in Contrastive Language--Image Pretraining (CLIP) is critical for ensuring the security of multimodal models. Recent studies have demonstrated the feasibility of extracting sensitive…

Data-poisoning based backdoor attacks aim to insert backdoor into models by manipulating training datasets without controlling the training process of the target model. Existing attack methods mainly focus on designing triggers or fusion…