Search Results for author:
Found 39 papers, 16 papers with code
AI-Compass: A Comprehensive and Effective Multi-module Testing Tool for AI Systems
Extensive experiments demonstrate that \tool is the state-of-the-art tool for a comprehensive assessment of the robustness and trustworthiness of AI systems.
Reconstruction of Differentially Private Text Sanitization via Large Language Models
Differential privacy (DP) is the de facto privacy standard against privacy leakage attacks, including many recently discovered ones against large language models (LLMs).
Edge Unlearning is Not "on Edge"! An Adaptive Exact Unlearning System on Resource-Constrained Devices
Another approach, exact unlearning, tackles this issue by discarding the data and retraining the model from scratch, but at the cost of considerable computational and memory resources.
Rethinking the Threat and Accessibility of Adversarial Attacks against Face Recognition Systems
In contrast to widely studied sophisticated attacks in the field, we propose an effective yet easy-to-launch physical adversarial attack, named AdvColor, against black-box face recognition pipelines in the physical world.
QUEEN: Query Unlearning against Model Extraction
To limit the potential threat, QUEEN has sensitivity measurement and outputs perturbation that prevents the adversary from training a piracy model with high performance.
On Security Weaknesses and Vulnerabilities in Deep Learning Systems
In this work, we specifically look into deep learning (DL) framework and perform the first systematic study of vulnerabilities in DL systems through a comprehensive analysis of identified vulnerabilities from Common Vulnerabilities and Exposures (CVE) and open-source DL tools, including TensorFlow, Caffe, OpenCV, Keras, and PyTorch.
Provably Unlearnable Data Examples
To safeguard both data privacy and IP-related domain knowledge, efforts have been undertaken to render shared data unlearnable for unauthorized models in the wild.
LocalStyleFool: Regional Video Style Transfer Attack Using Segment Anything Model
Benefiting from the popularity and scalably usability of Segment Anything Model (SAM), we first extract different regions according to semantic information and then track them through the video stream to maintain the temporal consistency.
Near-Optimal Algorithms for Constrained k-Center Clustering with Instance-level Background Knowledge
Center-based clustering has attracted significant research interest from both theory and practice.
Reinforcement Unlearning
Machine unlearning refers to the process of mitigating the influence of specific training data on machine learning models based on removal requests from data owners.
MFABA: A More Faithful and Accelerated Boundary-based Attribution Method for Deep Neural Networks
To better understand the output of deep neural networks (DNN), attribution based methods have been an important approach for model interpretability, which assign a score for each input dimension to indicate its importance towards the model outcome.
LogoStyleFool: Vitiating Video Recognition Systems via Logo Style Transfer
We separate the attack into three stages: style reference selection, reinforcement-learning-based logo style transfer, and perturbation optimization.
GraphGuard: Detecting and Counteracting Training Data Misuse in Graph Neural Networks
These limitations call for an effective and comprehensive solution that detects and mitigates data misuse without requiring exact training data while respecting the proprietary nature of such data.
Watch Out! Simple Horizontal Class Backdoor Can Trivially Evade Defense
In VCB attacks, any sample from a class activates the implanted backdoor when the secret trigger is present.
RAI4IoE: Responsible AI for Enabling the Internet of Energy
This paper plans to develop an Equitable and Responsible AI framework with enabling techniques and algorithms for the Internet of Energy (IoE), in short, RAI4IoE.
VeriDIP: Verifying Ownership of Deep Neural Networks through Privacy Leakage Fingerprints
(2) We introduce a novel approach using less private samples to enhance the performance of ownership testing.
Copyright Protection and Accountability of Generative AI:Attack, Watermarking and Attribution
toxic images) and models (resp.
The "Beatrix'' Resurrections: Robust Backdoor Detection via Gram Matrices
However, recent advanced backdoor attacks show that this assumption is no longer valid in dynamic backdoors where the triggers vary from input to input, thereby defeating the existing defenses.
M^4I: Multi-modal Models Membership Inference
To achieve this, we propose Multi-modal Models Membership Inference (M^4I) with two attack methods to infer the membership status, named metric-based (MB) M^4I and feature-based (FB) M^4I, respectively.
StyleFool: Fooling Video Classification Systems via Style Transfer
In this paper, we focus on unrestricted perturbations and propose StyleFool, a black-box video adversarial attack via style transfer to fool the video classification system.
PublicCheck: Public Integrity Verification for Services of Run-time Deep Models
Existing integrity verification approaches for deep models are designed for private verification (i. e., assuming the service provider is honest, with white-box access to model parameters).
Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations
In this paper, we propose a novel and practical mechanism which enables the service provider to verify whether a suspect model is stolen from the victim model via model extraction attacks.
PPA: Preference Profiling Attack Against Federated Learning
By observing a user model's gradient sensitivity to a class, PPA can profile the sample proportion of the class in the user's local dataset, and thus the user's preference of the class is exposed.
TnT Attacks! Universal Naturalistic Adversarial Patches Against Deep Neural Network Systems
Now, an adversary can arm themselves with a patch that is naturalistic, less malicious-looking, physically realizable, highly effective achieving high attack success rates, and universal.
Mate! Are You Really Aware? An Explainability-Guided Testing Framework for Robustness of Malware Detectors
We find that (i) commercial antivirus engines are vulnerable to AMM-guided test cases; (ii) the ability of a manipulated malware generated using one detector to evade detection by another detector (i. e., transferability) depends on the overlap of features with large AMM values between the different detectors; and (iii) AMM values effectively measure the fragility of features (i. e., capability of feature-space manipulation to flip the prediction results) and explain the robustness of malware detectors facing evasion attacks.
Quantization Backdoors to Deep Learning Commercial Frameworks
This work reveals that the standard quantization toolkits can be abused to activate a backdoor.
Data Hiding with Deep Learning: A Survey Unifying Digital Watermarking and Steganography
The advancement of secure communication and identity verification fields has significantly increased through the use of deep learning techniques for data hiding.
Hidden Backdoors in Human-Centric Language Models
We are able to demonstrate the adversary's high success rate of attacks, while maintaining functionality for regular users, with triggers inconspicuous by the human administrators.
Oriole: Thwarting Privacy against Trustworthy Deep Learning Models
Deep Neural Networks have achieved unprecedented success in the field of face recognition such that any individual can crawl the data of others from the Internet without their explicit permission for the purpose of training high-precision face recognition models, creating a serious violation of privacy.
Delayed Rewards Calibration via Reward Empirical Sufficiency
Therefore, a purify-trained classifier is designed to obtain the distribution and generate the calibrated rewards.
Deep Learning Backdoors
The trigger can take a plethora of forms, including a special object present in the image (e. g., a yellow pad), a shape filled with custom textures (e. g., logos with particular colors) or even image-wide stylizations with special filters (e. g., images altered by Nashville or Gotham filters).
With Great Dispersion Comes Greater Resilience: Efficient Poisoning Attacks and Defenses for Linear Regression Models
To this end, we analyze and develop a new poisoning attack algorithm.
Invisible Backdoor Attacks on Deep Neural Networks via Steganography and Regularization
We show that the proposed invisible backdoors can be fairly effective across various DNN models as well as four datasets MNIST, CIFAR-10, CIFAR-100, and GTSRB, by measuring their attack success rates for the adversary, functionality for the normal users, and invisibility scores for the administrators.
Differentially Private Data Generative Models
We conjecture that the key to defend against the model inversion and GAN-based attacks is not due to differential privacy but the perturbation of training data.
Secure Deep Learning Engineering: A Software Quality Assurance Perspective
Over the past decades, deep learning (DL) systems have achieved tremendous success and gained great popularity in various applications, such as intelligent machines, image processing, speech processing, and medical diagnostics.
DeepHunter: Hunting Deep Neural Network Defects via Coverage-Guided Fuzzing
In company with the data explosion over the past decade, deep neural network (DNN) based software has experienced unprecedented leap and is becoming the key driving force of many novel industrial applications, including many safety-critical scenarios such as autonomous driving.
Combinatorial Testing for Deep Learning Systems
Deep learning (DL) has achieved remarkable progress over the past decade and been widely applied to many safety-critical applications.
DeepMutation: Mutation Testing of Deep Learning Systems
To do this, by sharing the same spirit of mutation testing in traditional software, we first define a set of source-level mutation operators to inject faults to the source of DL (i. e., training data and training programs).
Software Engineering
DeepGauge: Multi-Granularity Testing Criteria for Deep Learning Systems
Deep learning (DL) defines a new data-driven programming paradigm that constructs the internal system logic of a crafted neuron network through a set of training data.
