Papers › Cross-modality Information Check for Detecting Jailbreaking in Multimodal Large Language Models

Cross-modality Information Check for Detecting Jailbreaking in Multimodal Large Language Models

31 Jul 2024arXiv:2407.21659archive 2025-07-28

Yue Xu, Xiuyuan Qi, Zhan Qin, Wenjie Wang

Multimodal Large Language Models (MLLMs) extend the capacity of LLMs to understand multimodal information comprehensively, achieving remarkable performance in many vision-centric tasks. Despite that, recent studies have shown that these models are susceptible to jailbreak attacks, which refer to an exploitative technique where malicious users can break the safety alignment of the target model and generate misleading and harmful answers. This potential threat is caused by both the inherent vulnerabilities of LLM and the larger attack scope introduced by vision input. To enhance the security of MLLMs against jailbreak attacks, researchers have developed various defense techniques. However, these methods either require modifications to the model's internal structure or demand significant computational resources during the inference phase. Multimodal information is a double-edged sword. While it increases the risk of attacks, it also provides additional data that can enhance safeguards. Inspired by this, we propose Cross-modality Information DEtectoR (CIDER), a plug-and-play jailbreaking detector designed to identify maliciously perturbed image inputs, utilizing the cross-modal similarity between harmful queries and adversarial images. CIDER is independent of the target MLLMs and requires less computation cost. Extensive experimental results demonstrate the effectiveness and efficiency of CIDER, as well as its transferability to both white-box and black-box MLLMs.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2407.21659")

Code

Syntology Ran 7 of 8 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 2 ran · fixture could not drive it; 5 ran with no contract checked.

By repository: official repository: 8 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

pandragonxiii/cider officialmentioned in papermentioned on GitHubpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

8 samples harvested; 7 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · fixture could not drive it
5ran
1unverified

Licence: 0 of the 8 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from pandragonxiii/cider. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

computeIoU pandragonxiii/cider/code/models/minigpt4/common/eval_utils.py official repository ran · fixture could not drive it Apache-2.0 (permissive) · f8e4c1c5aac977d6 · report
compute_cosine pandragonxiii/cider/code/threshold_selection.py official repository ran fingerprinted Apache-2.0 (permissive) · 8051b65c19e2efe3 · report
getAttMap pandragonxiii/cider/code/models/minigpt4/common/gradcam.py official repository ran · fixture could not drive it fingerprinted Apache-2.0 (permissive) · 7d214655954e2bc6 · report
log pandragonxiii/cider/code/utils.py official repository ran Apache-2.0 (permissive) · d4a0251a20b07a47 · report
main_process pandragonxiii/cider/code/models/minigpt4/common/dist_utils.py official repository ran Apache-2.0 (permissive) · 98589643273920ba · report
node_to_dict pandragonxiii/cider/code/models/minigpt4/common/config.py official repository ran Apache-2.0 (permissive) · 791c72070c0b1cfb · report
prepare_texts pandragonxiii/cider/code/models/minigpt4/common/eval_utils.py official repository ran Apache-2.0 (permissive) · 1acbd898be79b27e · report
download_cached_file pandragonxiii/cider/code/models/minigpt4/common/dist_utils.py official repository unverified Apache-2.0 (permissive) · 643539116e049080 · report

Tasks

Safety Alignment

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections