GPT-Red: Automated Red Teaming via Self-Play at Scale
Paper • 2607.26115 • Published • 8
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
GPT-Red: Automated Red Teaming via Self-Play at Scale
Reasoning Models Struggle to Control their Chains of Thought
taesiri
submitted a
paper to Daily Papers 17 days ago
ajh-oai
published a
dataset 25 days ago
unixpickle
authored a
paper almost 2 years ago
ljcc
authored 14
papers almost 2 years ago
DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training
Paper • 2310.02025 • Published • 1
Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning
Paper • 2310.08782 • Published
To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now
Paper • 2310.11868 • Published
SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation
Paper • 2310.12508 • Published • 1
UnlearnCanvas: A Stylized Image Dataset to Benchmark Machine Unlearning for Diffusion Models
Paper • 2402.11846 • Published • 1
SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning
Paper • 2404.18239 • Published
Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
Paper • 2405.15234 • Published • 1
ChainQueen: A Real-Time Differentiable Physical Simulator for Soft Robotics
Paper • 1810.01054 • Published
Model Sparsity Can Simplify Machine Unlearning
Paper • 2304.04934 • Published
Towards Universal Mesh Movement Networks
Paper • 2407.00382 • Published
Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning
Paper • 2403.07362 • Published • 1
Can Adversarial Examples Be Parsed to Reveal Victim Model Information?
Paper • 2303.07474 • Published
Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
Paper • 2410.07163 • Published • 1
WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models
Paper • 2410.17509 • Published
karan1149
authored 2
papers over 2 years ago
karan1149
authored a
paper almost 3 years ago