Mark Vero

Watch your steps: Dormant Adversarial Behaviors that Activate upon LLM Finetuning

Fewer Weights, More Problems: A Practical Attack on LLM Pruning

Pay Attention to the Triggers: Constructing Backdoors That Survive Distillation

AutoBaxBench: Bootstrapping Code Security Benchmarking

Mind the Gap: A Practical Attack on GGUF Quantization

Black-Box Adversarial Attacks on LLM-Based Code Completion

Language Models are Advanced Anonymizers

Black-Box Adversarial Attacks on LLM-Based Code Completion

BaxBench: Can LLMs Generate Correct and Secure Backends?