Niloofar Mireshghallah

niloofarm's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 16 papers 25 days ago

Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory

Paper • 2310.17884 • Published Oct 27, 2023 • 1

A Roadmap to Pluralistic Alignment

Paper • 2402.05070 • Published Feb 7, 2024

Do Membership Inference Attacks Work on Large Language Models?

Paper • 2402.07841 • Published Feb 12, 2024

Alpaca against Vicuna: Using LLMs to Uncover Memorization of LLMs

Paper • 2403.04801 • Published Mar 5, 2024

AI as Humanity's Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text

Paper • 2410.04265 • Published Oct 5, 2024

Breaking News: Case Studies of Generative AI's Use in Journalism

Paper • 2406.13706 • Published Jun 19, 2024

HAICOSYSTEM: An Ecosystem for Sandboxing Safety Risks in Human-AI Interactions

Paper • 2409.16427 • Published Sep 24, 2024 • 1

Information-Guided Identification of Training Data Imprint in (Proprietary) Large Language Models

Paper • 2503.12072 • Published Mar 15

Strong Membership Inference Attacks on Massive Datasets and (Moderately) Large Language Models

Paper • 2505.18773 • Published May 24 • 7

Bob's Confetti: Phonetic Memorization Attacks in Music and Video Generation

Paper • 2507.17937 • Published Jul 23 • 1

The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage

Paper • 2508.09603 • Published Aug 13 • 2

Harnessing Optimization Dynamics for Curvature-Informed Model Merging

Paper • 2509.11167 • Published Sep 14 • 1

Position: Privacy Is Not Just Memorization!

Paper • 2510.01645 • Published Oct 2 • 1

Privacy-Preserving LLM Interaction with Socratic Chain-of-Thought Reasoning and Homomorphically Encrypted Vector Databases

Paper • 2506.17336 • Published Jun 19 • 1

Spectrum Tuning: Post-Training for Distributional Coverage and In-Context Steerability

Paper • 2510.06084 • Published Oct 7

Reinforcement Learning Improves Traversal of Hierarchical Knowledge in LLMs

Paper • 2511.05933 • Published 28 days ago • 7

commented a paper 25 days ago

Reinforcement Learning Improves Traversal of Hierarchical Knowledge in LLMs

Paper • 2511.05933 • Published 28 days ago • 7 •

2

commented a paper about 2 months ago

Position: Privacy Is Not Just Memorization!

Paper • 2510.01645 • Published Oct 2 • 1 •

2

liked a Space 10 months ago

Running

6

Creativity Index

👩

6

Compute the Creativity Index of a text

authored a paper over 1 year ago

WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models

Paper • 2406.18510 • Published Jun 26, 2024 • 10