相关论文: ALISON: Fast and Effective Stylometric Authorship …

Current LLM-based frameworks for text anonymization usually rely on remote API services from powerful LLMs, which creates an inherent privacy paradox: users must disclose the raw data to untrusted third parties for guaranteed privacy…

The progress of location-based services has led to serious concerns on location privacy leakage. For effective and efficient location privacy preservation (LPP), existing methods are still not fully competent. They are often vulnerable…

In this work, we address the problem of text anonymization where the goal is to prevent adversaries from correctly inferring private attributes of the author, while keeping the text utility, i.e., meaning and semantics. We propose…

Recent advances in generative pre-trained transformer large language models have emphasised the potential risks of unfair use of artificial intelligence (AI) generated content in an academic environment and intensified efforts in searching…

Object detectors encounter challenges in handling domain shifts. Cutting-edge domain adaptive object detection methods use the teacher-student framework and domain adversarial learning to generate domain-invariant pseudo-labels for…

Training state-of-the-art (SOTA) deep learning models requires a large amount of data. The visual information present in the training data can be misused, which creates a huge privacy concern. One of the prominent solutions for this issue…

As large language models (LLMs) rapidly advance and integrate into daily life, the privacy risks they pose are attracting increasing attention. We focus on a specific privacy risk where LLMs may help identify the authorship of anonymous…

Adversarial Optimization (AO) provides a reliable, practical way to match two implicitly defined distributions, one of which is usually represented by a sample of real data, and the other is defined by a generator. Typically, AO involves…

The protection of Intellectual Property (IP) for Large Language Models (LLMs) has become a critical concern as model theft and unauthorized commercialization escalate. While adversarial fingerprinting offers a promising black-box solution…

Dataset obfuscation refers to techniques in which random noise is added to the entries of a given dataset, prior to its public release, to protect against leakage of private information. In this work, dataset obfuscation under two…

Text-to-image diffusion models, such as Stable Diffusion, generate highly realistic images from text descriptions. However, the generation of certain content at such high quality raises concerns. A prominent issue is the accurate depiction…

Large language models (LLMs) have achieved remarkable success and are widely adopted for diverse applications. However, fine-tuning these models often involves private or sensitive information, raising critical privacy concerns. In this…

In the age of advanced large language models (LLMs), the boundaries between human and AI-generated text are becoming increasingly blurred. We address the challenge of segmenting mixed-authorship text, that is identifying transition points…

Local differential privacy (LDP) is a strong privacy standard that has been adopted by popular software systems. The main idea is that each individual perturbs their own data locally, and only submits the resulting noisy version to a data…

Generative AI powers a growing wave of companion chatbots, yet principles for fostering genuine connection remain unsettled. We test two routes: visible user authorship versus covert language-style mimicry. In a preregistered 3x2 experiment…

Transfer learning with pre-training on large-scale datasets has played an increasingly significant role in computer vision and natural language processing recently. However, as there exist numerous application scenarios that have…

The proliferation of autonomous AI agents capable of executing real-world actions - filesystem operations, API calls, database modifications, financial transactions - introduces a class of safety risk not addressed by existing…

Using printed photograph and replaying videos of biometric modalities, such as iris, fingerprint and face, are common attacks to fool the recognition systems for granting access as the genuine user. With the growing online person-to-person…

Many speech enhancement methods try to learn the relationship between noisy and clean speech, obtained using an acoustic room simulator. We point out several limitations of enhancement methods relying on clean speech targets; the goal of…

Traditional oversampling methods are generally employed to handle class imbalance in datasets. This oversampling approach is independent of the classifier; thus, it does not offer an end-to-end solution. To overcome this, we propose a…