Side-Channel Exfiltration and Narrative Erosion in Frontier Language Models
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
Frontier language models that correctly identify and refuse social engineering attacks against system-prompt-protected data leak that data through the content of their refusal explanations. In multi-turn experiments across Claude Opus 4.6, GPT-5.4, and Claude Haiku 4.5 (2,200 API calls, 114 USD total), this confirmation side-channel appeared in 11 of 12 conversations through three mechanisms: direct disclosure under authority ambiguity, confirmation through refusal explanation, and cumulative refusal mapping. Longer conversations produced more extensive leakage, but the driver is not context length. Single-turn context flooding up to 843K tokens produced zero safety degradation (90+ calls, 3 runs per condition, 3 models). A three-condition control separated the variables: 300 turns of neutral conversation (210K tokens) produced zero erosion, while 300 turns of persuasive conversation (44K tokens) produced full behavioral erosion. A follow-up density-interleaving experiment identified narrative coherence as the critical factor: randomly mixing persuasive messages at 25%, 50%, and 75% density produced zero erosion, while a coherent persuasive narrative at the same content caused complete drift. These results challenge the context-length framing that dominates the multi-turn jailbreaking literature and suggest that conversational content and narrative structure, not token volume, constitute the primary attack surface for behavioral erosion in frontier models.
Fields of Study & Subjects
Adversarial Robustness in Machine Learning
Ethics and Social Impacts of AI
Security and Verification in Computing
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 31 March 2026
- Language
- EN
- Document type
- Preprint