Picture for Ashwinee Panda

Ashwinee Panda

Privacy Auditing of Large Language Models

Add code
Mar 09, 2025
Viaarxiv icon

Continual Pre-training of MoEs: How robust is your router?

Add code
Mar 06, 2025
Viaarxiv icon

Gemstones: A Model Suite for Multi-Faceted Scaling Laws

Add code
Feb 07, 2025
Figure 1 for Gemstones: A Model Suite for Multi-Faceted Scaling Laws
Figure 2 for Gemstones: A Model Suite for Multi-Faceted Scaling Laws
Figure 3 for Gemstones: A Model Suite for Multi-Faceted Scaling Laws
Figure 4 for Gemstones: A Model Suite for Multi-Faceted Scaling Laws
Viaarxiv icon

Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models

Add code
Dec 09, 2024
Figure 1 for Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models
Figure 2 for Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models
Figure 3 for Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models
Figure 4 for Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models
Viaarxiv icon

Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs

Add code
Jun 25, 2024
Figure 1 for Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs
Figure 2 for Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs
Figure 3 for Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs
Figure 4 for Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs
Viaarxiv icon

Safety Alignment Should Be Made More Than Just a Few Tokens Deep

Add code
Jun 10, 2024
Figure 1 for Safety Alignment Should Be Made More Than Just a Few Tokens Deep
Figure 2 for Safety Alignment Should Be Made More Than Just a Few Tokens Deep
Figure 3 for Safety Alignment Should Be Made More Than Just a Few Tokens Deep
Figure 4 for Safety Alignment Should Be Made More Than Just a Few Tokens Deep
Viaarxiv icon

Teach LLMs to Phish: Stealing Private Information from Language Models

Add code
Mar 01, 2024
Figure 1 for Teach LLMs to Phish: Stealing Private Information from Language Models
Figure 2 for Teach LLMs to Phish: Stealing Private Information from Language Models
Figure 3 for Teach LLMs to Phish: Stealing Private Information from Language Models
Figure 4 for Teach LLMs to Phish: Stealing Private Information from Language Models
Viaarxiv icon

Private Fine-tuning of Large Language Models with Zeroth-order Optimization

Add code
Jan 09, 2024
Figure 1 for Private Fine-tuning of Large Language Models with Zeroth-order Optimization
Figure 2 for Private Fine-tuning of Large Language Models with Zeroth-order Optimization
Figure 3 for Private Fine-tuning of Large Language Models with Zeroth-order Optimization
Figure 4 for Private Fine-tuning of Large Language Models with Zeroth-order Optimization
Viaarxiv icon

Visual Adversarial Examples Jailbreak Large Language Models

Add code
Jun 22, 2023
Figure 1 for Visual Adversarial Examples Jailbreak Large Language Models
Figure 2 for Visual Adversarial Examples Jailbreak Large Language Models
Figure 3 for Visual Adversarial Examples Jailbreak Large Language Models
Figure 4 for Visual Adversarial Examples Jailbreak Large Language Models
Viaarxiv icon

Differentially Private Image Classification by Learning Priors from Random Processes

Add code
Jun 08, 2023
Figure 1 for Differentially Private Image Classification by Learning Priors from Random Processes
Figure 2 for Differentially Private Image Classification by Learning Priors from Random Processes
Figure 3 for Differentially Private Image Classification by Learning Priors from Random Processes
Figure 4 for Differentially Private Image Classification by Learning Priors from Random Processes
Viaarxiv icon