1

Adversarial Hubness in Multi-Modal Retrieval
Hubness is a phenomenon in high-dimensional vector spaces where a single point from the natural distribution is unusually close to many …
PDF Cite Code
Adversarial Decoding: Generating Readable Documents for Adversarial Objectives

Recent work showed that retrieval based on embedding similarity (e.g., for retrieval-augmented generation) is vulnerable to poisoning: …

PDF Cite Code
Self-interpreting Adversarial Images

We introduce a new type of indirect, cross-modal injection attacks against visual language models that enable creation of …

PDF Cite Code Appendix USENIX Website
Adversarial Illusions in Multi-Modal Embeddings

Multi-modal embeddings encode texts, images, thermal images, sounds, and videos into a single embedding space, aligning representations …

PDF Cite Code Slides Video Appendix USENIX Website
SoK: Pitfalls in Evaluating Black-Box Attacks
Numerous works study black-box attacks on image classifiers. However, these works make different assumptions on the adversary’s …
PDF Cite Code Poster Post