Author

Arash Vashagh

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

Detecting Adversarial Images through Response Profiles of Vision-Language Models

Adversarial perturbations can alter the predictions of frozen vision-language models (VLMs) while leaving their confidence and image--text similarity patterns seemingly plausible. We investigate whether we can identify adversarial inputs based on the broader way an image interacts with a collection of general semantic...

Arash Vashagh, R. Razavi-Far · 0 citations

#graph neural networks Oct 2026

GraphRectify: Graph-Based Transfer of Adversarial Example Detectors Across Neural Networks

Adversarial example detectors are often tied to the classifier backbone they were trained on, limiting reuse when the protected model is replaced or upgraded. Directly transferring such detectors across backbones is challenging because different networks generally produce incompatible internal representations. We propo...

Arash Vashagh, R. Razavi-Far · arXiv (Cornell University) · 0 citations

#machine learning Preprint Aug 2026

ChronosAttack: Adversarial Tool Scheduling Attacks on LLM Agents

This work introduces ChronosAttack, a delay-only scheduling attack that changes when authentic tool responses arrive without modifying, adding, removing, or accelerating them, to show that tool-response timing can itself form an attack surface in asynchronous LLM agents.

Arash Vashagh · 0 citations