Research Insights

From award-winning academic research to production-grade AI safety.

Recognized by

Outstanding Paper | NeurIPS

DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models

Best Paper | NeurIPS

When Do Universal Image Jailbreaks Transfer Between Vision-Language Models?

Best Research Paper Finalist | PVLDB

LLM-PBE: Assessing Data Privacy in Large Language Models

Research Papers

New Research

MAStrike: Shapley-Guided Collusive Red-Teaming on Multi-Agent Systems

Red Teaming
June 12, 2026

New Research

BlueCodeAgent: A Blue Teaming Agent Enabled by Automated Red Teaming for CodeGen AI

Agent
May 15, 2026

New Research

Decoding Trust-Agent Platform (DTap): A Controllable and Interactive Red-Teaming Platform for AI Agents

Agent
May 5, 2026

ICLR

SoSBench: Benchmarking Safety Alignment on Six Scientific Domains

Governance
May 5, 2026

ICLR

DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle

Agent
January 27, 2026

ICLR

RedCodeAgent: Automatic Red-Teaming Agent Against Diverse Code Agents

Red Teaming
November 10, 2025

ICLR

Any-Depth Alignment: Unlocking Innate Safety Alignment of LLMs to Any-Depth

Governance
October 20, 2025

ICLR

Scaling Agent Learning via Experience Synthesis

Agent
October 10, 2025

ICLR

ARMs: Adaptive Red-Teaming Agent against Multimodal Models with Plug-and-Play Attacks

Red Teaming
October 3, 2025

ICLR

TrustGen: A Platform of Dynamic Benchmarking on the Trustworthiness of Generative Foundation Models

Governance
September 30, 2025

Blogs

See all Blogs ->

Announcement

April 30, 2026

We’re Not Just Hosting a Conference, We’re Closing the Gap Between AI Research and AI Risk

There's a conversation that needs to happen in AI security. Not a panel discussion. Not a keynote.

Announcement

April 27, 2026

Introducing PolicyGuard: Define, Edit, and Enforce Custom Guardrails for Every Enterprise Model, Agent, and Application

PolicyGuard gives you complete control over how AI policy is defined and enforced across your environment at runtime, without retraining your models.

Announcement

April 24, 2026

Virtue Presents: CTRL+AI A Conference on Trust, Risk, Leadership and AI

​CTRL+AI is an exclusive one-day conference bringing together the best and brightest minds from leading enterprises and AI labs: the researchers, executives, and operators who are building the reality of secure, scalable AI.

Secure your autonomous enterprise with the team that defines the standard.

Don't let safety be the friction that grounds your innovation. Virtue AI is the launchpad for agentic systems, clearing the path from research to production-ready performance.

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.