Adversarial Attack
The deliberate manipulation of inputs to an AI system to cause it to make errors, misclassify or behave unexpectedly, often through imperceptible perturbations.
In plain language
Deliberately tricking an AI by giving it sneaky inputs. A classic example: putting a tiny sticker on a stop sign that's invisible to humans but causes a self-driving car's AI to misread it.
Why this matters
Adversarial attacks represent a real and growing threat to AI systems. Your AI risk management framework must include threat assessments for adversarial attacks, particularly for AI systems that make high-stakes decisions.
Relevance
GovernanceAdversarial attacks are a security risk that governance has to own. Boards and risk committees need assurance that exposed AI systems have been threat assessed and monitored, not just tested for normal use.
Related terms
Putting adversarial attack into practice in your organisation?
Ready to transform your AI strategy?
Partner with Australia's AI strategy and governance specialists. From adoption roadmaps to ISO 42001 audit readiness.