Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms

• URL: http://arxiv.org/abs/2605.08496v1
• Date: Fri, 08 May 2026 21:21:59 GMT
• Title: Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms
• Abstract summary: 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.
• Score: 3.121353276954014
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Current adversarial robustness methods for large language models require extensive datasets of harmful prompts (thousands to hundreds of thousands of examples), yet remain vulnerable to novel attack vectors and distributional shifts. We propose Latent Personality Alignment (LPA), a sample-efficient defense that achieves robustness by training models on abstract personality traits rather than specific harmful behaviors. Using fewer than 100 trait statements and latent adversarial training, LPA achieves comparable attack success rates to methods trained on 150k+ examples, while maintaining superior utility. Critically, LPA generalizes better to unseen attack distributions, reducing misclassification rates by 2.6x compared to baseline across six harm benchmarks -- without ever seeing harmful examples during training. Our results demonstrate that personality-based alignment offers a principled approach to building robust defenses with minimal cost.

Related papers

• Efficient Safety Alignment of Language Models via Latent Personality Traits [3.72609623254254]
  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.
  arXiv  Detail & Related papers  (2026-07-08T21:03:27Z)
• Information Theoretic Adversarial Training of Large Language Models [26.056920129810294]
  WARDEN is a distributionally robust adversarial training framework for large language models.<n>It dynamically reweights adversarial examples through an f -divergence ambiguity set around the empirical training distribution.<n>It substantially reduces attack success rates with computational and utility costs comparable to CAT-, CAPO-, and MixAT-based baselines.
  arXiv  Detail & Related papers  (2026-05-06T20:20:09Z)
• 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)
• Doubly Robust Instance-Reweighted Adversarial Training [107.40683655362285]
  We propose a novel doubly-robust instance reweighted adversarial framework. Our importance weights are obtained by optimizing the KL-divergence regularized loss function. Our proposed approach outperforms related state-of-the-art baseline methods in terms of average robust performance.
  arXiv  Detail & Related papers  (2023-08-01T06:16:18Z)
• Effective Targeted Attacks for Adversarial Self-Supervised Learning [58.14233572578723]
  unsupervised adversarial training (AT) has been highlighted as a means of achieving robustness in models without any label information. We propose a novel positive mining for targeted adversarial attack to generate effective adversaries for adversarial SSL frameworks. Our method demonstrates significant enhancements in robustness when applied to non-contrastive SSL frameworks, and less but consistent robustness improvements with contrastive SSL frameworks.
  arXiv  Detail & Related papers  (2022-10-19T11:43:39Z)
• Adaptive Feature Alignment for Adversarial Training [56.17654691470554]
  CNNs are typically vulnerable to adversarial attacks, which pose a threat to security-sensitive applications. We propose the adaptive feature alignment (AFA) to generate features of arbitrary attacking strengths. Our method is trained to automatically align features of arbitrary attacking strength.
  arXiv  Detail & Related papers  (2021-05-31T17:01:05Z)
• Attack as Defense: Characterizing Adversarial Examples using Robustness [9.020456982421958]
  We propose a novel defense framework named attack as defense (A2D) to detect adversarial examples. A2D uses the cost of attacking an input for robustness evaluation and identifies those less robust examples as adversarial. Experiment results on MNIST, CIFAR10 and ImageNet show that A2D is more effective than recent promising approaches.
  arXiv  Detail & Related papers  (2021-03-13T06:29:13Z)
• Are Adversarial Examples Created Equal? A Learnable Weighted Minimax Risk for Robustness under Non-uniform Attacks [70.11599738647963]
  Adversarial Training is one of the few defenses that withstand strong attacks. Traditional defense mechanisms assume a uniform attack over the examples according to the underlying data distribution. We present a weighted minimax risk optimization that defends against non-uniform attacks.
  arXiv  Detail & Related papers  (2020-10-24T21:20:35Z)
• Adversarial Distributional Training for Robust Deep Learning [53.300984501078126]
  Adversarial training (AT) is among the most effective techniques to improve model robustness by augmenting training data with adversarial examples. Most existing AT methods adopt a specific attack to craft adversarial examples, leading to the unreliable robustness against other unseen attacks. In this paper, we introduce adversarial distributional training (ADT), a novel framework for learning robust models.
  arXiv  Detail & Related papers  (2020-02-14T12:36:59Z)

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.