Improving Phishing Resilience with AI-Generated Training: Evidence on Prompting, Personalization, and Duration

• URL: http://arxiv.org/abs/2512.01893v1
• Date: Mon, 01 Dec 2025 17:13:09 GMT
• Title: Improving Phishing Resilience with AI-Generated Training: Evidence on Prompting, Personalization, and Duration
• Authors: Francesco Greco, Giuseppe Desolda, Cesare Tucci, Andrea Esposito, Antonio Curci, Antonio Piccinno,
• Abstract summary: This paper provides an experimental validation of Large Language Models (LLMs) as autonomous engines for generating phishing resilience training.<n>We demonstrate that AI-generated content yields significant pre-post learning gains regardless of the specific prompting strategy employed.
• Score: 3.639013246937792
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Phishing remains a persistent cybersecurity threat; however, developing scalable and effective user training is labor-intensive and challenging to maintain. Generative Artificial Intelligence offers an interesting opportunity, but empirical evidence on its instructional efficacy remains scarce. This paper provides an experimental validation of Large Language Models (LLMs) as autonomous engines for generating phishing resilience training. Across two controlled studies (N=480), we demonstrate that AI-generated content yields significant pre-post learning gains regardless of the specific prompting strategy employed. Study 1 (N=80) compares four prompting techniques, finding that even a straightforward "direct-profile" strategy--simply embedding user traits into the prompt--produces effective training material. Study 2 (N=400) investigates the scalability of this approach by testing personalization and training duration. Results show that complex psychometric personalization offers no measurable advantage over well-designed generic content, while longer training duration provides a modest boost in accuracy. These findings suggest that organizations can leverage LLMs to generate high-quality, effective training at scale without the need for complex user profiling, relying instead on the inherent capabilities of the model.

Related papers

• Boosting Deep Reinforcement Learning with Semantic Knowledge for Robotic Manipulators [2.6913398550088483]
  Deep Reinforcement Learning (DRL) is a powerful framework for solving complex sequential decision-making problems.<n>We propose a novel integration of DRL with semantic knowledge in the form of Knowledge Graph Embeddings (KGEs)<n>Our architecture combines KGEs with visual observations, enabling the agent to exploit environmental knowledge during training.
  arXiv  Detail & Related papers  (2026-01-23T16:14:28Z)
• Confidence as a Reward: Transforming LLMs into Reward Models [54.98336080630691]
  Confidence-as-a-Reward (CRew) is a training-free method that utilizes token-level confidence in the model's final answers as a proxy for reward.<n>We show that CRew outperforms existing training-free reward approaches on the MATH500 and RewardMATH benchmarks.<n>We propose CRew-DPO, a training strategy that constructs preference data from confidence scores combined with correctness signals.
  arXiv  Detail & Related papers  (2025-10-15T12:51:47Z)
• The Path of Self-Evolving Large Language Models: Achieving Data-Efficient Learning via Intrinsic Feedback [51.144727949988436]
  Reinforcement learning (RL) has demonstrated potential to enhance the reasoning capabilities of large language models (LLMs)<n>In this work, we explore improving LLMs through RL with minimal data.<n>To minimize data dependency, we introduce two novel mechanisms grounded in self-awareness.
  arXiv  Detail & Related papers  (2025-10-03T06:32:10Z)
• WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning [73.91893534088798]
  WebSailor is a complete post-training methodology designed to instill this crucial capability.<n>Our approach involves generating novel, high-uncertainty tasks through structured sampling and information obfuscation.<n>WebSailor significantly outperforms all open-source agents in complex information-seeking tasks.
  arXiv  Detail & Related papers  (2025-09-16T17:57:03Z)
• Towards High Data Efficiency in Reinforcement Learning with Verifiable Reward [54.708851958671794]
  We propose a Data-Efficient Policy Optimization pipeline that combines optimized strategies for both offline and online data selection.<n>In offline phase, we curate a high-quality subset of training samples based on diversity, influence, and appropriate difficulty.<n>During online RLVR training, we introduce a sample-level explorability metric to dynamically filter samples with low exploration potential.
  arXiv  Detail & Related papers  (2025-09-01T10:04:20Z)
• Can Large Reasoning Models Self-Train? [51.0277533541394]
  We use majority voting as a simple self-feedback mechanism to study whether self-training can be sustained within reinforcement learning.<n>We find that this basic approach improves not only the model's reasoning performance, but also its capability of generating better quality feedback for the next RL iteration.<n>Yet our analysis also reveals a critical limitation of such a self-training paradigm - prolonged RL with self-reward leads to reward hacking, resulting in sudden and complete performance collapse.
  arXiv  Detail & Related papers  (2025-05-27T17:16:00Z)
• How Difficulty-Aware Staged Reinforcement Learning Enhances LLMs' Reasoning Capabilities: A Preliminary Experimental Study [16.441081996257576]
  This paper presents a rigorous experimental investigation into how difficulty-aware staged reinforcement learning strategies can substantially improve reasoning performance.<n>We show that strategically selecting training data according to well-defined difficulty levels markedly enhances RL optimization.<n>We will open-source our datasets on GitHub and Hugging Face.
  arXiv  Detail & Related papers  (2025-04-01T14:18:38Z)
• Evolving LLMs' Self-Refinement Capability via Synergistic Training-Inference Optimization [53.93621974137829]
  Self-Refinement refers to a model's ability to revise its own responses to produce improved outputs.<n>EVOLVE is a framework for eliciting and tracking the evolution of Self-Refinement through iterative training.<n>We demonstrate the potential of leveraging Self-Refinement to achieve broader Self-Improvement of intrinsic model abilities.
  arXiv  Detail & Related papers  (2025-02-08T15:21:55Z)
• Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy [4.737519767218666]
  We introduce Salient Information Preserving Adversarial Training (SIP-AT)<n>SIP-AT is an intuitive method for relieving the robustness-accuracy trade-off incurred by traditional adversarial training.<n>We demonstrate that SIP-AT is able to boost the clean accuracy of models while maintaining a high degree of robustness against attacks at multiple epsilon levels.
  arXiv  Detail & Related papers  (2025-01-15T19:12:59Z)
• Protecting Privacy Through Approximating Optimal Parameters for Sequence Unlearning in Language Models [37.172662930947446]
  Language models (LMs) are potentially vulnerable to extraction attacks, which represent a significant privacy risk. We propose Privacy Protection via Optimal Parameters (POP), a novel unlearning method that effectively forgets the target token sequences from the pretrained LM. POP exhibits remarkable retention performance post-unlearning across 9 classification and 4 dialogue benchmarks, outperforming the state-of-the-art by a large margin.
  arXiv  Detail & Related papers  (2024-06-20T08:12:49Z)
• Adversarial Training is Not Ready for Robot Learning [55.493354071227174]
  Adversarial training is an effective method to train deep learning models that are resilient to norm-bounded perturbations. We show theoretically and experimentally that neural controllers obtained via adversarial training are subjected to three types of defects. Our results suggest that adversarial training is not yet ready for robot learning.
  arXiv  Detail & Related papers  (2021-03-15T07:51:31Z)
• Self-Adaptive Training: Bridging the Supervised and Self-Supervised Learning [16.765461276790944]
  Self-adaptive training is a unified training algorithm that dynamically calibrates and enhances training process by model predictions without incurring extra computational cost. We analyze the training dynamics of deep networks on training data corrupted by, e.g., random noise and adversarial examples. Our analysis shows that model predictions are able to magnify useful underlying information in data and this phenomenon occurs broadly even in the absence of emphany label information.
  arXiv  Detail & Related papers  (2021-01-21T17:17:30Z)
• Improving the affordability of robustness training for DNNs [11.971637253035107]
  We show that the initial phase of adversarial training is redundant and can be replaced with natural training which significantly improves the computational efficiency. We show that our proposed method can reduce the training time by a factor of up to 2.5 with comparable or better model test accuracy and generalization on various strengths of adversarial attacks.
  arXiv  Detail & Related papers  (2020-02-11T07:29:45Z)

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.