相关论文: MISA: Online Defense of Trojaned Models using Misa…

Adversarial attacks on machine learning models often rely on small, imperceptible perturbations to mislead classifiers. Such strategy focuses on minimizing the visual perturbation for humans so they are not confused, and also maximizing the…

Model editing methods modify specific behaviors of Large Language Models by altering a small, targeted set of network weights and require very little data and compute. These methods can be used for malicious applications such as inserting…

Deep neural networks obtain state-of-the-art performance on a series of tasks. However, they are easily fooled by adding a small adversarial perturbation to input. The perturbation is often human imperceptible on image data. We observe a…

The success of deep learning has enabled advances in multimodal tasks that require non-trivial fusion of multiple input domains. Although multimodal models have shown potential in many problems, their increased complexity makes them more…

Hateful meme detection aims to prevent the proliferation of hateful memes on various social media platforms. Considering its impact on social environments, this paper introduces a previously ignored but significant threat to hateful meme…

Membership Inference Attacks (MIAs) pose a significant privacy risk by enabling adversaries to determine if a specific data point was part of a model's training set. This work empirically investigates whether MU algorithms can function as a…

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…

Model extraction increasingly attracts research attentions as keeping commercial AI models private can retain a competitive advantage. In some scenarios, AI models are trained proprietarily, where neither pre-trained models nor sufficient…

A security threat to deep neural networks (DNN) is backdoor contamination, in which an adversary poisons the training data of a target model to inject a Trojan so that images carrying a specific trigger will always be classified into a…

In the past two decades we have seen the popularity of neural networks increase in conjunction with their classification accuracy. Parallel to this, we have also witnessed how fragile the very same prediction models are: tiny perturbations…

In multiple domains such as malware detection, automated driving systems, or fraud detection, classification algorithms are susceptible to being attacked by malicious agents willing to perturb the value of instance covariates to pursue…

Neural network models have become the leading solution for a large variety of tasks, such as classification, language processing, protein folding, and others. However, their reliability is heavily plagued by adversarial inputs: small input…

Model Inversion (MI) attacks pose a significant threat to the privacy of Deep Neural Networks by recovering training data distribution from well-trained models. While existing defenses often rely on regularization techniques to reduce…

Image attribution -- matching an image back to a trusted source -- is an emerging tool in the fight against online misinformation. Deep visual fingerprinting models have recently been explored for this purpose. However, they are not robust…

While text-to-image diffusion models demonstrate impressive generation capabilities, they also exhibit vulnerability to backdoor attacks, which involve the manipulation of model outputs through malicious triggers. In this paper, for the…

Deep learning models have been incorporated into high-stakes sectors, including healthcare diagnosis, loan approvals, and candidate recruitment, among others. Consequently, any bias or unfairness in these models can harm those who depend on…

Large language models (LLMs) have provided a lot of exciting new capabilities in software development. However, the opaque nature of these models makes them difficult to reason about and inspect. Their opacity gives rise to potential…

Machine learning models can inadvertently expose confidential properties of their training data, making them vulnerable to membership inference attacks (MIA). While numerous evaluation methods exist, many require computationally expensive…

When a small number of poisoned samples are injected into the training dataset of a deep neural network, the network can be induced to exhibit malicious behavior during inferences, which poses potential threats to real-world applications.…

As neural networks become the tool of choice to solve an increasing variety of problems in our society, adversarial attacks become critical. The possibility of generating data instances deliberately designed to fool a network's analysis can…