Researchers have developed a new method to provide plausible deniability guarantees for whistleblowers, addressing the threat of retaliation that deters reporting. The proposed framework formalizes protection against a strong adversary by ensuring per-report $(0, \delta)$-differential privacy on audit selection transcripts. This approach reduces private auditing to private continual counting, offering improved noise scaling and selection error vanishing under certain conditions. AI
IMPACT This research could lead to more secure and private systems for reporting organizational wrongdoing, potentially impacting how sensitive data is handled in various sectors.
RANK_REASON The cluster contains an academic paper published on arXiv detailing a new theoretical framework and mechanism for privacy guarantees. [lever_c_demoted from research: ic=2 ai=0.4]
- $(0, \delta)$-differential privacy
- arXiv
- computer science
- Cryptography and Security
- Hugging Face
- private continual counting
- Randomized Response
- Whistleblowers
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
