Logo image
Back
Poster: The Art of Deception: Crafting Chimera Images for Covert and Robust Semantic Poisoning Attacks
Conference proceeding   Open access

Poster: The Art of Deception: Crafting Chimera Images for Covert and Robust Semantic Poisoning Attacks

Lin Li, Youyang Qu, Jiayang Ao, Ming Ding, Chao Chen and Jun Zhang
Proceedings of the 2025 ACM SIGSAC Conference on Computer and Communications Security, pp.4833-4835
ACM Conferences
CCS '25: ACM SIGSAC Conference on Computer and Communications Security (Taipei, Taiwan, 13/10/2025–17/10/2025)
22/11/2025
DOI: https://doi.org/10.1145/3719027.3760742
Appears in  Recent Faculty of Science and Engineering Publications
url
Poster: The Art of DeceptionView
Published (Version of record) Open Free to Read

Related links

Metrics

1 Record Views

Abstract

poisoning attacks image classification large language models
With the exponential surge in media data volumes and their growing intrinsic value, the landscape has become increasingly susceptible to persistent and strategically designed data poisoning attacks targeting these valuable assets. In this work, we propose a novel approach leveraging generative AI techniques to craft covert and robust poisonous data samples, referred to as Chimera Images. These images seamlessly blend visual features from two target classes to generate hybrid objects that preserve appearance fidelity. These ''normal'' samples with correct labels can subtly distort the model's decision boundary without raising suspicion. Extensive experimental results on CIFAR-10 and Flowers datasets demonstrate that the proposed method i) reduces the accuracy of the targeted class, ii) maintains the performance of other classes, and iii) exhibits immunity to state-of-the-art defence strategies. We also explore the usage of generative AI content detection as a defence mechanism, demonstrating that the recently discovered snapshot technique is ineffective against the AI-generated poisonous Chimera samples.

Details

Logo image