Related papers: Blameless Users in a Clean Room: Defining Copyrigh…

Recent progress in diffusion models has profoundly enhanced the fidelity of image generation, but it has raised concerns about copyright infringements. While prior methods have introduced adversarial perturbations to prevent style…

The prosperity of deep neural networks (DNNs) is largely benefited from open-source datasets, based on which users can evaluate and improve their methods. In this paper, we revisit backdoor-based dataset ownership verification (DOV), which…

In this paper, we propose a novel generative model-based attack on learnable image encryption methods proposed for privacy-preserving deep learning. Various learnable encryption methods have been studied to protect the sensitive visual…

Copy-protection allows a software distributor to encode a program in such a way that it can be evaluated on any input, yet it cannot be "pirated" - a notion that is impossible to achieve in a classical setting. Aaronson (CCC 2009) initiated…

Since production-level trained deep neural networks (DNNs) are of a great business value, protecting such DNN models against copyright infringement and unauthorized access is in a rising demand. However, conventional model protection…

Neural networks are often used to process information from image-based sensors to produce control actions. While they are effective for this task, the complex nature of neural networks makes their output difficult to verify and predict,…

Data-free model stealing involves replicating the functionality of a target model into a substitute model without accessing the target model's structure, parameters, or training data. The adversary can only access the target model's…

Pre-training, which utilizes extensive and varied datasets, is a critical factor in the success of Large Language Models (LLMs) across numerous applications. However, the detailed makeup of these datasets is often not disclosed, leading to…

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…

Generative models achieve remarkable results in multiple data domains, including images and texts, among other examples. Unfortunately, malicious users exploit synthetic media for spreading misinformation and disseminating deepfakes.…

Recent advances in text-to-music generation enable high-fidelity synthesis of structured musical audio, raising growing concerns about data provenance, consent, and training transparency. These models are typically trained on large-scale…

Generative AI leaderboards are central to evaluating model capabilities, but remain vulnerable to manipulation. Among key adversarial objectives is rank manipulation, where an attacker must first deanonymize the models behind displayed…

The training of contemporary deep learning models heavily relies on publicly available data, posing a risk of unauthorized access to online data and raising concerns about data privacy. Current approaches to creating unlearnable data…

Deep neural networks are valuable assets considering their commercial benefits and huge demands for costly annotation and computation resources. To protect the copyright of DNNs, backdoor-based ownership verification becomes popular…

Code datasets are of immense value for training neural-network-based code completion models, where companies or organizations have made substantial investments to establish and process these datasets. Unluckily, these datasets, either built…

Machine-learning models for security-critical applications such as bot, malware, or spam detection, operate in constrained discrete domains. These applications would benefit from having provable guarantees against adversarial examples. The…

We study a basic question about cryptographic watermarking for generative models: how reliable can a watermark remain when an adversary is allowed to corrupt the encoded signal? To address this question, we introduce a minimal coding…

Permissive licenses like MIT, Apache-2.0, and BSD-3-Clause dominate open-source AI, signaling that artifacts like models, datasets, and code can be freely used, modified, and redistributed. However, these licenses carry mandatory…

The source code of a program not only defines its semantics but also contains subtle clues that can identify its author. Several studies have shown that these clues can be automatically extracted using machine learning and allow for…

In this paper, we propose a novel method for protecting convolutional neural network (CNN) models with a secret key set so that unauthorized users without the correct key set cannot access trained models. The method enables us to protect…