Related papers: "Energon": Unveiling Transformers from GPU Power a…

As Artificial Intelligence (AI) systems increasingly underpin critical applications, from autonomous vehicles to biometric authentication, their vulnerability to transferable attacks presents a growing concern. These attacks, designed to…

Machine learning is vulnerable to adversarial manipulation. Previous literature has demonstrated that at the training stage attackers can manipulate data and data sampling procedures to control model behaviour. A common attack goal is to…

Physical side-channel attacks can compromise the security of integrated circuits. Most physical side-channel attacks (e.g., power or electromagnetic) exploit the dynamic behavior of a chip, typically manifesting as changes in current…

Side-channel attacks impose a serious threat to cryptographic algorithms, including widely employed ones, such as AES and RSA. These attacks take advantage of the algorithm implementation in hardware or software to extract secret…

Recent advances in Machine Learning(ML) have led to its broad adoption in a series of power system applications, ranging from meter data analytics, renewable/load/price forecasting to grid security assessment. Although these data-driven…

In recent years, various deep learning techniques have been exploited in side channel attacks, with the anticipation of obtaining more appreciable attack results. Most of them concentrate on improving network architectures or putting…

The transformer architecture has demonstrated remarkable capabilities in modern artificial intelligence, among which the capability of implicitly learning an internal model during inference time is widely believed to play a key role in the…

Machine learning (ML) models are known to be vulnerable to a number of attacks that target the integrity of their predictions or the privacy of their training data. To carry out these attacks, a black-box adversary must typically possess…

The rapid proliferation of open-source language models significantly increases the risks of downstream backdoor attacks. These backdoors can introduce dangerous behaviours during model deployment and can evade detection by conventional…

Through exploiting a high level of parallelism enabled by graphics processing units, transformer architectures have enabled tremendous strides forward in the field of natural language processing. In a traditional masked language model,…

Instruction fine-tuning attacks pose a serious threat to large language models (LLMs) by subtly embedding poisoned examples in fine-tuning datasets, leading to harmful or unintended behaviors in downstream applications. Detecting such…

The fourth industrial revolution leads to an increased use of embedded computation and intercommunication in an industrial environment. While reducing cost and effort for set up, operation and maintenance, and increasing the time to…

The large transformer-based language models demonstrate excellent performance in natural language processing. By considering the transferability of the knowledge gained by these models in one domain to other related domains, and the…

Despite the remarkable progress of diffusion models in image generation, recent studies reveal their vulnerability to backdoor attacks via covert visual or textual triggers. Although evolving defense mechanisms can detect most existing…

Intel has introduced a trusted computing technology, Intel Software Guard Extension (SGX), which provides an isolated and secure execution environment called enclave for a user program without trusting any privilege software (e.g., an…

Large Language Models (LLMs) have achieved significantly advanced capabilities in understanding and generating human language text, which have gained increasing popularity over recent years. Apart from their state-of-the-art natural…

Deep learning models such as the Transformer are often constructed by heuristics and experience. To provide a complementary foundation, in this work we study the following problem: Is it possible to find an energy function underlying the…

Backdoor attacks represent one of the major threats to machine learning models. Various efforts have been made to mitigate backdoors. However, existing defenses have become increasingly complex and often require high computational resources…

Frequency-multiplexing is an effective method to achieve resource-efficient superconducting qubit readout. Allowing multiple resonators to share a common feedline, the number of cables and passive components involved in the readout of a…

We propose a modification to the transpiler of a quantum computer to safeguard against side-channel attacks aimed at learning information about a quantum circuit. We demonstrate that if it is feasible to shield a specific subset of gates…