相关论文: Beyond Over-Protection: A Targeted Approach to Spe…

Large Language Models (LLMs) remain vulnerable to adaptive jailbreaks that easily bypass empirical defenses like GCG. We propose a framework for certifiable robustness that shifts safety guarantees from single-pass inference to the…

Despite extensive efforts to align Large Language Models (LLMs) with human values and safety rules, jailbreak attacks that exploit certain vulnerabilities continuously emerge, highlighting the need to strengthen existing LLMs with…

SPEculative Execution side Channel Hardware (SPEECH) Vulnerabilities have enabled the notorious Meltdown, Spectre, and L1 terminal fault (L1TF) attacks. While a number of studies have reported different variants of SPEECH vulnerabilities,…

Software vulnerabilities are major risks to software systems. Recently, researchers have proposed many deep learning approaches to detect software vulnerabilities. However, their accuracy is limited in practice. One of the main causes is…

Modern microarchitectures incorporate optimization techniques such as speculative loads and store forwarding to improve the memory bottleneck. The processor executes the load speculatively before the stores, and forwards the data of a…

Semi-Supervised Learning (SSL) seeks to leverage large amounts of non-annotated data along with the smallest amount possible of annotated data in order to achieve the same level of performance as if all data were annotated. A fruitful…

A machine learning-based detection framework is proposed to detect a class of cyber-attacks that redistribute loads by modifying measurements. The detection framework consists of a multi-output support vector regression (SVR) load predictor…

Despite the extent of recent advances in Machine Learning (ML) and Neural Networks, providing formal guarantees on the behavior of these systems is still an open problem, and a crucial requirement for their adoption in regulated or…

Recent work has shown that out-of-order and speculative execution mechanisms used to increase performance in the majority of processors expose the processors to critical attacks. These attacks, called Meltdown and Spectre, exploit the side…

Can we trust Large Language Models (LLMs) to accurately predict scam? This paper investigates the vulnerabilities of LLMs when facing adversarial scam messages for the task of scam detection. We addressed this issue by creating a…

Speculative decoding has become a widely adopted technique for accelerating large language model (LLM) inference by drafting multiple candidate tokens and verifying them with a target model in parallel. Its efficiency, however, critically…

The importance of information security dramatically increased and will further grow due to the shape and nature of the modern computing industry. Software is published at a continuously increasing pace. The Internet of Things and security…

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…

CPU cache is a limited but crucial storage component in modern processors, whereas the cache timing side-channel may inadvertently leak information through the physically measurable timing variance. Speculative execution, an essential…

Speculative Decoding (SD) is a recently proposed technique for faster inference using Large Language Models (LLMs). SD operates by using a smaller draft LLM for autoregressively generating a sequence of tokens and a larger target LLM for…

Transient execution attacks utilize micro-architectural covert channels to leak secrets that should not have been accessible during logical program execution. Commonly used micro-architectural covert channels are those that leave lasting…

As software becomes increasingly complex and prone to vulnerabilities, automated vulnerability detection is critically important, yet challenging. Given the significant successes of large language models (LLMs) in various tasks, there is…

Software testing and verification are critical for ensuring the reliability and security of modern software systems. Traditionally, formal verification techniques, such as model checking and theorem proving, have provided rigorous…

Deployed large language models (LLMs) often rely on speculative decoding, a technique that generates and verifies multiple candidate tokens in parallel, to improve throughput and latency. In this work, we reveal a new side-channel whereby…

Most discussions about Large Language Model (LLM) safety have focused on single-agent settings but multi-agent LLM systems now create novel adversarial risks because their behavior depends on communication between agents and decentralized…