Investigating the Effectiveness of Bayesian Spam Filters in Detecting LLM-modified Spam Mails

• URL: http://arxiv.org/abs/2408.14293v1
• Date: Mon, 26 Aug 2024 14:25:30 GMT
• Title: Investigating the Effectiveness of Bayesian Spam Filters in Detecting LLM-modified Spam Mails
• Authors: Malte Josten, Torben Weis,
• Abstract summary: Spam and phishing remain critical threats in cybersecurity, responsible for nearly 90% of security incidents. As these attacks grow in sophistication, the need for robust defensive mechanisms intensifies. The emergence of large language models (LLMs) such as ChatGPT presents new challenges. This work aims to evaluate the robustness and effectiveness of SpamAssassin against LLM-modified email content.
• Score: 1.6298172960110866
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Spam and phishing remain critical threats in cybersecurity, responsible for nearly 90% of security incidents. As these attacks grow in sophistication, the need for robust defensive mechanisms intensifies. Bayesian spam filters, like the widely adopted open-source SpamAssassin, are essential tools in this fight. However, the emergence of large language models (LLMs) such as ChatGPT presents new challenges. These models are not only powerful and accessible, but also inexpensive to use, raising concerns about their misuse in crafting sophisticated spam emails that evade traditional spam filters. This work aims to evaluate the robustness and effectiveness of SpamAssassin against LLM-modified email content. We developed a pipeline to test this vulnerability. Our pipeline modifies spam emails using GPT-3.5 Turbo and assesses SpamAssassin's ability to classify these modified emails correctly. The results show that SpamAssassin misclassified up to 73.7% of LLM-modified spam emails as legitimate. In contrast, a simpler dictionary-replacement attack showed a maximum success rate of only 0.4%. These findings highlight the significant threat posed by LLM-modified spam, especially given the cost-efficiency of such attacks (0.17 cents per email). This paper provides crucial insights into the vulnerabilities of current spam filters and the need for continuous improvement in cybersecurity measures.

Related papers

• Next-Generation Phishing: How LLM Agents Empower Cyber Attackers [10.067883724547182]
  The escalating threat of phishing emails has become increasingly sophisticated with the rise of Large Language Models (LLMs) As attackers exploit LLMs to craft more convincing and evasive phishing emails, it is crucial to assess the resilience of current phishing defenses. We conduct a comprehensive evaluation of traditional phishing detectors, such as Gmail Spam Filter, Apache SpamAssassin, and Proofpoint, as well as machine learning models like SVM, Logistic Regression, and Naive Bayes. Our results reveal notable declines in detection accuracy for rephrased emails across all detectors, highlighting critical weaknesses in current phishing defenses.
  arXiv  Detail & Related papers  (2024-11-21T06:20:29Z)
• ASETF: A Novel Method for Jailbreak Attack on LLMs through Translate Suffix Embeddings [58.82536530615557]
  We propose an Adversarial Suffix Embedding Translation Framework (ASETF) to transform continuous adversarial suffix embeddings into coherent and understandable text. Our method significantly reduces the computation time of adversarial suffixes and achieves a much better attack success rate to existing techniques.
  arXiv  Detail & Related papers  (2024-02-25T06:46:27Z)
• PAL: Proxy-Guided Black-Box Attack on Large Language Models [55.57987172146731]
  Large Language Models (LLMs) have surged in popularity in recent months, but they have demonstrated capabilities to generate harmful content when manipulated. We introduce the Proxy-Guided Attack on LLMs (PAL), the first optimization-based attack on LLMs in a black-box query-only setting. Our attack achieves 84% attack success rate (ASR) on GPT-3.5-Turbo and 48% on Llama-2-7B, compared to 4% for the current state of the art.
  arXiv  Detail & Related papers  (2024-02-15T02:54:49Z)
• Prompted Contextual Vectors for Spear-Phishing Detection [45.07804966535239]
  Spear-phishing attacks present a significant security challenge. We propose a detection approach based on a novel document vectorization method. Our method achieves a 91% F1 score in identifying LLM-generated spear-phishing emails.
  arXiv  Detail & Related papers  (2024-02-13T09:12:55Z)
• SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks [99.23352758320945]
  We propose SmoothLLM, the first algorithm designed to mitigate jailbreaking attacks on large language models (LLMs) Based on our finding that adversarially-generated prompts are brittle to character-level changes, our defense first randomly perturbs multiple copies of a given input prompt, and then aggregates the corresponding predictions to detect adversarial inputs.
  arXiv  Detail & Related papers  (2023-10-05T17:01:53Z)
• Application of BadNets in Spam Filters [1.5755923640031848]
  We design backdoor attacks in the domain of spam filtering. We highlight the need for careful consideration and evaluation of the models used in spam filters.
  arXiv  Detail & Related papers  (2023-07-18T21:39:39Z)
• Building an Effective Email Spam Classification Model with spaCy [0.0]
  Author has used spaCy natural language processing library and 3 machine learning (ML) algorithms Naive Bayes (NB), Decision Tree C45 and Multilayer Perceptron (MLP) in Python programming language to detect spam emails collected from Gmail service.
  arXiv  Detail & Related papers  (2023-03-15T17:41:11Z)
• Spam Detection Using BERT [0.0]
  We build a spam detector using BERT pre-trained model that classifies emails and messages by understanding to their context. Our spam detector performance was 98.62%, 97.83%, 99.13% and 99.28% respectively.
  arXiv  Detail & Related papers  (2022-06-06T09:09:40Z)
• Deep convolutional forest: a dynamic deep ensemble approach for spam detection in text [219.15486286590016]
  This paper introduces a dynamic deep ensemble model for spam detection that adjusts its complexity and extracts features automatically. As a result, the model achieved high precision, recall, f1-score and accuracy of 98.38%.
  arXiv  Detail & Related papers  (2021-10-10T17:19:37Z)
• Phishing and Spear Phishing: examples in Cyber Espionage and techniques to protect against them [91.3755431537592]
  Phishing attacks have become the most used technique in the online scams, initiating more than 91% of cyberattacks, from 2012 onwards. This study reviews how Phishing and Spear Phishing attacks are carried out by the phishers, through 5 steps which magnify the outcome.
  arXiv  Detail & Related papers  (2020-05-31T18:10:09Z)
• DeepQuarantine for Suspicious Mail [0.0]
  DeepQuarantine (DQ) is a cloud technology to detect and quarantine potential spam messages. Most of the quarantined mail is spam, which allows clients to use email without delay.
  arXiv  Detail & Related papers  (2020-01-13T11:32:58Z)

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.