13 accepted papers
Advanced image generative models have led to concerns about malicious use, underscoring the necessity for generalizable detection methods. However, existing approaches tend to overfit to domain-specific forgery patterns, while overlooking complementary cues from different domains. Therefore, we intr
While text embeddings enable efficient semantic processing in LLMs, they remain vulnerable to inversion attacks that reconstruct sensitive original text. However, current defense methods typically treat text embeddings from the feature level independently, ignoring the exploitation of the mutual rel
Due to the ability to provide point clouds and Doppler velocity, as well as the adaptability in harsh weather conditions, 4D Radar has emerged as a new option for Simultaneous Localization and Mapping (SLAM). However, there is limited research on both robustness and computational efficiency, which a
This work asks: with abundant, unlabeled real faces, how to learn a robust and transferable facial representation that boosts various face security tasks with respect to generalization performance? We make the first attempt and propose a self-supervised pretraining framework to learn fundamental rep…
Deepfake technology has given rise to a spectrum of novel and compelling applications. Unfortunately, the widespread proliferation of high-fidelity fake videos has led to pervasive confusion and deception, shattering our faith that seeing is believing. One aspect that has been overlooked so far is t…
This research aims to accelerate the inference speed of large language models (LLMs) with billions of parameters. We propose Smart Parallel Auto-Correct dEcoding (SPACE), an approach designed for achieving lossless acceleration of LLMs. By integrating semi-autoregressive inference and speculative de…
This paper proposes a novel Deconvolution-enhanced data Augmentation method, DeAug, for ultrasonic-based speaker verification anti-spoofing systems to detect the liveness of voice sources in physical access, which aims to improve the performance of liveness detection on unseen devices where no data…
Unsupervised training of deep representations has demonstrated remarkable potentials in mitigating the prohibitive expenses on annotating labeled data recently. Among them is predicting transformations as a pretext task to self-train representations, which has shown great potentials for unsupervised…
This work presents a general deep learning framework for large-scale point clouds understanding without voxelizations, called FG-Conv, which achieves an accurate and real-time understanding of point clouds. Through our novel design combining feature level correlation mining and deformable convolutio…
In this paper, we aim at solving a distributed machine learning problem under Byzantine attacks. In the distributed system, a number of workers (termed as Byzantine workers) could send arbitrary messages to the master and bias the learning process, due to data corruptions, computation errors or mali…
In this paper, we aim at completing a large-scale low-rank matrix over a distributed network, which is subject to Byzantine attacks. We consider solving a nonconvex matrix factorization model with the distributed successive over-relaxation (SOR) method, where the distributed workers compute their pr…
In this paper, we present a solution for autonomous exploration and reconstruction in 3-D unknown environments without a priori knowledge of the environments. In our framework, a two-stage heuristic information gain-based next-view planning algorithm is performed to dynamically select and update can
This paper presents a tracking method which decouples tracking process into translation and scale estimation steps. A coarse estimation step in translation is implemented with particle filter first. Then, a two layers of correlation filters is proposed to robustly estimate object variation in transl…