COLM 2026 privacy lineup: LLM agent re-identification, CIDER dataset, HAIPS workshop
tianshi_li · x · 2026-10-07
Researcher tianshili previews COLM 2026 highlights from her lab: work on how agent autonomy reshapes personalization's effect on privacy concerns and trust in LLM agents; CIDER, a new dataset of contextual disclosure boundaries for privacy preference alignment; and co-organizing the second HAIPS workshop on human-centered privacy and security for language models, with student papers on LLM-agent re-identification, anonymization against agentic re-identification, and authorization alignment for LLM agents (spotlight oral).
More from Safety
- AI outcomes grow extreme: unaligned persistent agents with full data access called reckless — amankhan · 2026-10-07
- Keurig coffee machine caught uploading 1TB of data in 10 days, sparks privacy backlash — zacharynado · 2026-10-07
- Project Glasswing Reports 135K Verified Vulnerabilities, 9,333 Already Patched — ResultBackground2450 · 2026-10-07
- Anthropic Expands Cyber Verification Program With Three Tiers, Opens Door to Authorized Offensive Work — EricBuess · 2026-10-07
- An excellent overview of AI watermarking and why it can't really be avoided — aronchick · 2026-10-07
- Pentagon pulls plug on Claude after Anthropic refused to lift limits on surveillance, weapons — mark_k · 2026-10-07