Lying Blindly: Bypassing ChatGPT's Safeguards to Generate Hard-to-Detect Disinformation Claims

• URL: http://arxiv.org/abs/2402.08467v2
• Date: Mon, 09 Dec 2024 11:34:28 GMT
• Title: Lying Blindly: Bypassing ChatGPT's Safeguards to Generate Hard-to-Detect Disinformation Claims
• Authors: Freddy Heppell, Mehmet E. Bakir, Kalina Bontcheva,
• Abstract summary: This study explores the capability of ChatGPT with GPT-3.5 to generate short-form disinformation claims about the war in Ukraine.<n>We do not provide the model with human-written disinformation narratives by including them in the prompt.<n>We show that ChatGPT can produce realistic, target-specific disinformation claims, even on a specific post-cutoff event.
• Score: 0.7478304180168185
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As Large Language Models become more proficient, their misuse in coordinated disinformation campaigns is a growing concern. This study explores the capability of ChatGPT with GPT-3.5 to generate short-form disinformation claims about the war in Ukraine, both in general and on a specific event, which is beyond the GPT-3.5 knowledge cutoff. Unlike prior work, we do not provide the model with human-written disinformation narratives by including them in the prompt. Thus the generated short claims are hallucinations based on prior world knowledge and inference from the minimal prompt. With a straightforward prompting technique, we are able to bypass model safeguards and generate numerous short claims. We compare those against human-authored false claims on the war in Ukraine from ClaimReview, specifically with respect to differences in their linguistic properties. We also evaluate whether AI authorship can be differentiated by human readers or state-of-the-art authorship detection tools. Thus, we demonstrate that ChatGPT can produce realistic, target-specific disinformation claims, even on a specific post-cutoff event, and that they cannot be reliably distinguished by humans or existing automated tools.

Related papers

• SLURG: Investigating the Feasibility of Generating Synthetic Online Fallacious Discourse [0.0]
  We explore the definition, and extrapolation of fallacies as they pertain to the automatic detection of manipulation on social media. In particular we explore how these logical fallacies might appear in the real world i.e internet forums. We discovered a prevalence of misinformation / misguided intention in discussion boards specifically centered around the Ukrainian Russian Conflict.
  arXiv  Detail & Related papers  (2025-04-16T20:03:47Z)
• 'Quis custodiet ipsos custodes?' Who will watch the watchmen? On Detecting AI-generated peer-reviews [20.030884734361358]
  There is a growing concern that AI-generated texts could compromise scientific publishing, including peer-review. We introduce the Term Frequency (TF) model, which posits that AI often repeats tokens, and the Review Regeneration (RR) model, which is based on the idea that ChatGPT generates similar outputs upon re-prompting. Our findings suggest both our proposed methods perform better than the other AI text detectors.
  arXiv  Detail & Related papers  (2024-10-13T08:06:08Z)
• RogueGPT: dis-ethical tuning transforms ChatGPT4 into a Rogue AI in 158 Words [0.0]
  This paper explores how easily the default ethical guardrails of ChatGPT, using its latest customization features, can be bypassed. This malevolently altered version of ChatGPT, nicknamed "RogueGPT", responded with worrying behaviours. Our findings raise significant concerns about the model's knowledge about topics like illegal drug production, torture methods and terrorism.
  arXiv  Detail & Related papers  (2024-06-11T18:59:43Z)
• Missci: Reconstructing Fallacies in Misrepresented Science [84.32990746227385]
  Health-related misinformation on social networks can lead to poor decision-making and real-world dangers. Missci is a novel argumentation theoretical model for fallacious reasoning. We present Missci as a dataset to test the critical reasoning abilities of large language models.
  arXiv  Detail & Related papers  (2024-06-05T12:11:10Z)
• Fine-tuning Language Models for Factuality [96.5203774943198]
  Large pre-trained language models (LLMs) have led to their widespread use, sometimes even as a replacement for traditional search engines. Yet language models are prone to making convincing but factually inaccurate claims, often referred to as 'hallucinations' In this work, we fine-tune language models to be more factual, without human labeling.
  arXiv  Detail & Related papers  (2023-11-14T18:59:15Z)
• Exploring ChatGPT's Capabilities on Vulnerability Management [56.4403395100589]
  We explore ChatGPT's capabilities on 6 tasks involving the complete vulnerability management process with a large-scale dataset containing 70,346 samples. One notable example is ChatGPT's proficiency in tasks like generating titles for software bug reports. Our findings reveal the difficulties encountered by ChatGPT and shed light on promising future directions.
  arXiv  Detail & Related papers  (2023-11-11T11:01:13Z)
• DEMASQ: Unmasking the ChatGPT Wordsmith [63.8746084667206]
  We propose an effective ChatGPT detector named DEMASQ, which accurately identifies ChatGPT-generated content. Our method addresses two critical factors: (i) the distinct biases in text composition observed in human- and machine-generated content and (ii) the alterations made by humans to evade previous detection methods.
  arXiv  Detail & Related papers  (2023-11-08T21:13:05Z)
• Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory [82.7042006247124]
  We show that even the most capable AI models reveal private information in contexts that humans would not, 39% and 57% of the time, respectively. Our work underscores the immediate need to explore novel inference-time privacy-preserving approaches, based on reasoning and theory of mind.
  arXiv  Detail & Related papers  (2023-10-27T04:15:30Z)
• Factuality Challenges in the Era of Large Language Models [113.3282633305118]
  Large Language Models (LLMs) generate false, erroneous, or misleading content. LLMs can be exploited for malicious applications. This poses a significant challenge to society in terms of the potential deception of users.
  arXiv  Detail & Related papers  (2023-10-08T14:55:02Z)
• Fighting Fire with Fire: Can ChatGPT Detect AI-generated Text? [20.37071875344405]
  We evaluate the zero-shot performance of ChatGPT in the task of human-written vs. AI-generated text detection. We empirically investigate if ChatGPT is symmetrically effective in detecting AI-generated or human-written text.
  arXiv  Detail & Related papers  (2023-08-02T17:11:37Z)
• Is ChatGPT Involved in Texts? Measure the Polish Ratio to Detect ChatGPT-Generated Text [48.36706154871577]
  We introduce a novel dataset termed HPPT (ChatGPT-polished academic abstracts) It diverges from extant corpora by comprising pairs of human-written and ChatGPT-polished abstracts instead of purely ChatGPT-generated texts. We also propose the "Polish Ratio" method, an innovative measure of the degree of modification made by ChatGPT compared to the original human-written text.
  arXiv  Detail & Related papers  (2023-07-21T06:38:37Z)
• "HOT" ChatGPT: The promise of ChatGPT in detecting and discriminating hateful, offensive, and toxic comments on social media [2.105577305992576]
  Generative AI models have the potential to understand and detect harmful content. ChatGPT can achieve an accuracy of approximately 80% when compared to human annotations.
  arXiv  Detail & Related papers  (2023-04-20T19:40:51Z)
• To ChatGPT, or not to ChatGPT: That is the question! [78.407861566006]
  This study provides a comprehensive and contemporary assessment of the most recent techniques in ChatGPT detection. We have curated a benchmark dataset consisting of prompts from ChatGPT and humans, including diverse questions from medical, open Q&A, and finance domains. Our evaluation results demonstrate that none of the existing methods can effectively detect ChatGPT-generated content.
  arXiv  Detail & Related papers  (2023-04-04T03:04:28Z)
• Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense [56.077252790310176]
  We present a paraphrase generation model (DIPPER) that can paraphrase paragraphs, condition on surrounding context, and control lexical diversity and content reordering. Using DIPPER to paraphrase text generated by three large language models (including GPT3.5-davinci-003) successfully evades several detectors, including watermarking. We introduce a simple defense that relies on retrieving semantically-similar generations and must be maintained by a language model API provider.
  arXiv  Detail & Related papers  (2023-03-23T16:29:27Z)
• Can AI-Generated Text be Reliably Detected? [50.95804851595018]
  Large Language Models (LLMs) perform impressively well in various applications. The potential for misuse of these models in activities such as plagiarism, generating fake news, and spamming has raised concern about their responsible use. We stress-test the robustness of these AI text detectors in the presence of an attacker.
  arXiv  Detail & Related papers  (2023-03-17T17:53:19Z)
• SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models [55.60306377044225]
  "SelfCheckGPT" is a simple sampling-based approach to fact-check the responses of black-box models. We investigate this approach by using GPT-3 to generate passages about individuals from the WikiBio dataset.
  arXiv  Detail & Related papers  (2023-03-15T19:31:21Z)
• A Categorical Archive of ChatGPT Failures [47.64219291655723]
  ChatGPT, developed by OpenAI, has been trained using massive amounts of data and simulates human conversation. It has garnered significant attention due to its ability to effectively answer a broad range of human inquiries. However, a comprehensive analysis of ChatGPT's failures is lacking, which is the focus of this study.
  arXiv  Detail & Related papers  (2023-02-06T04:21:59Z)
• ChatGPT or Human? Detect and Explain. Explaining Decisions of Machine Learning Model for Detecting Short ChatGPT-generated Text [2.0378492681344493]
  We study whether a machine learning model can be effectively trained to accurately distinguish between original human and seemingly human (that is, ChatGPT-generated) text. We employ an explainable artificial intelligence framework to gain insight into the reasoning behind the model trained to differentiate between ChatGPT-generated and human-generated text. Our study focuses on short online reviews, conducting two experiments comparing human-generated and ChatGPT-generated text.
  arXiv  Detail & Related papers  (2023-01-30T08:06:08Z)
• How would Stance Detection Techniques Evolve after the Launch of ChatGPT? [5.756359016880821]
  A new pre-trained language model chatGPT was launched on Nov 30, 2022. ChatGPT can achieve SOTA or similar performance for commonly used datasets including SemEval-2016 and P-Stance. ChatGPT has the potential to be the best AI model for stance detection tasks in NLP.
  arXiv  Detail & Related papers  (2022-12-30T05:03:15Z)

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.