arXiv:2608.30105v1 Announce Type: cross Abstract: Deep learning-based side-channel analysis has historically focused on single-byte targets and manually cropped traces, which risks discarding exploit...
The paper investigates privacy risks in Vision Transformer (ViT) split‑inference systems that use token reduction and token shuffling to lower computation and communication costs. It shows that even after token shuffling, transmitted token embeddings still contain enough positional information for a new attack, the Spatially Aligned Reconstruction Attack (SARA), which predicts token positions, restores spatial layout, fills missing embeddings with a masked autoencoder, and reconstructs the input image. While token reduction offers stronger protection, significant leakage remains when retained tokens preserve semantic and positional cues, and the authors propose a lightweight edge‑side defense that removes positional embeddings and adapts transformer blocks via knowledge distillation to reduce SARA’s effectiveness without harming downstream accuracy.
arXiv:2606. 04317v1 Announce Type: cross Abstract: Deep neural networks are increasingly deployed across heterogeneous and partially untrusted environments, where models are distributed through cloud storage, CI/CD pipelines, containerized services, and edge execution platforms.
arXiv:2304. 03388v2 Announce Type: replace Abstract: Deep Neural Networks (DNNs) have become ubiquitous for their ability to solve problems across various domains, including computer vision, natural language processing, and speech recognition.
Vision Transformers (ViTs) are increasingly used in split-inference systems, where edge devices transmit intermediate token representations to a remote cloud. In this setting, token reduction lowers c...
FSPGD introduces a feature-space black-box attack for semantic segmentation that targets intermediate representations rather than just output logits. The method uses a dual loss: an external loss to disrupt cross-model feature alignment and an internal loss to reduce consistency among same-class instances. Experiments on Pascal VOC 2012 and Cityscapes show that FSPGD outperforms existing logit-level and segmentation-specific attacks across CNN and Transformer backbones, and its adversarial examples improve robustness when used for training.
The paper introduces Imperfect Restoration Poisoning (IRP), a new data poisoning technique that maintains high image quality while effectively disrupting both supervised and self‑supervised learning models. It builds on a theoretical critique of the existing Convolution-based Unlearnable Dataset (CUDA) method, revealing CUDA’s sub‑optimal gradients and class‑bias strategy. Extensive experiments demonstrate IRP’s superiority over eight baseline attacks and its resilience against five defense methods.
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: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 introduces DistScan, a backdoor detection framework for object detection models that identifies malicious behavior by detecting shifts in the pre‑NMS prediction class distribution relative to training class frequencies. DistScan operates on clean validation data, requiring no access to model weights, trigger knowledge, or additional training, and it aggregates intermediate predictions to flag backdoored models. Experiments on MS‑COCO and PASCAL VOC across two architectures and three scene‑level attack scenarios show that DistScan outperforms existing methods, improving average detection accuracy by 27.32 percentage points over the best baseline.
arXiv:2608. 04477v1 Announce Type: cross Abstract: Cloud-based language model services routinely process prompts containing sensitive information.
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.