x.compaperCryptography and Security Papers (@FSFG) on X
PrivacyEvalClaw is a tool-augmented deliberative agent for auditing privacy leakage in LLM responses produced under jailbreak prompts. By Krishna Kanth Nakka and five co-authors, the paper is on arXiv (cs.CR) and accepted to AACL-IJCNLP 2026. The fetched post gives only the title, authors and venue, so method details and results are not available here.
TL;DR Presents an agentic evaluator that audits whether jailbroken LLM responses leak private information.
Also seen from another angle🛡️ Security →
Organisations named here
- AACL-IJCNLP 2026
- arXiv
- Krishna Kanth Nakka
- PrivacyEvalClaw
Technologies named here
- LLM
- PrivacyEvalClaw
Related in evals
