Zortium runs a full consortium of adversarial attacks against your VLM endpoint — visual injections, jailbreak benchmarks, text-channel exploits, and more. Get a per-suite ASR report in minutes.
Point Zortium at any OpenAI-compatible endpoint. Paste your base URL and API key — no SDK changes, no instrumentation.
Zortium fires 15+ adversarial attack suites across visual and text channels. Real benchmark images, real jailbreak payloads.
Get a full ASR breakdown per suite, per harm category, with individual breach details and remediation context.
Covering both the visual and text channels — the full attack surface of a deployed VLM.
Embeds harmful instructions as readable text inside an image. Tests if the model executes visual text it would refuse in chat.
Presents harmful topics as numbered blank-list documents for the model to 'complete' — exploiting document-task framing.
Runs real benchmark images from the 2024 COLM JailBreakV-28K dataset across 7 adversarial format types.
Appends adversarial token suffixes computed against open-source models to test cross-model transfer.
Prefixes 24 fake compliant-assistant exchanges to shift the model's in-context distribution toward compliance.
Classic prompt injection: buries a harmful directive inside a benign cover task using delimiter spoofing.
Any endpoint that speaks the OpenAI chat-completions protocol is supported out of the box.
Run the full attack suite locally against any endpoint. No account required.
Hosted dashboard, scan history, team sharing, and managed benchmark assets.
On-prem deployment, custom attack suites, SLA, and dedicated support.