← Search

Ben Nebgen

2 accepted papers

2025

LoRID: Low-Rank Iterative Diffusion for Adversarial Purification

AAAI 2025technical

This work presents an information-theoretic examination of diffusion-based purification methods, the state-of-the-art adversarial defenses that utilize diffusion models to remove malicious perturbations in adversarial examples. By theoretically characterizing the inherent purification errors associa…

Cited by 2Source ↗PDF ↗Scholar ↗
2025

Topological Signatures of Adversaries in Multimodal Alignments

ICML 2025poster

Multimodal Machine Learning systems, particularly those aligning text and image data like CLIP/BLIP models, have become increasingly prevalent, yet remain susceptible to adversarial attacks. While substantial research has addressed adversarial robustness in unimodal contexts, defense strategies for…

Cited by 0Source ↗PDF ↗Scholar ↗