Efficient Safety Alignment of Language Models via Latent Personality Traits

• URL: http://arxiv.org/abs/2607.07918v1
• Date: Wed, 08 Jul 2026 21:03:27 GMT
• Title: Efficient Safety Alignment of Language Models via Latent Personality Traits
• Abstract summary: We introduce Latent Personality Alignment (LPA), which replaces explicit harm refusal with adversarial training on just 66 harm-agnostic statements.<n>LPA achieves near-zero attack success rates on HarmBench across direct requests and five jailbreak methods.<n>The entire procedure completes in minutes on a single GPU and uses 75x fewer examples than standard LAT.
• Score: 3.72609623254254
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Boundary-targeted Membership Inference Attacks on Safety Classifiers [70.20833439671131]
  Safety classifiers are trained on sensitive datasets including discussions of self-harm and mental health.<n>We introduce a new boundary-targeted selection strategy that identifies low confidence examples.<n>Experiments show that an adversary can recover 19% of the conversations a safety classifier flagged as indicating user distress, at a 5% false-positive rate.<n>This is $3.5$ times more than attacking using state-of-the-art MIA methods alone.
  arXiv  Detail & Related papers  (2026-05-21T12:05:22Z)
• Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms [3.121353276954014]
  Latent Personality Alignment (LPA) is a sample-efficient defense that achieves robustness by training models on abstract personality traits rather than specific harmful behaviors.<n>Using fewer than 100 trait statements and latent adversarial training, LPA achieves comparable attack success rates to methods trained on 150k+ examples.<n>Our results demonstrate that personality-based alignment offers a principled approach to building robust defenses with minimal cost.
  arXiv  Detail & Related papers  (2026-05-08T21:21:59Z)
• A Simple and Efficient Jailbreak Method Exploiting LLMs' Helpfulness [32.47621091096285]
  Safety alignment aims to prevent Large Language Models (LLMs) from responding to harmful queries.<n>In this paper, we introduce HILL, a novel jailbreak approach that transforms imperative harmful requests into learning-style questions.<n> Experiments on the AdvBench dataset across a wide range of models demonstrate HILL's strong effectiveness, generalizability, and harmfulness.
  arXiv  Detail & Related papers  (2025-09-17T04:21:20Z)
• Behind the Mask: Benchmarking Camouflaged Jailbreaks in Large Language Models [0.0]
  camouflaged jailbreaking embeds malicious intent within seemingly benign language to evade existing safety mechanisms.<n>This paper investigates the construction and impact of camouflaged jailbreak prompts, emphasizing their deceptive characteristics and the limitations of traditional keyword-based detection methods.
  arXiv  Detail & Related papers  (2025-09-05T19:57:38Z)
• Improving LLM Safety Alignment with Dual-Objective Optimization [81.98466438000086]
  Existing training-time safety alignment techniques for large language models (LLMs) remain vulnerable to jailbreak attacks.<n>We propose an improved safety alignment that disentangles DPO objectives into two components: (1) robust refusal training, which encourages refusal even when partial unsafe generations are produced, and (2) targeted unlearning of harmful knowledge.
  arXiv  Detail & Related papers  (2025-03-05T18:01:05Z)
• Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacks [23.793583584784685]
  Large language models (LLMs) are susceptible to jailbreak attacks, which exploit system vulnerabilities to circumvent safety measures and elicit harmful or inappropriate outputs.<n>We introduce LATPC, a Latent-space Adrial Training with Post-aware framework.<n>LATPC identifies safety-critical latent dimensions by contrasting harmful and benign inputs, enabling the adaptive construction of targeted refusal feature removal attacks.
  arXiv  Detail & Related papers  (2025-01-18T02:57:12Z)
• Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense [55.77152277982117]
  We introduce Layer-AdvPatcher, a methodology designed to defend against jailbreak attacks.<n>We use an unlearning strategy to patch specific layers within large language models through self-augmented datasets.<n>Our framework reduces the harmfulness and attack success rate of jailbreak attacks.
  arXiv  Detail & Related papers  (2025-01-05T19:06:03Z)
• Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models [55.253208152184065]
  Jailbreaking in Large Language Models (LLMs) is a major security concern as it can deceive LLMs to generate harmful text.<n>We conduct a detailed analysis of seven different jailbreak methods and find that disagreements stem from insufficient observation samples.<n>We propose a novel defense called textbfActivation Boundary Defense (ABD), which adaptively constrains the activations within the safety boundary.
  arXiv  Detail & Related papers  (2024-12-22T14:18:39Z)
• LIAR: Leveraging Inference Time Alignment (Best-of-N) to Jailbreak LLMs in Seconds [98.20826635707341]
  Jailbreak attacks expose vulnerabilities in safety-aligned LLMs by eliciting harmful outputs through carefully crafted prompts.<n>We frame jailbreaks as inference-time misalignment and introduce LIAR, a fast, black-box, best-of-$N$ sampling attack requiring no training.<n>We also introduce a theoretical "safety net against jailbreaks" metric to quantify safety alignment strength and derive suboptimality bounds.
  arXiv  Detail & Related papers  (2024-12-06T18:02:59Z)
• Efficient Adversarial Training in LLMs with Continuous Attacks [99.5882845458567]
  Large language models (LLMs) are vulnerable to adversarial attacks that can bypass their safety guardrails. We propose a fast adversarial training algorithm (C-AdvUL) composed of two losses. C-AdvIPO is an adversarial variant of IPO that does not require utility data for adversarially robust alignment.
  arXiv  Detail & Related papers  (2024-05-24T14:20:09Z)
• Break the Breakout: Reinventing LM Defense Against Jailbreak Attacks with Self-Refinement [2.854482269849925]
  Language models (LMs) are vulnerable to exploitation for adversarial misuse. We propose self-refine with formatting that achieves outstanding safety even in non-safety-aligned LMs. We've also observed that non-safety-aligned LMs outperform safety-aligned LMs in safety tasks by giving more helpful and safe responses.
  arXiv  Detail & Related papers  (2024-02-23T08:22:24Z)
• Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization [98.18718484152595]
  We propose to integrate goal prioritization at both training and inference stages to counteract the intrinsic conflict between the goals of being helpful and ensuring safety. Our work thus contributes to the comprehension of jailbreaking attacks and defenses, and sheds light on the relationship between LLMs' capability and safety.
  arXiv  Detail & Related papers  (2023-11-15T16:42:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.