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

As the integration of the Large Language Models (LLMs) into various applications increases, so does their susceptibility to misuse, raising significant security concerns. Numerous jailbreak attacks have been proposed to assess the security…

The adversarial model presented by trusted execution environments (TEEs) has prompted researchers to investigate unusual attack vectors. One particularly powerful class of controlled-channel attacks abuses page-table modifications to…

Speculative execution techniques have been a cornerstone of modern processors to improve instruction-level parallelism. However, recent studies showed that this kind of techniques could be exploited by attackers to leak secret data via…

We will discuss the RowHammer problem in DRAM, which is a prime (and likely the first) example of how a circuit-level failure mechanism in Dynamic Random Access Memory (DRAM) can cause a practical and widespread system security…

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…

Context switching is utilized by operating systems to change the execution context between application programs. It involves saving and restoring the states of multiple registers and performing a pipeline flush to remove any pre-fetched…

Memory spatial errors, i.e., buffer overflow vulnerabilities, have been a well-known issue in computer security for a long time and remain one of the root causes of exploitable vulnerabilities. Most of the existing mitigation tools adopt a…

Deploying pretrained visual models in real-world environments often suffers from significant performance degradation due to the diversity of testing scenarios. Continuous adaptation of learning models on edge devices via unlabeled data…

A learned database system uses machine learning (ML) internally to improve performance. We can expect such systems to be vulnerable to some adversarial-ML attacks. Often, the learned component is shared between mutually-distrusting users or…

The IoT is vulnerable to network attacks, and Intrusion Detection Systems (IDS) can provide high attack detection accuracy and are easily installed in IoT Servers. However, IDS are seldom evaluated in operational conditions which are…

Since the initial discovery of Meltdown and Spectre in 2017, different variants of these attacks have been discovered. One often overlooked variant is Meltdown 3a, also known as Meltdown-CPL-REG. Even though Meltdown-CPL-REG was initially…

We present a novel mechanism to construct a covert channel based on page faults. A page fault is an event that occurs when a process or a thread tries to access a page of memory that is not currently mapped to its address space. The kernel…

LLM-based chatbot agents increasingly process user requests by combining natural-language reasoning with external tools such as web browsing. These capabilities improve usability, but they also create attack surfaces when untrusted external…

As machine learning models become increasingly deployed across the edge of internet of things environments, a partitioned deep learning paradigm in which models are split across multiple computational nodes introduces a new dimension of…

Covert channel attacks represent a significant threat to system security, leveraging shared resources to clandestinely transmit information from highly secure systems, thereby violating the system's security policies. These attacks exploit…

Due to their proven efficiency, machine-learning systems are deployed in a wide range of complex real-life problems. More specifically, Spiking Neural Networks (SNNs) emerged as a promising solution to the accuracy, resource-utilization,…

Implementations of cryptographic libraries have been scrutinized for secret-dependent execution behavior exploitable by microarchitectural side-channel attacks. To prevent unintended leakages, most libraries moved to constant-time…

Continual learning algorithms are typically exposed to untrusted sources that contain training data inserted by adversaries and bad actors. An adversary can insert a small number of poisoned samples, such as mislabeled samples from…

We present a preliminary study of buffer overflow vulnerabilities in CUDA software running on GPUs. We show how an attacker can overrun a buffer to corrupt sensitive data or steer the execution flow by overwriting function pointers, e.g.,…

Federated learning is particularly susceptible to model poisoning and backdoor attacks because individual users have direct control over the training data and model updates. At the same time, the attack power of an individual user is…