Skip to content

SocietyAI glossary

Jailbreak

Bypassing an AI's guardrails with clever prompts to make it produce what it should refuse. A perpetual game of cat and mouse with its designers.

In other words

Finding the right wording to make the security guard say, "Alright, fine, come in."

Alyriaz articles that mention it

  • Can security research be dangerous? · Vision

    A security research method has turned out to be directly usable as an attack tool. We examine the dual-use dilemma, the responses built by other disciplines, and what AI is missing.

  • A security research tool turned into a master key · Society

    A researcher has shown that a technique from security research could be turned into a universal attack template, with success rates of 84 to 100% on the most vulnerable models tested. We analyse the mechanism and what it reveals.

  • One link was enough to leak your emails: the Copilot flaw that makes agentjacking a reality. · Society

    Microsoft has patched a vulnerability that, via a simple malicious link, could automatically trigger instructions in Copilot and exfiltrate connected data. We break down the mechanism and the lessons to be learned.

  • The flaw that makes AIs decrypt the secret thoughts of their big sisters · Society

    A research paper shows that the encrypted reasoning blocks emitted by major providers are interchangeable between models within the same ecosystem, allowing a weaker model to decrypt in plain text the reasoning of a more powerful one. We explain the flaw and its consequences.

  • Data centers protected against drones: AI security goes physical · Society

    Companies are developing anti-drone protection systems for AI data centres. We look at what this emerging market reveals about the new status of these facilities.

  • What is an AI "jailbreak"? The security problem no one has solved yet · Explainers

    A jailbreak involves bypassing an AI model's guardrails to make it produce content it should refuse to generate. We explain what this phenomenon is, why it is structurally difficult to prevent, what labs are doing to protect against it, and why an incident of this kind led to a model being suspended worldwide.

Go further at the Academy

See also

More in this family: Society

Find it in the full glossary →All the terms