Martin Gubri

mgubri's activity

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

authored a paper 19 days ago

Is Multilingual LLM Watermarking Truly Multilingual? A Simple Back-Translation Solution

Paper • 2510.18019 • Published 21 days ago • 17

authored a paper 25 days ago

Dr.LLM: Dynamic Layer Routing in LLMs

Paper • 2510.12773 • Published 27 days ago • 31

authored a paper 28 days ago

DISCO: Diversifying Sample Condensation for Efficient Model Evaluation

Paper • 2510.07959 • Published Oct 9 • 14

authored 3 papers 2 months ago

Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models

Paper • 2411.00154 • Published Oct 31, 2024 • 1

Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers

Paper • 2506.15674 • Published Jun 18 • 2

C-SEO Bench: Does Conversational SEO Work?

Paper • 2506.11097 • Published Jun 6 • 2

authored 6 papers over 1 year ago

Calibrating Large Language Models Using Their Generations Only

Paper • 2403.05973 • Published Mar 9, 2024 • 1

LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinity

Paper • 2207.13129 • Published Jul 26, 2022

Going Further: Flatness at the Rescue of Early Stopping for Adversarial Example Transferability

Paper • 2304.02688 • Published Apr 5, 2023

ProPILE: Probing Privacy Leakage in Large Language Models

Paper • 2307.01881 • Published Jul 4, 2023 • 2

Efficient and Transferable Adversarial Examples from Bayesian Neural Networks

Paper • 2011.05074 • Published Nov 10, 2020

TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification

Paper • 2402.12991 • Published Feb 20, 2024 • 1