mlsanityData to 7 Oct 2026

Do not think about pink elephant!

arXiv 2404.15154 ↗First posted 22 Apr 2024cs.CL cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

Large Models (LMs) have heightened expectations for the potential of general AI as they are akin to human intelligence. This paper shows that recent large models such as Stable Diffusion and DALL-E3 also share the vulnerability of human intelligence, namely the "white bear phenomenon". We investigate the causes of the white bear phenomenon by analyzing their representation space. Based on this analysis, we propose a simple prompt-based attack method, which generates figures prohibited by the LM provider's policy. To counter these attacks, we introduce prompt-based defense strategies inspired by cognitive therapy techniques, successfully mitigating attacks by up to 48.22%.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 9 of its 17 references that are in the map. First posted on arXiv 22 Apr 2024.

Builds on

9 of 17 references.

References · 9

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2023GPT-4 Technical Reportcited by 18,132
  4. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  5. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,393
  6. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,287
  7. 2022GLM-130B: An Open Bilingual Pre-trained Modelcited by 837
  8. 2021Trustworthy AI: From Principles to Practicescited by 206
  9. 2023Safety and Fairness for Content Moderation in Generative Modelscited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 1.

3 papers.

  1. 2024Controlling Language and Diffusion Models by Transporting Activationscited by 59
  2. 2026Feedback That Backfires: Why Small Language Model Agents Repeat the Call They Just Watched Failcited by 2
  3. 2025Don't Think of the White Bear: Ironic Negation in Transformer Models Under Cognitive Loadcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026Honeyquest for LLMs: Rethinking Cyber Deception for AI Attackers
  2. 2026Detection of adversarial intent in Human-AI teams using LLMs
  3. 2026Assessing Automated Prompt Injection Attacks in Agentic Environments
  4. 2026Architecting Secure AI Agents: Perspectives on System-Level Defenses Against Indirect Prompt Injection Attacks
  5. 2025Adversarial Testing in LLMs: Insights into Decision-Making Vulnerabilities
  6. 2023LLMs Killed the Script Kiddie: How Agents Supported by Large Language Models Change the Landscape of Network Threat Testing
  7. 2025Are My Optimized Prompts Compromised? Exploring Vulnerabilities of LLM-based Optimizers
  8. 2023Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking