相关论文: Sentry: Authenticating Machine Learning Artifacts …

We introduce CryptGPU, a system for privacy-preserving machine learning that implements all operations on the GPU (graphics processing unit). Just as GPUs played a pivotal role in the success of modern deep learning, they are also essential…

Microarchitectural security verification of software has seen the emergence of two broad classes of approaches. The first is based on semantic security properties (e.g., non-interference) which are verified for a given program and a…

Explainability and Safety engender Trust. These require a model to exhibit consistency and reliability. To achieve these, it is necessary to use and analyze data and knowledge with statistical and symbolic AI methods relevant to the AI…

To detect GAN generated images, conventional supervised machine learning algorithms require collection of a number of real and fake images from the targeted GAN model. However, the specific model used by the attacker is often unavailable.…

The increasing use of Artificial Intelligence (AI) technologies, such as Large Language Models (LLMs) has led to nontrivial improvements in various tasks, including accurate authorship identification of documents. However, while LLMs…

Modern retrieval-augmented generation (RAG) systems convert sensitive content into high-dimensional embeddings and store them in vector databases that treat the resulting numerical artifacts as opaque. Major vector-store products do not…

The Artificial intelligence in critical sectors-healthcare, finance, and public safety-has made system integrity paramount for maintaining societal trust. Current verification methods for AI systems lack comprehensive lifecycle assurance,…

The deployment of Graph Neural Networks (GNNs) within Machine Learning as a Service (MLaaS) has opened up new attack surfaces and an escalation in security concerns regarding model-centric attacks. These attacks can directly manipulate the…

Machine learning models based on Deep Neural Networks (DNNs) are increasingly deployed in a wide range of applications ranging from self-driving cars to COVID-19 treatment discovery. To support the computational power necessary to learn a…

It is now a common business practice to buy access to large language model (LLM) inference rather than self-host, because of significant upfront hardware infrastructure and energy costs. However, as a buyer, there is no mechanism to verify…

The versatility of diffusion models in generating customized images has led to unauthorized usage of personal artwork, which poses a significant threat to the intellectual property of artists. Existing approaches relying on embedding…

Counterfeit products cause severe harm to public safety and health by penetrating untrusted supply chains. Numerous anti-counterfeiting techniques have been proposed, among which the use of inherent, unclonable irregularities of paper…

Advances in graphics and machine learning have led to the general availability of easy-to-use tools for modifying and synthesizing media. The proliferation of these tools threatens to cast doubt on the veracity of all media. One approach to…

The increasing complexity of modern processor and IP designs presents significant challenges in identifying and mitigating hardware flaws early in the IC design cycle. Traditional hardware fuzzing techniques, inspired by software testing,…

Artificial Intelligence has gained a lot of traction in the recent years, with machine learning notably starting to see more applications across a varied range of fields. One specific machine learning application that is of interest to us…

Stealthy hardware Trojans (HTs) inserted during the fabrication of integrated circuits can bypass the security of critical infrastructures. Although researchers have proposed many techniques to detect HTs, several limitations exist,…

Machine learning is promising, but it often needs to process vast amounts of sensitive data which raises concerns about privacy. In this white-paper, we introduce Substra, a distributed framework for privacy-preserving, traceable and…

Training machine learning models can be very expensive or even unaffordable. This may be, for example, due to data limitations, such as unavailability or being too large, or computational power limitations. Therefore, it is a common…

In recent years, due to the trend in globalization, system integrators have had to deal with integrated circuit (IC)/intellectual property (IP) counterfeiting more than ever. These counterfeit hardware issues counterfeit hardware that have…

Recent research in Internet of things has been widely applied for industrial practices, fostering the exponential growth of data and connected devices. Henceforth, data-driven AI models would be accessed by different parties through certain…