Probing the Safety Robustness of LLMs in Latent Space

Safety alignment is a fundamental prerequisite for building trustworthy artificial general intelligence. Despite substantial progress in safety alignment techniques, empirical evidence shows that aligned large language models can still produce unsafe responses under minor internal perturbations, revealing a robustness gap in existing safety mechanisms at the latent representation level. In this paper, we study the robustness evaluation of safety alignment under latent-space perturbations. We introduce Activation Steering Attack (ASA), and leverage the Negative Log-Likelihood (NLL) as a diagnostic signal to probe the local sensitivity of safety behaviors in latent space. By measuring a model’s likelihood under controlled perturbations to its hidden representations, we assess the stability of its original responses. The probing signal is model-agnostic and supervision-free, enabling a general and reproducible diagnostic metric for analyzing safety robustness. Leveraging these probes, we systematically uncover a set of previously underexplored empirical findings, including (1) non-stationarity of layer vulnerabilities, revealing that the most vulnerable layer is an unstable property and even relocates after robustness training; (2) instance-level alignment with cross-layer consistency, where specific inputs remain universally vulnerable across the entire model hierarchy; (3) compositional effects of ASA, characterized by its incremental accumulation across sequential decoding steps and its potential for prompt-level jailbreak effectiveness. Codes are available at (cid:135) LatentSafety.