Involuntary In-Context Learning: Exploiting Few-Shot Pattern Completion to Bypass Safety Alignment in GPT-5.4

arXiv:2604.19461v2 Announce Type: replace Abstract: Safety alignment in large language models relies on behavioral training that can be overridden when sufficiently strong in-context patterns compete with learned refusal behaviors. We introduce Involuntary In-Context Learning (IICL), an attack class that uses abstract operator framing with few-shot examples to force pattern completion that overrides safety training. Through 3479 probes across 10 OpenAI models, we identify the attack's effective components through a seven-experiment ablation study. Key findings: (1)~semantic operator naming achieves 100% bypass rate (50/50, $p < 0.001$); (2)~the attack requires abstract framing, since identical examples in direct question-and-answer format yield 0%; (3)~example ordering matters strongly (interleaved: 76%, harmful-first: 6%); (4)~temperature has no meaningful effect (46-56% across 0.0--1.0). On the HarmBench benchmark, IICL achieves 24.0% bypass $[18.6%, 30.4%]$ against GPT-5.4 with detailed 619-word responses, compared to 0.0% for direct queries.