SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2308.10741 · 2023

On the Adversarial Robustness of Multi-Modal Foundation Models

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 4 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
copy not recorded — 4 of 4
FunctionStatusWhere it lives
compute_acc Ran this paper's copy was not recorded; identical code first harvested from chs20/robustvlm
pointer only · get_code("1f2be2216dc3f7cd")
compute_loss Ran this paper's copy was not recorded; identical code first harvested from chs20/robustvlm
pointer only · get_code("75f68885e2ff2684")
get_query_set Ran this paper's copy was not recorded; identical code first harvested from chs20/robustvlm
pointer only · get_code("68d0f41190a26308")
get_random_indices Ran this paper's copy was not recorded; identical code first harvested from chs20/robustvlm
pointer only · get_code("63ec736a72a6cb74")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Multi-modal foundation models combining vision and language models such as Flamingo or GPT-4 have recently gained enormous interest. Alignment of foundation models is used to prevent models from providing toxic or harmful output. While malicious users have successfully tried to jailbreak foundation models, an equally important question is if honest users could be harmed by malicious third-party content. In this paper we show that imperceivable attacks on images in order to change the caption output of a multi-modal foundation model can be used by malicious content providers to harm honest users e.g. by guiding them to malicious websites or broadcast fake information. This indicates that countermeasures to adversarial attacks should be used by any deployed multi-modal foundation model.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2308.10741")
get_code_for_paper("2308.10741")
have("2308.10741")

Connect an agent — have() is free.