Suklav Ghosh

suklav's activity

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

authored 2 papers 4 months ago

Universal Adversarial Suffixes for Language Models Using Reinforcement Learning with Calibrated Reward

Paper • 2512.08131 • Published Dec 9, 2025

Universal Adversarial Suffixes Using Calibrated Gumbel-Softmax Relaxation

Paper • 2512.08123 • Published Dec 9, 2025

authored a paper 6 months ago

C-LEAD: Contrastive Learning for Enhanced Adversarial Defense

Paper • 2510.27249 • Published Oct 31, 2025 • 1