Vision Transformers (ViTs) increasingly rely on input-adaptive inference, such as token pruning and early halting, to meet energy and latency budgets. This survey examines a recent class of adversarial efficiency degradation attacks that target these mechanisms to increase computation without necessarily degrading accuracy.
arXiv:2609.39134v1 Announce Type: new Abstract: Visual-token compression improves the efficiency of large vision-language models, but can expose failures that full-token evaluation misses. We study a...
The paper examines how preprocessing defenses, commonly used to protect edge vision systems, perform on depthwise‑separable CNNs versus residual architectures. Six preprocessing methods were tested against adversarial attacks, revealing that depthwise‑separable models consistently fail to recover from perturbations while residual models show partial recovery. Interestingly, the same preprocessing that hinders clean predictions leaves adversarial predictions largely intact, offering a measurable detection signal, and the study also finds that typical image‑quality metrics do not reliably indicate defense success.
The paper demonstrates that undervolting GPUs during CNN training introduces stochastic faults that act as implicit regularization, improving adversarial robustness while reducing power consumption. Experiments on LeNet, VGG-6, and MobileNetV3 trained on MNIST and CIFAR-10 show that undervolted models consistently outperform nominal-voltage models in both standard and adversarial training regimes. The approach offers a hardware-level defense that requires no algorithmic changes and yields significant energy savings due to the quadratic relationship between dynamic power and supply voltage.
The paper evaluates six preprocessing defenses against adversarial attacks on depthwise‑separable CNNs, the dominant architecture in edge vision systems, and finds that these defenses consistently fail to recover clean predictions for such models, whereas a residual architecture shows partial recovery. The study reveals that the same preprocessing steps that break clean predictions leave adversarial predictions largely intact, creating a measurable asymmetry that can be exploited for detection without retraining or architectural changes. It also demonstrates that common image quality metrics do not reliably indicate defense effectiveness, highlighting a methodological gap in current evaluation practices.
arXiv:2505. 03646v5 Announce Type: replace-cross Abstract: Adversarial robustness of deep autoencoders (AEs) has received less attention than that of discriminative models, although their compressed latent representations induce ill-conditioned mappings that can amplify small input perturbations and destabilize reconstructions.
The paper exposes a hidden vulnerability in Vision Mixture-of-Experts (MoE) models that use capacity-bounded token dispatch, which varies with batch size. It presents a three-phase backdoor attack: injecting a backdoor into an early MoE layer, training a neutralizer in a deeper layer to suppress it under normal capacity, and then adjusting the batch-adaptive capacity factor so that the neutralizer is disabled when large batches are used at deployment. Experiments on V-MoE and Swin-MoE show high attack success rates (76‑87%) for large batches while keeping the attack dormant and undetected during small-batch audits, evading several state‑of‑the‑art defenses.
arXiv:2607. 07922v1 Announce Type: cross Abstract: Vision Transformers (ViTs) remain vulnerable to localized adversarial attacks, e.
arXiv:2608. 15113v1 Announce Type: cross Abstract: Learned image compression (LIC) has demonstrated remarkable rate-distortion (RD) performance in benign settings.
arXiv:2606. 02267v1 Announce Type: new Abstract: The vulnerability of deep neural networks to adversarial examples poses a significant challenge for real-world deployment.
arXiv:2607. 00174v1 Announce Type: cross Abstract: We present a black-box model-stealing attack that recovers private vision-tokenizer configurations of deployed vision-language models (VLMs), including the visual patch size and input preprocessing pipeline.
arXiv:2506. 03933v2 Announce Type: replace-cross Abstract: Vision Language Models (VLMs) have shown remarkable capabilities in multimodal understanding, yet their susceptibility to adversarial perturbations poses a significant threat to their reliability in real-world applications.
The paper introduces RIBA, a reinforcement‑learning inspired black‑box adversarial attack that generates perturbations for neural networks with fewer queries than existing methods. RIBA achieves a 25.4% reduction in median queries on ResNet‑18/Cifar10 and a 22.5% reduction on Vit‑B/16/ImageNet, while matching white‑box attack performance on an adversarially trained model.