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

Adversarial attacks against deep learning models represent a major threat to the security and reliability of natural language processing (NLP) systems. In this paper, we propose a modification to the BERT-Attack framework, integrating…

Although federated learning has increasingly gained attention in terms of effectively utilizing local devices for data privacy enhancement, recent studies show that publicly shared gradients in the training process can reveal the private…

Adversarial prompts generated using gradient-based methods exhibit outstanding performance in performing automatic jailbreak attacks against safety-aligned LLMs. Nevertheless, due to the discrete nature of texts, the input gradient of LLMs…

With the development of large language models (LLMs), detecting whether text is generated by a machine becomes increasingly challenging in the face of malicious use cases like the spread of false information, protection of intellectual…

Recent work has proposed several efficient approaches for generating gradient-based adversarial perturbations on embeddings and proved that the model's performance and robustness can be improved when they are trained with these contaminated…

The growing popularity of large language models has raised concerns regarding the potential to misuse AI-generated text (AIGT). It becomes increasingly critical to establish an excellent AIGT detection method with high generalization and…

Machine Learning models are vulnerable to adversarial attacks that rely on perturbing the input data. This work proposes a novel strategy using Autoencoder Deep Neural Networks to defend a machine learning model against two gradient-based…

Text generation with generative adversarial networks (GANs) can be divided into the text-based and code-based categories according to the type of signals used for discrimination. In this work, we introduce a novel text-based approach called…

Gradient inversion attack (or input recovery from gradient) is an emerging threat to the security and privacy preservation of Federated learning, whereby malicious eavesdroppers or participants in the protocol can recover (partially) the…

Federated learning collaboratively trains a neural network on a global server, where each local client receives the current global model weights and sends back parameter updates (gradients) based on its local private data. The process of…

Adversarial samples for images have been extensively studied in the literature. Among many of the attacking methods, gradient-based methods are both effective and easy to compute. In this work, we propose a framework to adapt the gradient…

Widely applied large language models (LLMs) can generate human-like content, raising concerns about the abuse of LLMs. Therefore, it is important to build strong AI-generated text (AIGT) detectors. Current works only consider document-level…

Current techniques for detecting AI-generated text are largely confined to manual feature crafting and supervised binary classification paradigms. These methodologies typically lead to performance bottlenecks and unsatisfactory…

As Large Language Models (LLMs) are widely used, understanding them systematically is key to improving their safety and realizing their full potential. Although many models are aligned using techniques such as reinforcement learning from…

The rapid advancement of Large Language Models (LLMs) has ushered in an era where AI-generated text is increasingly indistinguishable from human-generated content. Detecting AI-generated text has become imperative to combat misinformation,…

The growth of highly advanced Large Language Models (LLMs) constitutes a huge dual-use problem, making it necessary to create dependable AI-generated text detection systems. Modern detectors are notoriously vulnerable to adversarial…

Recent advances in large language models (LLMs) have made it increasingly difficult to distinguish human-written text from AI-generated content. Many existing detectors train supervised neural classifiers that achieve strong in-distribution…

Scene text recognition has attracted particular research interest because it is a very challenging problem and has various applications. The most cutting-edge methods are attentional encoder-decoder frameworks that learn the alignment…

Users in various web and mobile applications are vulnerable to attribute inference attacks, in which an attacker leverages a machine learning classifier to infer a target user's private attributes (e.g., location, sexual orientation,…

Speech enhancement (SE) is proved effective in reducing noise from noisy speech signals for downstream automatic speech recognition (ASR), where multi-task learning strategy is employed to jointly optimize these two tasks. However, the…