相关论文: Adversarial Sparse Teacher: Defense Against Distil…

Despite the remarkable performance and generalization levels of deep learning models in a wide range of artificial intelligence tasks, it has been demonstrated that these models can be easily fooled by the addition of imperceptible yet…

Multimodal sarcasm detection is challenging, especially in low-resource settings where subtle image-text contradictions are hard to learn due to scarce annotated data, which hinders the model's performance. Parameter-efficient fine-tuning…

With the wide application of knowledge distillation between an ImageNet pre-trained teacher model and a learnable student model, unsupervised anomaly detection has witnessed a significant achievement in the past few years. The success of…

Knowledge distillation (KD) is a technique used to transfer knowledge from an overparameterized teacher network to a less-parameterized student network, thereby minimizing the incurred performance loss. KD methods can be categorized into…

State-of-the-art machine learning models are vulnerable to data poisoning attacks whose purpose is to undermine the integrity of the model. However, the current literature on data poisoning attacks is mainly focused on ad hoc techniques…

Exemplar-free class-incremental learning (EFCIL) aims to retain old knowledge acquired in the previous task while learning new classes, without storing the previous images due to storage constraints or privacy concerns. In EFCIL, the…

Currently, deep learning models are easily exposed to data leakage risks. As a distributed model, Split Learning thus emerged as a solution to address this issue. The model is splitted to avoid data uploading to the server and reduce…

Frontier models that generate extended reasoning traces inadvertently produce rich token sequences that can facilitate model distillation. Recognizing this vulnerability, model owners may seek sampling strategies that limit the…

The countermeasure (CM) model is developed to protect ASV systems from spoof attacks and prevent resulting personal information leakage in Automatic Speaker Verification (ASV) system. Based on practicality and security considerations, the…

The performance of autoregressive models on natural language generation tasks has dramatically improved due to the adoption of deep, self-attentive architectures. However, these gains have come at the cost of hindering inference speed,…

Neural networks are known to be susceptible to adversarial samples: small variations of natural examples crafted to deliberately mislead the models. While they can be easily generated using gradient-based techniques in digital and physical…

Class-incremental continual learning addresses catastrophic forgetting by enabling classification models to preserve knowledge of previously learned classes while acquiring new ones. However, the vulnerability of the models against…

Knowledge Distillation (KD) aims to transfer knowledge from a large teacher model to a smaller student model. While contrastive learning has shown promise in self-supervised learning by creating discriminative representations, its…

Knowledge distillation (KD) has been widely used in teacher-student training, with applications to model compression in resource-constrained deep learning. Current works mainly focus on preserving the accuracy of the teacher model. However,…

Advances in self-distillation have shown that when knowledge is distilled from a teacher to a student using the same deep learning (DL) architecture, the student performance can surpass the teacher particularly when the network is…

Industrial defect detection is commonly addressed with anomaly detection (AD) methods where no or only incomplete data of potentially occurring defects is available. This work discovers previously unknown problems of student-teacher…

Adversarial extraction attacks constitute an insidious threat against Deep Learning (DL) models in-which an adversary aims to steal the architecture, parameters, and hyper-parameters of a targeted DL model. Existing extraction attack…

Knowledge distillation (KD) is a common approach to compress a teacher model to reduce its inference cost and memory footprint, by training a smaller student model. However, in the context of autoregressive language models (LMs), we…

Frontier commercial generative models face a growing threat from distillation, whereby a distiller harvests generated responses and trains a competing model of its own at drastically lower cost. Existing defenses either rely on modifying…

To ensure that the data collected from human subjects is entrusted with a secret, rival labels are introduced to conceal the information provided by the participants on purpose. The corresponding learning task can be formulated as a noisy…