paper-with-me

Papers

TrojVLM: Backdoor Attack Against Vision Language Models

2024-09-28 · Weimin Lyu, Lu Pang, Tengfei Ma, Haibin Ling, Chao Chen

The emergence of Vision Language Models (VLMs) is a significant advancement in integrating computer vision with Large Language Models (LLMs) to produce detailed text descriptions based on visual inputs, yet it introduces new security vulnerabilities. Unlike prior work that centered on single modalities or classification tasks, this study introduces TrojVLM, the first exploration of backdoor attacks aimed at VLMs engaged in complex image-to-text generation. Specifically, TrojVLM inserts predetermined target text into output text when encountering poisoned images. Moreover, a novel semantic preserving loss is proposed to ensure the semantic integrity of the original image content. Our evaluation on image captioning and visual question answering (VQA) tasks confirms the effectiveness of TrojVLM in maintaining original semantic content while triggering specific target text outputs. This study not only uncovers a critical security risk in VLMs and image-to-text generation but also sets a foundation for future research on securing multimodal models against such sophisticated threats.

📄 PDF Abstract BibTeX arXiv:2409.19232

Code (0)

등록된 구현이 없습니다.

Tasks

Backdoor AttackImage CaptioningImage to textQuestion AnsweringText GenerationVisual Question AnsweringVisual Question Answering (VQA)

Similar Papers 제목 키워드 기반

On Certifying Robustness against Backdoor Attacks via Randomized Smoothing

2020-02-26 · Binghui Wang, Xiaoyu Cao, Jinyuan Jia, Neil Zhenqiang Gong

Backdoor attack is a severe security threat to deep neural networks (DNNs). We envision that, like adversarial examples, there will be a cat-and-mouse game for backdoor attacks, i.e., new empirical defenses are developed…

Backdoor Attack

Backdooring Vision-Language Models with Out-Of-Distribution Data

2024-10-02 · Weimin Lyu, Jiachen Yao, Saumya Gupta, Lu Pang 외

The emergence of Vision-Language Models (VLMs) represents a significant advancement in integrating computer vision with Large Language Models (LLMs) to generate detailed text descriptions from visual inputs. Despite thei…

Image CaptioningImage to textQuestion AnsweringVisual Question Answering+1

BadNL: Backdoor Attacks Against NLP Models

2021-06-18 · ICML Workshop AML 2021 7 · Xiaoyi Chen, Ahmed Salem, Michael Backes, Shiqing Ma 외

Deep Neural Networks (DNNs) have progressed rapidly during the past decade. Meanwhile, DNN models have been shown to be vulnerable to various security and privacy attacks. One such attack that has attracted a great deal …

Backdoor AttackSentenceSentiment Analysis

Robust Contrastive Language-Image Pre-training against Data Poisoning and Backdoor Attacks

2023-03-13 · Wenhan Yang, Jingdong Gao, Baharan Mirzasoleiman

Contrastive vision-language representation learning has achieved state-of-the-art performance for zero-shot classification, by learning from millions of image-caption pairs crawled from the internet. However, the massive…

Backdoor AttackData PoisoningRepresentation Learningzero-shot-classification+1

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations

2025-02-06 · Yihe Zhou, Tao Ni, Wei-Bin Lee, Qingchuan Zhao

Large Language Models (LLMs) have achieved significantly advanced capabilities in understanding and generating human language text, which have gained increasing popularity over recent years. Apart from their state-of-the…