Related papers: SPOILER: Speculative Load Hazards Boost Rowhammer …

Local fine-tuning datasets routinely contain sensitive secrets such as API keys, personal identifiers, and financial records. Although ''local offline fine-tuning'' is often viewed as a privacy boundary, we reveal that compromised model…

We provide a queueing-theoretic framework for job replication schemes based on the principle "\emph{replicate a job as soon as the system detects it as a \emph{straggler}}". This is called job \emph{speculation}. Recent works have analyzed…

The power consumption of a microprocessor is a huge channel for information leakage. While the most popular exploitation of this channel is to recover cryptographic keys from embedded devices, other applications such as mobile app…

An extensive line of work on modern computing architectures has shown that the execution time of instructions can (i) depend on the operand of the instruction or (ii) be influenced by system optimizations, e.g., branch prediction and…

Mixture-of-Experts models have become a dominant architecture for scaling Large Language Models by activating only a sparse subset of experts per token. However, latency-critical MoE inference faces a fundamental tension: while expert…

The immense memory requirements of state-of-the-art Mixture-of-Experts (MoE) models present a significant challenge for inference, often exceeding the capacity of a single accelerator. While offloading experts to host memory is a common…

Cloud providers are concerned that Rowhammer poses a potentially critical threat to their servers, yet today they lack a systematic way to test whether the DRAM used in their servers is vulnerable to Rowhammer attacks. This paper presents…

This paper introduces Okapi, a new hardware/software cross-layer architecture designed to mitigate Transient Execution Side Channel attacks, including Spectre variants, in modern computing systems. Okapi provides a hardware basis for secure…

Decision-based attacks construct adversarial examples against a machine learning (ML) model by making only hard-label queries. These attacks have mainly been applied directly to standalone neural networks. However, in practice, ML models…

Large language models (LLMs) possess extensive knowledge and question-answering capabilities, having been widely deployed in privacy-sensitive domains like finance and medical consultation. During LLM inferences, cache-sharing methods are…

Spear Phishing is a harmful cyber-attack facing business and individuals worldwide. Considerable research has been conducted recently into the use of Machine Learning (ML) techniques to detect spear-phishing emails. ML-based solutions may…

Recent advancements in speculative decoding have demonstrated considerable speedup across a wide array of large language model (LLM) tasks. Speculative decoding inherently relies on sacrificing extra memory allocations to generate several…

New hardware primitives such as Intel SGX secure a user-level process in presence of an untrusted or compromised OS. Such "enclaved execution" systems are vulnerable to several side-channels, one of which is the page fault channel. In this…

Mixture-of-Experts (MoE) models have gained popularity as a means of scaling the capacity of large language models (LLMs) while maintaining sparse activations and reduced per-token compute. However, in memory-constrained inference settings,…

In recent years, Rowhammer has attracted significant attention from academia and industry alike. This technique, first published in 2014, flips bits in memory by repeatedly accessing neighbouring memory locations. Since its discovery,…

Large amounts of incremental learning algorithms have been proposed to alleviate the catastrophic forgetting issue arises while dealing with sequential data on a time series. However, the adversarial robustness of incremental learners has…

Large language models (LLMs) suffer from low efficiency as the mismatch between the requirement of auto-regressive decoding and the design of most contemporary GPUs. Specifically, billions to trillions of parameters must be loaded to the…

Caches are widely used to improve performance in modern processors. By carefully evicting cache lines and identifying cache hit/miss time, contention-based cache timing channel attacks can be orchestrated to leak information from the victim…

The importance of preventing microarchitectural timing side channels in security-critical applications has surged in recent years. Constant-time programming has emerged as a best-practice technique for preventing the leakage of secret…

Timing-based side and covert channels in processor caches continue to be a threat to modern computers. This work shows for the first time a systematic, large-scale analysis of Arm devices and the detailed results of attacks the processors…