Gradient Mirage is a defense for large language model split learning that disrupts the assumption that exposed gradients faithfully reflect the client’s full-label training objective, thereby thwarting gradient matching attacks. It introduces inconsistencies across objective, direction, and scale by using selective autoregressive supervision, scale blinding, and directional privatization with a von Mises-Fisher mechanism. The method preserves utility through dual-track backpropagation and bottom-gradient recovery, achieving a stronger privacy‑utility trade‑off in experiments.
arXiv:2607. 02903v1 Announce Type: cross Abstract: Explainability is central to building trustworthy AI, yet explanation interfaces can inadvertently provide adversaries with an expanded privacy-related attack surfaces.
The paper investigates the impact of label‑flipping attacks on distributed machine learning, where an adversary can only flip a limited number of training labels. It formalizes the attack as a per‑round constrained optimization problem, derives a greedy label‑selection rule for logistic regression, and shows that this rule is provably optimal under mean aggregation. Experiments demonstrate that optimized label flipping can significantly degrade model accuracy, outperforming random flips, and that the attack transfers to other robust aggregators such as coordinate‑wise median and trimmed mean.
arXiv:2606. 17110v1 Announce Type: cross Abstract: Large Language Models are increasingly trained on proprietary or sensitive data, from private healthcare and financial records to user conversations containing secrets.
arXiv:2507. 01752v4 Announce Type: replace-cross Abstract: Gradient-based optimization is the workhorse of deep learning, offering efficient and scalable training via backpropagation.
arXiv:2511. 13749v2 Announce Type: replace Abstract: Deep neural networks are known to be vulnerable to adversarial perturbations, which are small, carefully crafted inputs that lead to incorrect predictions.
arXiv:2606. 12251v1 Announce Type: cross Abstract: Gradient-based adversarial attacks remain a dominant threat to deep neural networks (DNNs), as they exploit gradient information to efficiently optimize adversarial perturbations.
arXiv:2607. 28959v1 Announce Type: cross Abstract: Adversarial training is one of the most effective defenses against adversarial attacks, yet the computational cost remains prohibitive at modern scales, especially for large language models (LLMs).
arXiv:2606. 10571v1 Announce Type: cross Abstract: Adversarial examples reveal vulnerabilities in Vision-Language Pre-training (VLP) models and provide insights for improving robustness.
arXiv:2606. 14078v1 Announce Type: cross Abstract: Existing studies reveal that current backdoor defenses exhibit limited robustness and often fail against specific types of attacks.
arXiv:2601. 14300v4 Announce Type: replace Abstract: Hard-label black-box attacks, relying solely on top-1 predictions, represent one of the most challenging yet practically threat models.
arXiv:2607. 27940v1 Announce Type: new Abstract: Federated fine-tuning of large language models (LLMs) enables collaborative training without exposing raw data.
arXiv:2607. 12354v1 Announce Type: new Abstract: In this paper, we challenge the prevailing view that information dependency (including rote memorization) drives training data exposure to image reconstruction attacks.