cs.AIOct 29, 2026

Violet Teaming in Practice: Lessons from a Pilot Expert Workshop on Governing Complex AI Systems

Authors: Steph Batalis, Kait Connors, Ben C. Snyder, Vikram Venkatram, Josh Wentzel

Organizations: Center for Security and Emerging Technology, Georgetown University, Washington D.C., United States · Independent Researcher, Washington D.C., United States · Biosecurity and Pandemic Policy Center, Bush School of Government & Public Service, Texas A&M University, Washington D.C., United States

Abstract

Violet teaming has been proposed as a method to integrate technical, policy, and societal considerations into the evaluation of emerging technologies. Here, we document a pilot expert workshop used to explore violet teaming as a governance methodology for biodefense-relevant AI capabilities and describe observations from the exercise. The workshop used a hypothetical technology scenario across three sequential stages - capability development, misuse potential, and implementation - while incorporating technical, security, operational, and policy perspectives. The sequential format provided an integrated way to examine potential benefits, misuse risks, and real-world implementation challenges, rather than considering these issues in isolation. The exercise surfaced non-obvious misuse pathways, expanded potential interventions beyond purely technical safeguards, and highlighted operational and policy constraints that could affect implementation. This report summarizes the workshop design, outputs, and lessons learned for applying violet teaming to the evaluation of complex, dual-use technologies.

Figures & tables

Explore similar work

Sep 14, 2026

Artificial intelligence and biosecurity: capabilities, threat pathways, and defense-in-depth governance

Artificial intelligence is reshaping biological research across an increasingly connected digital-to-physical workflow. General-purpose large language models can retrieve and integrate scientific information, support experimental planning, and computational analysis; biological foundation models can predict, optimize, and generate proteins, genes, and genome-scale sequences; agentic systems can coordinate multistep research tasks; automated laboratories can partially close the design-build-test-learn cycle. These technologies could greatly benefit medicine, public health, and biotechnology. However, their biosecurity risk depends not only on what the AI can do, but also on who uses it, their expertise and intent, their access to laboratory tools and materials, and the safeguards in place. Current evidence shows that AI uplift exists but primarily affects digital rather than physical tasks. Frontier systems have exceeded expert baselines on in-silico, and screening-evasion benchmarks, whereas controlled wet-laboratory studies find that tacit knowledge and physical execution remain substantial barriers. This review describes the different biological threats from AI tool use, from information gathering and biological design to procurement, synthesis, testing, scale-up, and potential release. We further examine why alignment techniques for general-purpose models transfer poorly to biological ones, and the emerging role of interpretability in auditing whether hazardous capabilities are genuinely removed. We argue for defense-in-depth governance that links capability thresholds to proportionate responsibilities across the biological AI ecosystem, reducing high-consequence risk while preserving beneficial use.
Jun 18, 2026

Measuring Biological Capabilities and Risks of AI Agents

This paper addresses a rapidly emerging policy challenge: how to generate and interpret credible evidence about the biological capabilities and risks of AI scientists, or agentic AI systems capable of autonomously or collaboratively performing multi-step scientific tasks. As these systems enter real research workflows, decision-makers increasingly face evaluation results whose meaning depends on underlying design choices that are often implicit or under-documented. We synthesize current evidence on AI-enabled biological risks and introduce biological agentic evaluations as a promising, but interpretation-sensitive, tool for assessing these systems. Our central contribution is a set of practical, experience-grounded considerations -- drawing from our own evaluations -- that show how choices around defining, designing, running, scoring, and documenting evaluations materially shape what results do and do not imply about risk. The analysis is intended to help policymakers interpret biological evaluation outputs with appropriate caution; guide public and private funders toward high-leverage investments in AI-biology evaluation research; and support biosecurity practitioners assessing emerging AI systems. A secondary audience includes researchers designing or conducting agentic evaluations within frontier AI labs, AI providers, scientific institutions, and third-party evaluation organizations.
Jul 6, 2026

Evaluating calibrated refusal and safe usefulness in dual-use biology settings

As AI agents are incorporated into life science workflows, the capabilities that speed discovery might also enable misuse. We present BioSecBench-Refusal, a benchmark for risk identification and refusal behavior for biological research tasks. The benchmark pairs 61 Routine tasks, legitimate analyses adapted from the published literature, with 46 Red-Team tasks, fictional scenarios that resemble real research but conceal a biosecurity hazard. Across 16 model-harness configurations, refusal rates ranged from 7% to 74% on Routine tasks and 1% to 62% on Red-Team tasks, with many configurations refusing legitimate Routine work at comparable or higher rates than concealed hazards. Refusals were most often triggered by provider API filters applied prior to agentic reasoning. However, models given room to reason showed the potential to identify more real threats. We release BioSecBench-Refusal as a tool for model developers to calibrate capability and caution for agentic biotech R&D.