Related papers: SPEECHMINER: A Framework for Investigating and Mea…

In recent years, multimodal large language models (MLLMs) have significantly advanced, integrating more modalities into diverse applications. However, the lack of explainability remains a major barrier to their use in scenarios requiring…

This study systematically analyzes the vulnerability of 36 large language models (LLMs) to various prompt injection attacks, a technique that leverages carefully crafted prompts to elicit malicious LLM behavior. Across 144 prompt injection…

Since the advent of SPECTRE, a number of countermeasures have been proposed and deployed. Rigorously reasoning about their effectiveness, however, requires a well-defined notion of security against speculative execution attacks, which has…

Since the discovery of Spectre, a large number of hardware mechanisms for secure speculation has been proposed. Intuitively, more defensive mechanisms are less efficient but can securely execute a larger class of programs, while more…

While Large Language Models (LLMs) have made significant strides in replicating human-like abilities, there are concerns about a reduction in the linguistic diversity of their outputs. This results in the homogenization of viewpoints and…

In this study, we evaluated the capability of Large Language Models (LLMs), particularly OpenAI's GPT-4, in detecting software vulnerabilities, comparing their performance against traditional static code analyzers like Snyk and Fortify. Our…

We present AutoBencher, a declarative framework for automatic benchmark construction, and use it to scalably discover novel insights and vulnerabilities of existing language models. Concretely, given a few desiderata of benchmarks (e.g.,…

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…

Computer systems often provide hardware support for isolation mechanisms like privilege levels, virtual memory, or enclaved execution. Over the past years, several successful software-based side-channel attacks have been developed that…

We present CureSpec, the first model-checking based framework for automatic repair of programs with respect to information leaks in the presence of side-channels and speculative execution. CureSpec is based on formal models of attacker…

The recent Spectre attacks exploit speculative execution, a pervasively used feature of modern microprocessors, to allow the exfiltration of sensitive data across protection boundaries. In this paper, we introduce a new Spectre-class attack…

Recently, there has been a growing interest in automatic software vulnerability detection. Pre-trained model-based approaches have demonstrated superior performance than other Deep Learning (DL)-based approaches in detecting…

Exploitation is not a binary event. It is a ladder of acquiring progressive capabilities, from executing a single buggy line of code to taking full control of the target. However, existing LLM security benchmarks treat a crash as…

Large language models (LLMs) are increasingly used in software development, but their level of software security expertise remains unclear. This work systematically evaluates the security comprehension of five leading LLMs: GPT-4o-Mini,…

The problem of synthetic speech detection has enjoyed considerable attention, with recent methods achieving low error rates across several established benchmarks. However, to what extent can low error rates on academic benchmarks translate…

Large language model (LLM) benchmarks inform LLM use decisions (e.g., "is this LLM safe to deploy for my use case and context?"). However, benchmarks may be rendered unreliable by various failure modes that impact benchmark bias, variance,…

Large language models (LLMs) have achieved strong performance on natural language to SQL (NL2SQL) benchmarks, yet their reported accuracy may be inflated by contamination from benchmark queries or structurally similar patterns seen during…

Large Language Models (LLMs) remain vulnerable to multi-turn jailbreak attacks. We introduce HarmNet, a modular framework comprising ThoughtNet, a hierarchical semantic network; a feedback-driven Simulator for iterative query refinement;…

The complexity of modern processor architectures has given rise to sophisticated interactions among their components. Such interactions may result in potential attack vectors in terms of side channels, possibly available to user-land…

Transient execution attacks have been one of the widely explored microarchitectural side channels since the discovery of Spectre and Meltdown. However, much of the research has been driven by manual discovery of new transient paths through…