相关论文: BadEncoder: Backdoor Attacks to Pre-trained Encode…

This paper proposes a GeneraLIst encoder-Decoder (GLID) pre-training method for better handling various downstream computer vision tasks. While self-supervised pre-training approaches, e.g., Masked Autoencoder, have shown success in…

Self-supervised diffusion models learn high-quality visual representations via latent space denoising. However, their representation layer poses a distinct threat: unlike traditional attacks targeting generative outputs, its unconstrained…

Contrastive representation learning has been recently proved to be very efficient for self-supervised training. These methods have been successfully used to train encoders which perform comparably to supervised training on downstream…

Self-supervised learning (SSL) is increasingly attractive for pre-training encoders without requiring labeled data. Downstream tasks built on top of those pre-trained encoders can achieve nearly state-of-the-art performance. The pre-trained…

In this paper, we introduce a unique variant of the denoising Auto-Encoder and combine it with the perceptual loss to classify images in an unsupervised manner. The proposed method, called Pseudo Labelling, consists of first applying a…

Over the past decade, side-channels have proven to be significant and practical threats to modern computing systems. Recent attacks have all exploited the underlying shared hardware. While practical, mounting such a complicated attack is…

Semantic segmentation models are widely deployed in safety-critical applications such as autonomous driving, yet their vulnerability to backdoor attacks remains largely underexplored. Prior segmentation backdoor studies transfer threat…

In the light of recent analyses on privacy-concerning scene revelation from visual descriptors, we develop descriptors that conceal the input image content. In particular, we propose an adversarial learning framework for training visual…

Masked Image Modeling (MIM) has achieved significant success in the realm of self-supervised learning (SSL) for visual recognition. The image encoder pre-trained through MIM, involving the masking and subsequent reconstruction of input…

Building deep learning models on source code has found many successful software engineering applications, such as code search, code comment generation, bug detection, code migration, and so on. Current learning techniques, however, have a…

Weakly-supervised anomaly detection aims at learning an anomaly detector from a limited amount of labeled data and abundant unlabeled data. Recent works build deep neural networks for anomaly detection by discriminatively mapping the normal…

Dense retrieval requires high-quality text sequence embeddings to support effective search in the representation space. Autoencoder-based language models are appealing in dense retrieval as they train the encoder to output high-quality…

Recent work has demonstrated that neural networks are vulnerable to adversarial examples. To escape from the predicament, many works try to harden the model in various ways, in which adversarial training is an effective way which learns…

In the area of natural language processing, deep learning models are recently known to be vulnerable to various types of adversarial perturbations, but relatively few works are done on the defense side. Especially, there exists few…

Backdoor attacks pose a serious security threat to large language models (LLMs), which are increasingly deployed as general-purpose assistants in safety- and privacy-critical applications. Existing LLM backdoors rely primarily on…

With the development of deep learning (DL), DL-based code search models have achieved state-of-the-art performance and have been widely used by developers during software development. However, the security issue, e.g., recommending…

Recent years have witnessed the prosperous development of Graph Self-supervised Learning (GSSL), which enables to pre-train transferable foundation graph encoders. However, the easy-to-plug-in nature of such encoders makes them vulnerable…

The primary objective of this work is to present an alternative approach aimed at reducing the dependency on labeled data. Our proposed method involves utilizing autoencoder pre-training within a face image recognition task with two step…

Benefiting from its superior feature learning capabilities and efficiency, deep hashing has achieved remarkable success in large-scale image retrieval. Recent studies have demonstrated the vulnerability of deep hashing models to backdoor…

This work investigates three methods for calculating loss for autoencoder-based pretraining of image encoders: The commonly used reconstruction loss, the more recently introduced deep perceptual similarity loss, and a feature prediction…