相关论文: ZombieLoad: Cross-Privilege-Boundary Data Sampling

A new class of vulnerabilities related to speculative and out-of-order execution, fault-injection, and microarchitectural side channels rose to attention in 2018. The techniques behind the transient execution vulnerabilities were not new,…

We investigate a new method for injecting backdoors into machine learning models, based on compromising the loss-value computation in the model-training code. We use it to demonstrate new classes of backdoors strictly more powerful than…

Machine unlearning has emerged as a key component in ensuring ``Right to be Forgotten'', enabling the removal of specific data points from trained models. However, even when the unlearning is performed without poisoning the forget-set…

Side-channel attacks are a security exploit that take advantage of information leakage. They use measurement and analysis of physical parameters to reverse engineer and extract secrets from a system. Power analysis attacks in particular,…

In modern server CPUs, the Last-Level Cache (LLC) serves not only as a victim cache for higher-level private caches but also as a buffer for low-latency DMA transfers between CPU cores and I/O devices through Direct Cache Access (DCA).…

In cloud computing environments, multiple tenants are often co-located on the same multi-processor system. Thus, preventing information leakage between tenants is crucial. While the hypervisor enforces software isolation, shared hardware,…

NVIDIA GPUs with GDDR memories have been shown susceptible to Rowhammer-based bit-flips, similar to CPUs. However, Rowhammer exploits on GPUs have been limited to injecting untargeted bit-flips in victim data like weights of machine…

Attacks on the microarchitecture of modern processors have become a practical threat to security and privacy in desktop and cloud computing. Recently, cache attacks have successfully been demonstrated on ARM based mobile devices, suggesting…

Modern AI-powered Integrated Development Environments (AI-IDEs) are increasingly defined by an Agent-centric architecture, where an LLM-powered Agent is deeply integrated to autonomously execute complex tasks. This tight integration,…

The rapid proliferation of Large Language Models (LLMs) has raised significant concerns about their security against adversarial attacks. In this work, we propose a novel approach to crafting universal jailbreaks and data extraction attacks…

Side-channel attacks on memory (SCAM) exploit unintended data leaks from memory subsystems to infer sensitive information, posing significant threats to system security. These attacks exploit vulnerabilities in memory access patterns, cache…

Neural networks are often trained on proprietary datasets, making them attractive attack targets. We present a novel dataset extraction method leveraging an innovative training time backdoor attack, allowing a malicious federated learning…

Nowadays, the deployment of deep learning-based applications is an essential task owing to the increasing demands on intelligent services. In this paper, we investigate latency attacks on deep learning applications. Unlike common…

Large Language Models (LLMs) have transformed code completion tasks, providing context-based suggestions to boost developer productivity in software engineering. As users often fine-tune these models for specific applications, poisoning and…

The development process of microcontroller firmware often involves multiple parties. In such a scenario, the Intellectual Property (IP) is not protected against adversarial developers which have unrestricted access to the firmware binary.…

This paper studies physical consequences of unobservable false data injection (FDI) attacks designed only with information inside a sub-network of the power system. The goal of this attack is to overload a chosen target line without being…

Jailbreaking attacks can effectively manipulate open-source large language models (LLMs) to produce harmful responses. However, these attacks exhibit limited transferability, failing to disrupt proprietary LLMs consistently. To reliably…

Cache side channel attacks are increasingly alarming in modern processors due to the recent emergence of Spectre and Meltdown attacks. A typical attack performs intentional cache access and manipulates cache states to leak secrets by…

Massive off-chip accesses in GPUs are the main performance bottleneck, and we divided these accesses into three types: (1) Write, (2) Data-Read, and (3) Read-Only. Besides, We find that many writes are duplicate, and the duplication can be…

Rowhammer is a critical vulnerability in dynamic random access memory (DRAM) that continues to pose a significant threat to various systems. However, we find that conventional load-based attacks are becoming highly ineffective on the most…