Related papers: Red-Teaming Claude Opus and ChatGPT-based Security…

Large Language Models (LLMs) have demonstrated strong capabilities as autonomous agents through tool use, planning, and decision-making abilities, leading to their widespread adoption across diverse tasks. As task complexity grows,…

Scientific workflow systems are increasingly popular for expressing and executing complex data analysis pipelines over large datasets, as they offer reproducibility, dependability, and scalability of analyses by automatic parallelization on…

This research article critically examines the potential risks and implications arising from the malicious utilization of large language models(LLM), focusing specifically on ChatGPT and Google's Bard. Although these large language models…

Security and privacy concerns in computer systems have grown in importance with the ubiquity of connected devices. TEEs provide security guarantees based on cryptographic constructs built in hardware. Intel software guard extensions (SGX),…

Large Language Models (LLMs) have been suggested for use in automated vulnerability repair, but benchmarks showing they can consistently identify security-related bugs are lacking. We thus develop SecLLMHolmes, a fully automated evaluation…

Agentic language-model systems increasingly rely on mutable execution contexts, including files, memory, tools, skills, and auxiliary artifacts, creating security risks beyond explicit user prompts. This paper presents DeepTrap, an…

Large language models (LLMs) are increasingly embedded in open-source software (OSS) ecosystems, creating complex interactions among natural language prompts, probabilistic model outputs, and execution-capable components. However, it…

Trusted Execution Environments (TEEs) have been proposed as a solution to protect code confidentiality in scenarios where computation is outsourced to an untrusted operator. We study the resilience of such solutions to side-channel attacks…

With the integration of large language models (LLMs), embodied agents have strong capabilities to understand and plan complicated natural language instructions. However, a foreseeable issue is that those embodied agents can also flawlessly…

We consider the problem of red teaming LLMs on elementary calculations and algebraic tasks to evaluate how various prompting techniques affect the quality of outputs. We present a framework to procedurally generate numerical questions and…

Understanding the capabilities of text-to-image (T2I) models in harmful content generation is essential to safety and compliance. However, human red-teaming is costly and inconsistent, driving the need for automatic tools that simulate…

Process attestation systems verify that a continuous physical process, such as human authorship, actually occurred, rather than merely checking system state. These systems face a fundamental dependability challenge: the evidence collection…

Large language models (LLMs) are increasingly used in business dialogue systems but they pose security and ethical risks. Multi-turn conversations, where context influences the model's behavior, can be exploited to produce undesired…

The rapid progress of Large Language Models (LLMs) has opened up new opportunities across various domains and applications; yet it also presents challenges related to potential misuse. To mitigate such risks, red teaming has been employed…

We introduce WildTeaming, an automatic LLM safety red-teaming framework that mines in-the-wild user-chatbot interactions to discover 5.7K unique clusters of novel jailbreak tactics, and then composes multiple tactics for systematic…

As large language models (LLMs) are increasingly used for code generation, concerns over the security risks have grown substantially. Early research has primarily focused on red teaming, which aims to uncover and evaluate vulnerabilities…

Protection of data-in-use is a key priority, for which Trusted Execution Environment (TEE) technology has unarguably emerged as a, possibly the most, promising solution. Multiple server-side TEE offerings have been released over the years,…

Vision-Language-Action (VLA) models have achieved remarkable success in robotic manipulation. However, their robustness to linguistic nuances remains a critical, under-explored safety concern, posing a significant safety risk to real-world…

Large Language Models (LLMs) presents significant priority in text understanding and generation. However, LLMs suffer from the risk of generating harmful contents especially while being employed to applications. There are several black-box…

Embodied agents powered by large language models (LLMs) inherit advanced planning capabilities; however, their direct interaction with the physical world exposes them to safety vulnerabilities. In this work, we identify four key reasoning…