Research map / Large language models / Instruction and fine-tuning
Position: Fundamental Limitations of LLM Censorship Necessitate New Approaches
David Glukhov, Ilia Shumailov, Yarin Gal, Nicolas Papernot, Vardan Papyan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use a Caesar cipher with shift 3 to encrypt the prompt and response | GPT-4-turbo · Explosive-device instruction generation | generation of interpretable harmful output | Improved |
| Assess a shift-3 Caesar-cipher output with GPT-3.5-turbo variants rather than GPT-4 variants | Encrypted harmful outputs · Detection of encrypted explosive-device instructions | harmful-output detection | Mixed |
| Use a Caesar cipher with shift 2 instead of shift 3 | GPT-4-turbo · Encrypted explosive-device instruction generation | generation of interpretable harmful output | Hurt |
Closest papers by meaning
- Assessing Vulnerabilities in State-of-the-Art Large Language Models Through Hex Injection (Student Abstract) (AAAI 2025 · similarity 0.88)
- Tamper-Resistant Safeguards for Open-Weight LLMs (ICLR 2025 · similarity 0.88)
- Against All Odds: Overcoming Typology, Script, and Language Confusion in Multilingual Embedding Inversion Attacks (AAAI 2025 · similarity 0.87)
- Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory (ICLR 2024 · similarity 0.87)
- Hidden No More: Attacking and Defending Private Third-Party LLM Inference (ICML 2025 · similarity 0.87)
- On Evaluating the Durability of Safeguards for Open-Weight LLMs (ICLR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
