Picture for Niloofar Mireshghallah

Niloofar Mireshghallah

Alpaca against Vicuna: Using LLMs to Uncover Memorization of LLMs

Add code
Mar 05, 2024
Figure 1 for Alpaca against Vicuna: Using LLMs to Uncover Memorization of LLMs
Figure 2 for Alpaca against Vicuna: Using LLMs to Uncover Memorization of LLMs
Figure 3 for Alpaca against Vicuna: Using LLMs to Uncover Memorization of LLMs
Figure 4 for Alpaca against Vicuna: Using LLMs to Uncover Memorization of LLMs
Viaarxiv icon

Do Membership Inference Attacks Work on Large Language Models?

Add code
Feb 12, 2024
Viaarxiv icon

A Roadmap to Pluralistic Alignment

Add code
Feb 07, 2024
Viaarxiv icon

A Block Metropolis-Hastings Sampler for Controllable Energy-based Text Generation

Add code
Dec 07, 2023
Viaarxiv icon

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

Add code
Oct 27, 2023
Figure 1 for Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
Figure 2 for Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
Figure 3 for Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
Figure 4 for Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
Viaarxiv icon

Misusing Tools in Large Language Models With Visual Adversarial Examples

Add code
Oct 04, 2023
Figure 1 for Misusing Tools in Large Language Models With Visual Adversarial Examples
Figure 2 for Misusing Tools in Large Language Models With Visual Adversarial Examples
Figure 3 for Misusing Tools in Large Language Models With Visual Adversarial Examples
Figure 4 for Misusing Tools in Large Language Models With Visual Adversarial Examples
Viaarxiv icon