Promptcare: Prompt copyright protection by watermark injection and verification
Large language models (LLMs) have witnessed a meteoric rise in popularity among the
general public users over the past few months, facilitating diverse downstream tasks with …
general public users over the past few months, facilitating diverse downstream tasks with …
Towards reliable and efficient backdoor trigger inversion via decoupling benign features
Recent studies revealed that using third-party models may lead to backdoor threats, where
adversaries can maliciously manipulate model predictions based on backdoors implanted …
adversaries can maliciously manipulate model predictions based on backdoors implanted …
Towards faithful xai evaluation via generalization-limited backdoor watermark
Saliency-based representation visualization (SRV)($ eg $, Grad-CAM) is one of the most
classical and widely adopted explainable artificial intelligence (XAI) methods for its simplicity …
classical and widely adopted explainable artificial intelligence (XAI) methods for its simplicity …
Defending against data-free model extraction by distributionally robust defensive training
Abstract Data-Free Model Extraction (DFME) aims to clone a black-box model without
knowing its original training data distribution, making it much easier for attackers to steal …
knowing its original training data distribution, making it much easier for attackers to steal …
Towards stealthy backdoor attacks against speech recognition via elements of sound
Deep neural networks (DNNs) have been widely and successfully adopted and deployed in
various applications of speech recognition. Recently, a few works revealed that these …
various applications of speech recognition. Recently, a few works revealed that these …
Defenses in adversarial machine learning: A survey
Adversarial phenomenon has been widely observed in machine learning (ML) systems,
especially in those using deep neural networks, describing that ML systems may produce …
especially in those using deep neural networks, describing that ML systems may produce …
Pointncbw: Towards dataset ownership verification for point clouds via negative clean-label backdoor watermark
Recently, point clouds have been widely used in computer vision, whereas their collection is
time-consuming and expensive. As such, point cloud datasets are the valuable intellectual …
time-consuming and expensive. As such, point cloud datasets are the valuable intellectual …
A general framework for data-use auditing of ml models
Auditing the use of data in training machine-learning (ML) models is an increasingly
pressing challenge, as myriad ML practitioners routinely leverage the effort of content …
pressing challenge, as myriad ML practitioners routinely leverage the effort of content …
Towards reliable verification of unauthorized data usage in personalized text-to-image diffusion models
Text-to-image diffusion models are pushing the boundaries of what generative AI can
achieve in our lives. Beyond their ability to generate general images, new personalization …
achieve in our lives. Beyond their ability to generate general images, new personalization …
M-to-N Backdoor Paradigm: A Multi-Trigger and Multi-Target Attack to Deep Learning Models
Deep neural networks (DNNs) are vulnerable to backdoor attacks, where a backdoored
model behaves normally with clean inputs but exhibits attacker-specified behaviors upon the …
model behaves normally with clean inputs but exhibits attacker-specified behaviors upon the …