Understanding the Impact of LLM Watermarking on AI Agent Behavior
15 min
LLMs respond differently to harmful prompts when AI watermarking is used
4 min3
Harm Laundering in GPT Models: Evidence That Gender Discrimination Is Transformed Rather Than Reduced Across Safety-Trained Generations
Local Sparsity Enables Unsupervised LLM Safety Detection
Safety Beyond the Interface: Detecting Harm via Latent States in Large Language Models
1
K-Bench: a clinically calibrated benchmark for evaluating large language models in high-risk mental health conversations
Divide, Consult, Conquer: Capability Laundering Through Aligned LLMs
Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration
Structural Jailbreaks Generalize but Do Not Compound: A cross-provider and multilingual study of Involuntary In-Context Learning
1
Perturbation Probing: A New Diagnostic for the Fragility of LLM Safety
1