mlsanityData to 14 Oct 2026

Technical Report for ICML 2024 TiFA Workshop MLLM Attack Challenge: Suffix Injection and Projected Gradient Descent Can Easily Fool An MLLM

arXiv 2412.15614 ↗First posted 20 Dec 2024cs.CR cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

This technical report introduces our top-ranked solution that employs two approaches, ie suffix injection and projected gradient descent (PGD) , to address the TiFA workshop MLLM attack challenge. Specifically, we first append the text from an incorrectly labeled option (pseudo-labeled) to the original query as a suffix. Using this modified query, our second approach applies the PGD method to add imperceptible perturbations to the image. Combining these two techniques enables successful attacks on the LLaVA 1.5 model.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 6 of its 11 references that are in the map. First posted on arXiv 20 Dec 2024.

Builds on

6 of 11 references.

References · 6

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 3,104
  4. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  5. 2024Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Modelscited by 167
  6. 2024Assessment of Multimodal Large Language Models in Alignment with Human Valuescited by 36

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Attacking Large Language Models with Projected Gradient Descent
  2. 2025Adversarial Suffix Filtering: a Defense Pipeline for LLMs
  3. 2026Adversarial Attacks Against MLLMs via Progressive Resolution Processing and Adaptive Feature Alignment
  4. 2025Enhanced MLLM Black-Box Jailbreaking Attacks and Defenses
  5. 2024Improved Generation of Adversarial Examples Against Safety-aligned LLMs
  6. 2025Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency
  7. 2025Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025
  8. 2025WebInject: Prompt Injection Attack to Web Agents