arXiv:2509. 23689v2 Announce Type: replace Abstract: Model Merging (MM) has proven to be an effective alternative to multi-task learning, where several fine-tuned models are merged, without access to the tasks' training data, into one model that retains performance across different tasks.
arXiv:2506.12454v2 Announce Type: replace-cross Abstract: What fundamentally distinguishes an adversarial attack from a misclassification due to limited model expressivity or finite data? In this wor...
arXiv:2606. 07857v1 Announce Type: cross Abstract: The rise of edge-based machine learning has enabled distributed adaptation of language models across mobile and IoT devices, offering privacy preservation and real-time responsiveness.
The paper introduces Inverse Knowledge Distillation (IKD), an attack‑agnostic technique that enhances adversarial transferability by maximizing the discrepancy between benign and adversarial prediction distributions on a surrogate model. IKD employs a CE/KL‑equivalent soft‑label objective to push adversarial predictions away from a fixed benign anchor, leveraging Fisher‑sensitive surrogate directions. The authors provide theoretical analysis showing CE and KL induce identical gradients, derive a lower bound on Fisher‑subspace overlap, and demonstrate through extensive ImageNet experiments that IKD consistently improves black‑box attack performance across CNN, ViT, and defended models.
arXiv:2607. 03075v1 Announce Type: new Abstract: Safety-critical applications require classifiers that are both robust and reliable.
arXiv:2609.10002v1 Announce Type: new Abstract: Deepfake detectors remain vulnerable to transfer-based black-box attacks, in which adversarial examples are generated on a source surrogate model and t...
arXiv:2606. 11409v1 Announce Type: cross Abstract: Adversarial robustness evaluations of large language models (LLMs) typically report attack success rate (ASR) under fixed query budgets, implicitly treating all attacks as equally costly.
The paper introduces the Threat Conditional Network (TCN), a model that achieves robust performance across a continuous range of adversarial threat levels. TCN splits representation learning into a threat‑invariant backbone and a lightweight threat‑conditional adaptor, using Fourier‑based embeddings and channel‑wise affine modulation to condition on perturbation budgets. Experiments on CIFAR‑10, CIFAR‑100, and Tiny‑ImageNet demonstrate that TCN matches or exceeds ensembles of budget‑specialized models while adding only 4.6% more parameters, and it generalizes to unseen budgets and mismatched threat conditions.
Multi-modal Large Language Models (MLLMs) achieve strong performance on vision-language tasks, but incorporating visual inputs through a vision encoder (e. g.
arXiv:2608. 14594v1 Announce Type: new Abstract: Projected Gradient Descent (PGD) is widely used to evaluate adversarial robustness, typically via final adversarial accuracy, which does not capture model behaviour throughout the attack.
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. 01746v1 Announce Type: cross Abstract: Modern neural networks are highly susceptible to adversarial perturbations.