English
Related papers

Related papers: Detecting speculative data flow vulnerabilities us…

200 papers

Speculative decoding accelerates LLM inference by utilizing otherwise idle computational resources during memory-to-chip data transfer. Current speculative decoding methods typically assume a considerable amount of available computing…

Computation and Language · Computer Science 2025-11-26 Luohe Shi , Zuchao Li , Lefei Zhang , Baoyuan Qi , Guoming Liu , Hai Zhao

Autoregressive decoding is bottlenecked by its sequential nature. Speculative decoding has become a standard way to accelerate inference by using a fast draft model to predict upcoming tokens from a slower target model, and then verifying…

Machine Learning · Computer Science 2026-05-06 Tanishq Kumar , Tri Dao , Avner May

In this work, we focus on analyzing vulnerability of nonlinear dynamical control systems to stealthy false data injection attacks on sensors. We start by defining the stealthiness notion in the most general form where an attack is…

Systems and Control · Electrical Eng. & Systems 2023-10-10 Amir Khazraei , Miroslav Pajic

Many security and software testing applications require checking whether certain properties of a program hold for any possible usage scenario. For instance, a tool for identifying software vulnerabilities may need to rule out the existence…

Software Engineering · Computer Science 2018-05-03 Roberto Baldoni , Emilio Coppa , Daniele Cono D'Elia , Camil Demetrescu , Irene Finocchi

Behavioral software contracts are a widely used mechanism for governing the flow of values between components. However, run-time monitoring and enforcement of contracts imposes significant overhead and delays discovery of faulty components…

Programming Languages · Computer Science 2014-06-17 Phuc C. Nguyen , Sam Tobin-Hochstadt , David Van Horn

Timing side-channel attacks exploit variations in program execution time to recover sensitive information. Cryptographic implementations are especially vulnerable to these attacks, since even small timing differences in operations such as…

Cryptography and Security · Computer Science 2026-04-21 Nges Brian Njungle , Edwin P. Kayang , Mishel J. Paul , Michel A. Kinsy

Background: Debugging is a key task during the software development cycle. Spectrum-based Fault Localization (SFL) is a promising technique to improve and automate debugging. SFL techniques use control-flow spectra to pinpoint the most…

We propose Speculative Decoding (SpecDec), for the first time ever, to formally study exploiting the idea of speculative execution to accelerate autoregressive (AR) decoding. Speculative Decoding has two innovations: Spec-Drafter -- an…

Computation and Language · Computer Science 2023-10-31 Heming Xia , Tao Ge , Peiyi Wang , Si-Qing Chen , Furu Wei , Zhifang Sui

The wide availability of data coupled with the computational advances in artificial intelligence and machine learning promise to enable many future technologies such as autonomous driving. While there has been a variety of successful…

Systems and Control · Electrical Eng. & Systems 2022-10-11 Lars Lindemann , Lejun Jiang , Nikolai Matni , George J. Pappas

Large Language Models (LLMs) have become widely used for Software Engineering (SE) tasks, spanning from function-level code generation to complex repository-level workflows. However, the high latency of autoregressive inference remains a…

Software Engineering · Computer Science 2026-05-05 Yijia Li , Junkai Chen , Xing Hu , Xin Xia

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…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-26 Yunhe Han , Yunqi Gao , Bing Hu , Mahdi Boloursaz Mashhadi , Yitong Duan , Pei Xiao , Yanfeng Zhang

Speculative decoding (SD) accelerates large language model (LLM) inference by using a smaller draft model to propose multiple tokens that are verified by a larger target model in parallel. While prior work demonstrates substantial speedups…

Machine Learning · Computer Science 2026-05-15 Linghao Kong , Megan Flynn , Michael Peng , Nir Shavit , Mark Kurtz , Alexandre Marques

Phishing continues to be one of the most prevalent attack vectors, making accurate classification of phishing URLs essential. Recently, large language models (LLMs) have demonstrated promising results in phishing URL detection. However,…

Cryptography and Security · Computer Science 2026-01-29 Holly Trikilis , Pasindu Marasinghe , Fariza Rashid , Suranga Seneviratne

Speculative decoding is an effective method for lossless acceleration of large language models during inference. It uses a fast model to draft a block of tokens which are then verified in parallel by the target model, and provides a…

Machine Learning · Computer Science 2025-04-14 Ziteng Sun , Uri Mendlovic , Yaniv Leviathan , Asaf Aharoni , Jae Hun Ro , Ahmad Beirami , Ananda Theertha Suresh

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…

Machine Learning · Computer Science 2025-06-04 Selin Yildirim , Deming Chen

Early exiting has recently emerged as a promising technique for accelerating large language models (LLMs) by effectively reducing the hardware computation and memory access. In this paper, we present SpecEE, a fast LLM inference engine with…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-04-15 Jiaming Xu , Jiayi Pan , Yongkang Zhou , Siming Chen , Jinhao Li , Yaoxiu Lian , Junyi Wu , Guohao Dai

Nowadays, a computing cluster in a typical data center can easily consist of hundreds of thousands of commodity servers, making component/ machine failures the norm rather than exception. A parallel processing job can be delayed…

Distributed, Parallel, and Cluster Computing · Computer Science 2015-01-06 Huanle Xu , Wing Cheong Lau

Speculative decoding accelerates LLM inference by using a smaller draft model to speculate tokens that a larger target model verifies. Verification is often the bottleneck (e.g. verification is $4\times$ slower than token generation when a…

Computation and Language · Computer Science 2026-05-27 Avinash Kumar , Sujay Sanghavi , Poulami Das

Speculative decoding accelerates Large Language Model (LLM) inference by employing a small speculative model (SSM) to generate multiple candidate tokens and verify them using the LLM in parallel. This technique has been widely integrated…

Computation and Language · Computer Science 2025-05-26 Ruixiao Li , Fahao Chen , Peng Li

Deep learning (DL) has recently emerged as an efficient approach for array processing tasks such as signal detection and direction of arrival. However, DL models lack statistical guarantees and, moreover, are highly susceptible to…

Signal Processing · Electrical Eng. & Systems 2026-05-08 Nian-Cin Wang , Rajeev Sahay