Jonathan Petit

This paper analyzes existing watermarking schemes for autoregressive image generators and demonstrates that they are vulnerable to various removal and forgery attacks, suggesting they are unreliable for content detection and dataset filtering.

The paper argues that the standard Attack Success Rate (ASR) metric for LLM jailbreaks is unstable and systematically inflated, proposing new frameworks to account for stochasticity in both evaluation and generation.

The paper introduces MIRAGE, a framework that systematically discovers semantic attacks on online HD map construction by finding plausible environmental variations that bypass standard adversarial defenses, demonstrating attacks that remove or inject critical road boundaries.

This paper demonstrates that reasoning-enabled Vision-Language-Action (VLA) models for autonomous driving are highly vulnerable to realistic input perturbations, significantly compromising both reasoning accuracy and driving safety.