SAFETY RESEARCH

OpenAI studies attacks that succeed repeatedly rather than occasionally

By IDAKIM Digital · Published November 13, 2026

Fuzzy robustness research changes how adaptive jailbreaks are selected and used during model training.

OpenAI published its fuzzy robustness research on November 12. The work examines automated attackers that spend additional computation finding attacks with reliable success, rather than optimizing only for a single successful response. Its worst@n framing evaluates behavior over repeated attempts and supports collecting stronger adversarial training examples. OpenAI reports improved robustness against adaptive multi-turn attacks in controlled experiments and describes using the approach in frontier-model safety training. These results concern the model layer and the evaluated attack distributions. They do not prove that every future attack fails, or replace deployment controls around tools, credentials and external actions. The practical contribution is a more demanding way to select and measure adversarial examples, making occasional lucky failures and consistently exploitable weaknesses easier to distinguish.

Why it matters

When evaluating an agent, record repeated-trial outcomes and attacker budgets. Keep held-out attacks separate from training examples and measure normal task performance alongside refusal behavior.

Source: OpenAI · November 12, 2026

Product claims are attributed to the linked publisher. IDAKIM Digital has not independently tested these claims.