Related papers: SpecuSym: Speculative Symbolic Execution for Cache…

Microarchitectural side channels expose unprotected software to information leakage attacks where a software adversary is able to track runtime behavior of a benign process and steal secrets such as cryptographic keys. As suggested by…

Distributed inference serves as a promising approach to enabling the inference of large language models (LLMs) at the network edge. It distributes the inference process to multiple devices to ensure that the LLMs can fit into the device…

Side-channel attacks on shared hardware resources increasingly threaten confidentiality, especially with the rise of Large Language Models (LLMs). In this work, we introduce Spill The Beans, a novel application of cache side-channels to…

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.…

Caches are used to reduce the speed differential between the CPU and memory to improve the performance of modern processors. However, attackers can use contention-based cache timing attacks to steal sensitive information from victim…

Confidential computing on GPUs, like NVIDIA H100, mitigates the security risks of outsourced Large Language Models (LLMs) by implementing strong isolation and data encryption. Nonetheless, this encryption incurs a significant performance…

An accurate prediction of scheduling and execution of instruction streams is a necessary prerequisite for predicting the in-core performance behavior of throughput-bound loop kernels on out-of-order processor architectures. Such predictions…

We present Cacheback Decoding, a training-free and model-agnostic speculative decoding method that exploits the locality in language to accelerate Large Language Model (LLM) inference. Cacheback leverages only Least Recently Used (LRU)…

Large reasoning language models such as OpenAI-o1 and Deepseek-R1 have recently attracted widespread attention due to their impressive task-solving abilities. However, the enormous model size and the generation of lengthy thought chains…

In several software development scenarios, it is desirable to detect runtime errors and exceptions in code snippets without actual execution. A typical example is to detect runtime exceptions in online code snippets before integrating them…

Stream processing systems are important in modern applications in which data arrive continuously and need to be processed in real time. Because of their resource and scalability requirements, many of these systems run on the cloud, which is…

The wide deployment of Large Language Models (LLMs) has given rise to strong demands for optimizing their inference performance. Today's techniques serving this purpose primarily focus on reducing latency and improving throughput through…

Hardware (HW) security issues have been emerging at an alarming rate in recent years. Transient execution attacks, in particular, pose a genuine threat to the security of modern computing systems. Despite recent advances, understanding the…

Test-time scaling has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs) by allocating additional computational resources during inference. However, this paradigm is inherently…

Firmware serves as the critical interface between hardware and software in computing systems, making any bugs or vulnerabilities particularly dangerous as they can cause catastrophic system failures. While fuzzing is a promising approach…

Cache-based side channels enable a dedicated attacker to reveal program secrets by measuring the cache access patterns. Practical attacks have been shown against real-world crypto algorithm implementations such as RSA, AES, and ElGamal. By…

Speculative decoding can significantly accelerate LLM inference, especially given that its cloud-edge collaborative deployment offers cloud workload offloading, offline robustness, and privacy enhancement. However, existing collaborative…

Fault-tolerance is critically important in highly-distributed modern cloud applications. Solutions such as Temporal, Azure Durable Functions, and Beldi hide fault-tolerance complexity from developers by persisting execution state and…

Ethereum smart contracts are an innovation built on top of the blockchain technology, which provides a platform for automatically executing contracts in an anonymous, distributed, and trusted way. The problem is magnified by the fact that…

The Mixture-of-Experts (MoE) architecture has emerged as a promising approach to mitigate the rising computational costs of large language models (LLMs) by selectively activating parameters. However, its high memory requirements and…