Safety Is Not Universal: The Selective Safety Trap in LLM Alignment

Large language models (LLMs) are rigorously aligned to refuse harmful requests, a process that inherently cultivates a latent capacity to evaluate and recognize unsafe content. In this work, we reveal that this advanced safety awareness inadvertently introduces a fatal vulnerability. We introduce Posterior Attack, a single-query jailbreak that bypasses guardrails by prompting the model to generate the exact harmful response its internal classifier would normally flag as unsafe. Through extensive empirical evaluation across 30 open-source LLMs (up to 35B parameters in size) and frontier models (e.g., GPT-5, Claude 4.6), we observe a striking phenomenon: models with superior safety-judgment capabilities are disproportionately more susceptible to this exploitation. To explain this, we formalize the Safety Paradox, analytically showing that monotonic improvements in safety alignment naturally amplify posterior vulnerability. Finally, we establish a causal link via reinforcement learning interventions, exemplifying that artificially degrading a model's safety judgment immunizes it against the attack, whereas enhancing judgment exacerbates the vulnerability. Our findings highlight potential flaws in current alignment paradigms, indicating that defense mechanisms may require further structural refinement.

Aligning large language models (LLMs) is essential for their safe deployment. Current alignment methods mainly optimize observable responses, yet models remain vulnerable when the same harmful intent is recast in unfamiliar or adversarial forms that humans can easily recognize. Prototype theory offers an account of this adaptability. Human concepts are represented around central cases, and new instances are categorized according to their graded typicality relative to these prototypes. Here we show that such categorization of moral concepts is weakly preserved in current LLMs. Across 23 LLMs, models often failed to distinguish opposed moral categories or preserve fine-grained typicality within each category. These deficits persist across parameter sizes and alignment stages. We developed representational similarity optimization, which directly aligns the latent representations in LLMs with the categorization expressed in human moral judgements, without supervising generated responses. In matched experiments using the same 251,334 moral annotations, standard behavioral alignment learned the intended moral judgements at the response level while leaving the categorization structure largely unchanged and increasing vulnerability across adversarial evaluations. Reorganizing moral categorization produced more modest gains in explicit judgements but consistently improved adversarial robustness across model scales on diverse benchmarks and attack strategies. Our findings provide functional support for the view that prototype-based categorization contributes to behavioral adaptability. They also show that transferring this representational principle to LLMs yields generalizable safety under adversarial conditions.

Current safety methods for large language models are known to be vulnerable to adversarial attacks, motivating research into robust alternatives. Latent Adversarial Training (LAT) is among the most effective defenses, but can degrade utility and requires training on large datasets of harmful prompts. We introduce Latent Personality Alignment (LPA), which replaces explicit harm refusal with adversarial training on just 66 harm-agnostic statements drawn from psychometric personality literature. We hypothesize that personality-anchored representations share latent structure with harm avoidance, so adversarially stabilizing them implicitly constrains the subspace exploited by jailbreak attacks. LPA achieves near-zero attack success rates on HarmBench across direct requests and five jailbreak methods, despite never seeing harmful content during training and no loss of performance on standard benchmarks. Moreover, the training process is lightweight; the entire procedure completes in minutes on a single GPU and uses 75x fewer examples than standard LAT. Extensive ablations demonstrate the robustness, efficiency, and generalization of our method.