Search Results for author:
Found 14 papers, 1 papers with code
SandboxEval: Towards Securing Test Environment for Untrusted Code
While large language models (LLMs) are powerful assistants in programming tasks, they may also produce malicious code.
Malicious and Unintentional Disclosure Risks in Large Language Models for Code Generation
This paper explores the risk that a large language model (LLM) trained for code generation on data mined from software repositories will generate content that discloses sensitive information included in its training data.
In-House Evaluation Is Not Enough: Towards Robust Third-Party Flaw Disclosure for General-Purpose AI
The widespread deployment of general-purpose AI (GPAI) systems introduces significant new risks.
AILuminate: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons
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.
To Err is AI : A Case Study Informing LLM Flaw Reporting Practices
In August of 2024, 495 hackers generated evaluations in an open-ended bug bounty targeting the Open Language Model (OLMo) from The Allen Institute for AI.
Lessons for Editors of AI Incidents from the AI Incident Database
As artificial intelligence (AI) systems become increasingly deployed across the world, they are also increasingly implicated in AI incidents - harm events to individuals and society.
Introducing v0.5 of the AI Safety Benchmark from MLCommons
We created a new taxonomy of 13 hazard categories, of which 7 have tests in the v0. 5 benchmark.
Data-Centric Governance
Modern AI systems are data-centric: they act on data, produce data, and are built through data engineering.
Indexing AI Risks with Incidents, Issues, and Variants
Two years after publicly launching the AI Incident Database (AIID) as a collection of harms or near harms produced by AI in the world, a backlog of "issues" that do not meet its incident ingestion criteria have accumulated in its review queue.
Participation Interfaces for Human-Centered AI
Emerging artificial intelligence (AI) applications often balance the preferences and impacts among diverse and contentious stakeholder groups.
A taxonomic system for failure cause analysis of open source AI incidents
While certain industrial sectors (e. g., aviation) have a long history of mandatory incident reporting complete with analytical findings, the practice of artificial intelligence (AI) safety benefits from no such mandate and thus analyses must be performed on publicly known ``open source'' AI incidents.
The Deepfake Detection Dilemma: A Multistakeholder Exploration of Adversarial Dynamics in Synthetic Media
Synthetic media detection technologies label media as either synthetic or non-synthetic and are increasingly used by journalists, web platforms, and the general public to identify misinformation and other forms of problematic content.
Factoring Exogenous State for Model-Free Monte Carlo
One visualization approach is to invoke the simulator to generate on-policy trajectories and then visualize those trajectories.
Fast Optimization of Wildfire Suppression Policies with SMAC
SMAC is applied to find the optimal policy in this class for the reward functions of each of the stakeholder constituencies.
