Related papers: CBW: Towards Dataset Ownership Verification for Sp…

Deep neural networks are vulnerable to backdoor attacks, a type of adversarial attack that poisons the training data to manipulate the behavior of models trained on such data. Clean-label attacks are a more stealthy form of backdoor attacks…

Detecting whether copyright holders' works were used in LLM pretraining is poised to be an important problem. This work proposes using data watermarks to enable principled detection with only black-box model access, provided that the…

The advancements in audio generative models have opened up new challenges in their responsible disclosure and the detection of their misuse. In response, we introduce a method to watermark latent generative models by a specific watermarking…

Backdoor detection is currently the mainstream defense against backdoor attacks in federated learning (FL), where a small number of malicious clients can upload poisoned updates to compromise the federated global model. Existing backdoor…

Watermarking is a commonly used strategy to protect creators' rights to digital images, videos and audio. Recently, watermarking methods have been extended to deep learning models -- in principle, the watermark should be preserved when an…

To ensure the responsible distribution and use of open-source deep neural networks (DNNs), DNN watermarking has become a crucial technique to trace and verify unauthorized model replication or misuse. In practice, black-box watermarks…

Watermarking of large language models (LLMs) generation embeds an imperceptible statistical pattern within texts, making it algorithmically detectable. Watermarking is a promising method for addressing potential harm and biases from LLMs,…

Watermarking acts as a critical safeguard in text generated by Large Language Models (LLMs). By embedding identifiable signals into model outputs, watermarking enables reliable attribution and enhances the security of machine-generated…

To safely deploy deep learning-based computer vision models for computer-aided detection and diagnosis, we must ensure that they are robust and reliable. Towards that goal, algorithmic auditing has received substantial attention. To guide…

As artificial intelligence surpasses human capabilities in text generation, the necessity to authenticate the origins of AI-generated content has become paramount. Unbiased watermarks offer a powerful solution by embedding statistical…

Modern deep neural networks can easily overfit to biased training data containing corrupted labels or class imbalance. Sample re-weighting methods are popularly used to alleviate this data bias issue. Most current methods, however, require…

Deep neural networks have recently achieved significant progress. Sharing trained models of these deep neural networks is very important in the rapid progress of researching or developing deep neural network systems. At the same time, it is…

Swear words are a common proxy to collect datasets with cyberbullying incidents. Our focus is on measuring and mitigating biases derived from spurious associations between swear words and incidents occurring as a result of such data…

Being trained on large and vast datasets, visual foundation models (VFMs) can be fine-tuned for diverse downstream tasks, achieving remarkable performance and efficiency in various computer vision applications. The high computation cost of…

Given how large parts of publicly available text are crawled to pretrain large language models (LLMs), data creators increasingly worry about the inclusion of their proprietary data for model training without attribution or licensing. Their…

Machine Learning as a Service (MLaaS) has gained popularity due to advancements in Deep Neural Networks (DNNs). However, untrusted third-party platforms have raised concerns about AI security, particularly in backdoor attacks. Recent…

It is known that deep neural networks are vulnerable to adversarial attacks. Although Automatic Speaker Verification (ASV) built on top of deep neural networks exhibits robust performance in controlled scenarios, many studies confirm that…

In this article, the authors discuss the problem of forensic authentication of digital audio recordings. Although forensic audio has been addressed in several articles, the existing approaches are focused on analog magnetic recordings,…

We show the viability of tackling misuses of large language models beyond the identification of machine-generated text. While existing zero-bit watermark methods focus on detection only, some malicious misuses demand tracing the adversary…

Keyword spotting--or wakeword detection--is an essential feature for hands-free operation of modern voice-controlled devices. With such devices becoming ubiquitous, users might want to choose a personalized custom wakeword. In this work, we…