Activation Surgery: Jailbreaking White-box LLMs without Touching the Prompt

Most jailbreak techniques for Large Language Models (LLMs) primarily rely on prompt modifications, including paraphrasing, obfuscation, or conversational strategies. Meanwhile, abliteration techniques (also known as targeted ablations of internal components) have been used to study and explain LLM outputs by probing which internal structures causally support particular responses. In this work, we combine these two lines of research by directly manipulating the model's internal activations to alter its generation trajectory without changing the prompt. Our method constructs a nearby benign prompt and performs layer-wise activation substitutions using a sequential procedure. We show that this activation surgery method reveals where and how refusal arises, and prevents refusal signals from propagating across layers, thereby inhibiting the model's safety mechanisms. Finally, we discuss the security implications for open-weights models and instrumented inference environments.

Comment

To appear in Proceedings of ESORICS 2026 (Springer LNCS)