Bitstream Collisions in Neural Image Compression via Adversarial Perturbations
Neural image compression (NIC) has emerged as a promising alternative to classical compression techniques, offering improved compression ratios. Despite its progress towards standardization and practical deployment, there has been minimal exploration into it's robustness and security. This study reveals an unexpected vulnerability in NIC - bitstream collisions - where semantically different images produce identical compressed bitstreams. Utilizing a novel whitebox adversarial attack algorithm, this paper demonstrates that adding carefully crafted perturbations to semantically different images can cause their compressed bitstreams to collide exactly. The collision vulnerability poses a threat to the practical usability of NIC, particularly in security-critical applications. The cause of the collision is analyzed, and a simple yet effective mitigation method is presented.
Code (1)
Tasks
Adversarial AttackImage CompressionSimilar Papers 제목 키워드 기반
Inevitable Encounters: Backdoor Attacks Involving Lossy Compression
Real-world backdoor attacks often require poisoned datasets to be stored and transmitted before being used to compromise deep learning systems. However, in the era of big data, the inevitable use of lossy compression pos…
Image CompressionApplying adversarial networks to increase the data efficiency and reliability of Self-Driving Cars
Convolutional Neural Networks (CNNs) are vulnerable to misclassifying images when small perturbations are present. With the increasing prevalence of CNNs in self-driving cars, it is vital to ensure these algorithms are r…
Generative Adversarial Networkimage-classificationImage ClassificationSelf-Driving CarsMALICE: Manipulation Attacks on Learned Image ComprEssion
Deep learning techniques have shown promising results in image compression, with competitive bitrate and image reconstruction quality from compressed latent. However, while image compression has progressed towards a high…
Image CompressionImage ReconstructionCompressing Weight-updates for Image Artifacts Removal Neural Networks
In this paper, we present a novel approach for fine-tuning a decoder-side neural network in the context of image compression, such that the weight-updates are better compressible. At encoder side, we fine-tune a pre-trai…
DecoderImage CompressionQuantizationTransferable Learned Image Compression-Resistant Adversarial Perturbations
Adversarial attacks can readily disrupt the image classification system, revealing the vulnerability of DNN-based recognition tasks. While existing adversarial perturbations are primarily applied to uncompressed images o…
Adversarial AttackAutonomous DrivingClassificationFace Recognition+3