Related papers: Layered Binary Templating: Efficient Detection of …

The fast advancements in Large Language Models (LLMs) are driving an increasing number of applications. Together with the growing number of users, we also see an increasing number of attackers who try to outsmart these systems. They want…

Browser agents are increasingly deployed in long-horizon tasks, which require executing extended action chains to accomplish user goals. However, this prolonged execution process provides attackers with more opportunities to inject…

The code generation modules inside modern compilers such as GCC and LLVM, which use a limited number of CPU registers to store a large number of program variables, may introduce side-channel leaks even in software equipped with…

The implications of backdoor attacks on English-centric large language models (LLMs) have been widely examined - such attacks can be achieved by embedding malicious behaviors during training and activated under specific conditions that…

The rapid advancement of Large Language Models (LLMs) has brought about remarkable generative capabilities but also raised concerns about their potential misuse. While strategies like supervised fine-tuning and reinforcement learning from…

ARM Memory Tagging Extension (MTE) is a new hardware feature introduced in ARMv8.5-A architecture, aiming to detect memory corruption vulnerabilities. The low overhead of MTE makes it an attractive solution to mitigate memory corruption…

Large Language Models (LLMs) have recently demonstrated remarkable performance in generating high-quality tabular synthetic data. In practice, two primary approaches have emerged for adapting LLMs to tabular data generation: (i) fine-tuning…

This paper demonstrates a new side-channel that enables an adversary to extract sensitive information about inference inputs in large language models (LLMs) based on the number of output tokens in the LLM response. We construct attacks…

CPUs provide isolation mechanisms like virtualization and privilege levels to protect software. Yet these focus on architectural isolation while typically overlooking microarchitectural side channels, exemplified by Meltdown and Foreshadow.…

Large Language Models (LLMs) have transformed human-machine interaction since ChatGPT's 2022 debut, with Retrieval-Augmented Generation (RAG) emerging as a key framework that enhances LLM outputs by integrating external knowledge. However,…

Open-weight language models are increasingly used in production settings, raising new security challenges. One prominent threat is backdoor attacks, in which adversaries embed hidden behaviors that activate under specific conditions.…

Existing tools to detect side-channel attacks on Intel SGX are grounded on the observation that attacks affect the performance of the victim application. As such, all detection tools monitor the potential victim and raise an alarm if the…

Side-channel information leakage is a known limitation of SGX. Researchers have demonstrated that secret-dependent information can be extracted from enclave execution through page-fault access patterns. Consequently, various recent research…

Meltdown and Spectre exploit microarchitectural changes the CPU makes during transient out-of-order execution. Using side-channel techniques, these attacks enable leaking arbitrary data from memory. As state-of-the-art software mitigations…

Searchable symmetric encryption enables private queries over an encrypted database, but it also yields information leakages. Adversaries can exploit these leakages to launch injection attacks (Zhang et al., USENIX'16) to recover the…

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…

The success of Large Language Models (LLMs) relies heavily on the huge amount of pre-training data learned in the pre-training phase. The opacity of the pre-training process and the training data causes the results of many benchmark tests…

Timing side channels have been used to extract cryptographic keys and sensitive documents, even from trusted enclaves. In this paper, we focus on cache side channels created by access to shared code or data in the memory hierarchy. This…

As Android malware is growing and evolving, deep learning has been introduced into malware detection, resulting in great effectiveness. Recent work is considering hybrid models and multi-view learning. However, they use only simple…

Modern multi-core processors share cache resources for maximum cache utilization and performance gains. However, this leaves the cache vulnerable to side-channel attacks, where timing differences in shared cache behavior are exploited to…