arXiv subjects

Ryan Tsang

Publications and source records attributed to Ryan Tsang.

4 recordsLinked to original sources

arXiv2025

AILuminate: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons

The rapid advancement and deployment of AI systems have created an urgent need for standard safety-evaluation frameworks. This paper introduces AILuminate v1.0, the first comprehensive industry-standard benchmark for assessing AI-product risk and reliability. Its development employed an open process that included participants from multiple fields. The benchmark evaluates an AI system's resistance to prompts designed to elicit dangerous, illegal, or undesirable behavior in 12 hazard categories, including violent crimes, nonviolent crimes, sex-related crimes, child sexual exploitation, indiscriminate weapons, suicide and self-harm, intellectual property, privacy, defamation, hate, sexual content, and specialized advice (election, financial, health, legal). Our method incorporates a complete assessment standard, extensive prompt datasets, a novel evaluation framework, a grading and reporting system, and the technical as well as organizational infrastructure for long-term support and evolution. In particular, the benchmark employs an understandable five-tier grading scale (Poor to Excellent) and incorporates an innovative entropy-based system-response evaluation. In addition to unveiling the benchmark, this report also identifies limitations of our method and of building safety benchmarks generally, including evaluator uncertainty and the constraints of single-turn interactions. This work represents a crucial step toward establishing global standards for AI risk and reliability evaluation while acknowledging the need for continued development in areas such as multiturn interactions, multimodal understanding, coverage of additional languages, and emerging hazard categories. Our findings provide valuable insights for model developers, system integrators, and policymakers working to promote safer AI deployment.

cs.CY↗

arXiv2024

Fuzzing BusyBox: Leveraging LLM and Crash Reuse for Embedded Bug Unearthing

BusyBox, an open-source software bundling over 300 essential Linux commands into a single executable, is ubiquitous in Linux-based embedded devices. Vulnerabilities in BusyBox can have far-reaching consequences, affecting a wide array of devices. This research, driven by the extensive use of BusyBox, delved into its analysis. The study revealed the prevalence of older BusyBox versions in real-world embedded products, prompting us to conduct fuzz testing on BusyBox. Fuzzing, a pivotal software testing method, aims to induce crashes that are subsequently scrutinized to uncover vulnerabilities. Within this study, we introduce two techniques to fortify software testing. The first technique enhances fuzzing by leveraging Large Language Models (LLM) to generate target-specific initial seeds. Our study showed a substantial increase in crashes when using LLM-generated initial seeds, highlighting the potential of LLM to efficiently tackle the typically labor-intensive task of generating target-specific initial seeds. The second technique involves repurposing previously acquired crash data from similar fuzzed targets before initiating fuzzing on a new target. This approach streamlines the time-consuming fuzz testing process by providing crash data directly to the new target before commencing fuzzing. We successfully identified crashes in the latest BusyBox target without conducting traditional fuzzing, emphasizing the effectiveness of LLM and crash reuse techniques in enhancing software testing and improving vulnerability detection in embedded systems. Additionally, manual triaging was performed to identify the nature of crashes in the latest BusyBox.

cs.SE↗

arXiv2023

Large Language Models for Code Analysis: Do LLMs Really Do Their Job?

Large language models (LLMs) have demonstrated significant potential in the realm of natural language understanding and programming code processing tasks. Their capacity to comprehend and generate human-like code has spurred research into harnessing LLMs for code analysis purposes. However, the existing body of literature falls short in delivering a systematic evaluation and assessment of LLMs' effectiveness in code analysis, particularly in the context of obfuscated code. This paper seeks to bridge this gap by offering a comprehensive evaluation of LLMs' capabilities in performing code analysis tasks. Additionally, it presents real-world case studies that employ LLMs for code analysis. Our findings indicate that LLMs can indeed serve as valuable tools for automating code analysis, albeit with certain limitations. Through meticulous exploration, this research contributes to a deeper understanding of the potential and constraints associated with utilizing LLMs in code analysis, paving the way for enhanced applications in this critical domain.

cs.SE↗

arXiv2018

Room temperature "Optical Nanodiamond Hyperpolarizer": physics, design and operation

Dynamic Nuclear Polarization (DNP) is a powerful suite of techniques that deliver multifold signal enhancements in NMR and MRI. The generated athermal spin states can also be exploited for quantum sensing and as probes for many-body physics. Typical DNP methods require use of cryogens, large magnetic fields, and high power microwaves, which are expensive and unwieldy. Nanodiamond particles, rich in Nitrogen-Vacancy (NV) centers, have attracted attention as alternative DNP agents because they can potentially be optically hyperpolarized at room temperature. Indeed the realization of a miniature "optical nanodiamond hyperpolarizer", where 13C nuclei are optically hyperpolarized has been a longstanding goal but has been technically challenging to achieve. Here, unravelling new physics underlying an optical DNP mechanism first introduced in [Ajoy et al., Sci. Adv. 4, eaar5492 (2018)], we report the realization of such a device in an ultracompact footprint and working fully at room temperature. Instrumental requirements are very modest: low polarizing fields, extremely low optical and microwave irradiation powers, and convenient frequency ranges that enable device miniaturization. We obtain best reported optical 13C hyperpolarization in diamond particles exceeding 720 times of the thermal 7T value (0.86% bulk polarization), corresponding to a ten-million-fold gain in NMR averaging time. In addition the hyperpolarization signal can be background-suppressed by over two-orders of magnitude and retained for multiple-minute long periods. Besides compelling applications in quantum sensing, and bright-contrast MRI imaging, this work paves the way for low-cost DNP platforms that relay the 13C polarization to liquids in contact with the high surface-area particles. This will ultimately allow development of miniature "quantum-assisted" NMR spectrometers for chemical analysis.

quant-ph↗