Search Results for author:
Found 31 papers, 11 papers with code
Generate to Adapt: Resolution Adaption Network for Surveillance Face Recognition
Although deep learning techniques have largely improved face recognition, unconstrained surveillance face recognition (FR) is still an unsolved challenge, due to the limited training data and the gap of domain distribution.
Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models
To address this issue, we propose Gaussian Shading, a diffusion model watermarking technique that is both performance-lossless and training-free, while serving the dual purpose of copyright protection and tracing of offending content.
Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMs
Large Language Models (LLMs), used in creative writing, code generation, and translation, generate text based on input sequences but are vulnerable to jailbreak attacks, where crafted prompts induce harmful outputs.
Domain Bridge: Generative model-based domain forensic for black-box models
In forensic investigations of machine learning models, techniques that determine a model's data domain play an essential role, with prior work relying on large-scale corpora like ImageNet to approximate the target model's domain.
INViT: A Generalizable Routing Problem Solver with Invariant Nested View Transformer
Recently, deep reinforcement learning has shown promising results for learning fast heuristics to solve routing problems.
Improving Adversarial Transferability by Stable Diffusion
Various techniques have emerged to enhance the transferability of adversarial attacks for the black-box scenario.
Skywork: A More Open Bilingual Foundation Model
In this technical report, we present Skywork-13B, a family of large language models (LLMs) trained on a corpus of over 3. 2 trillion tokens drawn from both English and Chinese texts.
Effective Long-Context Scaling of Foundation Models
We also examine the impact of various design choices in the pretraining process, including the data mix and the training curriculum of sequence lengths -- our ablation experiments suggest that having abundant long texts in the pretrain dataset is not the key to achieving strong performance, and we empirically verify that long context continual pretraining is more efficient and similarly effective compared to pretraining from scratch with long sequences.
Adaptive Attractors: A Defense Strategy against ML Adversarial Collusion Attacks
This induces different adversarial regions in different copies, making adversarial samples generated on one copy not replicable on others.
Watermarking Text Generated by Black-Box Language Models
To allow third-parties to autonomously inject watermarks into generated text, we develop a watermarking framework for black-box language model usage scenarios.
Mask to reconstruct: Cooperative Semantics Completion for Video-text Retrieval
Specifically, after applying attention-based video masking to generate high-informed and low-informed masks, we propose Informed Semantics Completion to recover masked semantics information.
Finding Meaningful Distributions of ML Black-boxes under Forensic Investigation
Our goal is to select a set of samples from the corpus for the given model.
Multi-objective Generative Design of Three-Dimensional Composite Materials
Composite materials with 3D architectures are desirable in a variety of applications for the capability of tailoring their properties to meet multiple functional requirements.
Representation Deficiency in Masked Language Modeling
In this work, we offer a new perspective on the consequence of such a discrepancy: We demonstrate empirically and theoretically that MLM pretraining allocates some model dimensions exclusively for representing $\texttt{[MASK]}$ tokens, resulting in a representation deficiency for real tokens and limiting the pretrained model's expressiveness when it is adapted to downstream data without $\texttt{[MASK]}$ tokens.
Tracing the Origin of Adversarial Attack for Forensic Investigation and Deterrence
In this paper, we take the role of investigators who want to trace the attack and identify the source, that is, the particular model which the adversarial examples are generated from.
Improved Adaptive Algorithm for Scalable Active Learning with Weak Labeler
We design a novel algorithmic template, Weak Labeler Active Cover (WL-AC), that is able to robustly leverage the lower quality weak labelers to reduce the query complexity while retaining the desired level of accuracy.
PIMoG: An Effective Screen-shooting Noise-Layer Simulation for Deep-Learning-Based Watermarking Network
In order to design an effective noise layer for screen-shooting robustness, we propose new insight in this paper, that is, it is not necessary to quantitatively simulate the overall procedure in the screen-shooting noise layer, only including the most influenced distortions is enough to generate an effective noise layer with strong robustness.
BayesFormer: Transformer with Uncertainty Estimation
Transformer has become ubiquitous due to its dominant performance in various NLP and image processing tasks.
Conditional Variational Autoencoder with Balanced Pre-training for Generative Adversarial Networks
The two recent methods, Balancing GAN (BAGAN) and improved BAGAN (BAGAN-GP), are proposed as an augmentation tool to handle this problem and restore the balance to the data.
Reducing Target Group Bias in Hate Speech Detectors
The ubiquity of offensive and hateful content on online fora necessitates the need for automatic solutions that detect such content competently across target groups.
Mitigating Adversarial Attacks by Distributing Different Copies to Different Users
We point out that by distributing different copies of the model to different buyers, we can mitigate the attack such that adversarial samples found on one copy would not work on another copy.
Speech Pattern based Black-box Model Watermarking for Automatic Speech Recognition
As an effective method for intellectual property (IP) protection, model watermarking technology has been applied on a wide variety of deep neural networks (DNN), including speech classification models.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
MLFW: A Database for Face Recognition on Masked Faces
As more and more people begin to wear masks due to current COVID-19 pandemic, existing face recognition systems may encounter severe performance degradation when recognizing masked faces.
Ranked #1 on
Face Recognition
on MLFW
MBRS : Enhancing Robustness of DNN-based Watermarking by Mini-Batch of Real and Simulated JPEG Compression
To address such limitations, we proposed a novel end-to-end training architecture, which utilizes Mini-Batch of Real and Simulated JPEG compression (MBRS) to enhance the JPEG robustness.
Exploring Structure Consistency for Deep Model Watermarking
However, little attention has been devoted to the protection of DNNs in image processing tasks.
CLIP2Video: Mastering Video-Text Retrieval via Image CLIP
We present CLIP2Video network to transfer the image-language pre-training model to video-text retrieval in an end-to-end manner.
Ranked #11 on
Video Retrieval
on VATEX
(using extra training data)
Entailment as Few-Shot Learner
Large pre-trained language models (LMs) have demonstrated remarkable ability as few-shot learners.
Ranked #1 on
Topic Classification
on OS
Micro-Estimates of Wealth for all Low- and Middle-Income Countries
Many critical policy decisions, from strategic investments to the allocation of humanitarian aid, rely on data about the geographic distribution of wealth and poverty.
Linformer: Self-Attention with Linear Complexity
Large transformer models have shown extraordinary success in achieving state-of-the-art results in many natural language processing applications.
Model Watermarking for Image Processing Networks
In this way, when the attacker trains one surrogate model by using the input-output pairs of the target model, the hidden watermark will be learned and extracted afterward.
DUP-Net: Denoiser and Upsampler Network for 3D Adversarial Point Clouds Defense
We propose a Denoiser and UPsampler Network (DUP-Net) structure as defenses for 3D adversarial point cloud classification, where the two modules reconstruct surface smoothness by dropping or adding points.
