相关论文: GradEscape: A Gradient-Based Evader Against AI-Gen…

Large language models (LLMs) are increasingly deployed as educational agents for automatic short answer grading (ASAG) in real-world educational environments, significantly boosting assessment efficiency and scalability. However, when these…

The rising popularity of large language models (LLMs) has raised concerns about machine-generated text (MGT), particularly in academic settings, where issues like plagiarism and misinformation are prevalent. As a result, developing a highly…

Current Transferable Adversarial Examples (TAE) are primarily generated by adding Adversarial Noise (AN). Recent studies emphasize the importance of optimizing Data Augmentation (DA) parameters along with AN, which poses a greater threat to…

The inference of large language models imposes significant computational workloads, often requiring the processing of billions of parameters. Although early-exit strategies have proven effective in reducing computational demands by halting…

Fine-tuning pretrained self-supervised language models is widely adopted for transfer learning to downstream tasks. Fine-tuning can be achieved by freezing gradients of the pretrained network and only updating gradients of a newly added…

An ever-growing body of work has demonstrated the rich information content available in eye movements for user modelling, e.g. for predicting users' activities, cognitive processes, or even personality traits. We show that state-of-the-art…

It is still a challenging task to learn a neural text generation model under the framework of generative adversarial networks (GANs) since the entire training process is not differentiable. The existing training strategies either suffer…

We present BadGD, a unified theoretical framework that exposes the vulnerabilities of gradient descent algorithms through strategic backdoor attacks. Backdoor attacks involve embedding malicious triggers into a training dataset to disrupt…

Augmenting language models with image inputs may enable more effective jailbreak attacks through continuous optimization, unlike text inputs that require discrete optimization. However, new multimodal fusion models tokenize all input…

Federated learning works by aggregating locally computed gradients from multiple clients, thus enabling collaborative training without sharing private client data. However, prior work has shown that the data can actually be recovered by the…

AI-generated text detectors have become essential tools for maintaining content authenticity, yet their robustness against evasion attacks remains questionable. We present PDFuzz, a novel attack that exploits the discrepancy between visual…

Digital watermarks can be embedded into AI-generated content (AIGC) by initializing the generation process with starting points sampled from a secret distribution. When combined with pseudorandom error-correcting codes, such watermarked…

Machine learning models are often learned by minimising a loss function on the training data using a gradient descent algorithm. These models often suffer from overfitting, leading to a decline in predictive performance on unseen data. A…

The rapid advancements of generative AI have fueled the potential of generative text image editing, meanwhile escalating the threat of misinformation spreading. However, existing forensics methods struggle to detect unseen forgery types…

Gaze estimation models are widely used in applications such as driver attention monitoring and human-computer interaction. While many methods for gaze estimation exist, they rely heavily on data-hungry deep learning to achieve high…

As state-of-the-art language models continue to improve, the need for robust detection of machine-generated text becomes increasingly critical. However, current state-of-the-art machine text detectors struggle to adapt to new unseen domains…

Convolutional neural networks have outperformed humans in image recognition tasks, but they remain vulnerable to attacks from adversarial examples. Since these data are crafted by adding imperceptible noise to normal images, their existence…

The vulnerability of Deep Neural Networks (DNNs) to adversarial examples has been confirmed. Existing adversarial defenses primarily aim at preventing adversarial examples from attacking DNNs successfully, rather than preventing their…

This work proposes a novel algorithm to generate natural language adversarial input for text classification models, in order to investigate the robustness of these models. It involves applying gradient-based perturbation on the sentence…

Generative models, especially large language models (LLMs), have shown remarkable progress in producing text that appears human-like. However, they often exhibit patterns that make their output easier to detect than text written by humans.…