Search Results for author:
Found 31 papers, 21 papers with code
COLEP: Certifiably Robust Learning-Reasoning Conformal Prediction via Probabilistic Circuits
In this work, we propose a certifiably robust learning-reasoning conformal prediction framework (COLEP) via probabilistic circuits, which comprise a data-driven learning component that trains statistical models to learn different semantic concepts, and a reasoning component that encodes knowledge and characterizes the relationships among the trained models for logic reasoning.
InfiCoder-Eval: Systematically Evaluating the Question-Answering Capabilities of Code Large Language Models
Large Language Models for understanding and generating code (code LLMs) have witnessed tremendous progress in recent years.
COMMIT: Certifying Robustness of Multi-Sensor Fusion Systems against Semantic Attacks
In this work, we propose the first robustness certification framework COMMIT certify robustness of multi-sensor fusion systems against semantic attacks.
Pixel-wise Smoothing for Certified Robustness against Camera Motion Perturbations
The current certification process for assessing robustness is costly and time-consuming due to the extensive number of image projections required for Monte Carlo sampling in the 3D camera motion space.
Reliability Assurance for Deep Neural Network Architectures Against Numerical Defects
To assure high reliability against numerical defects, in this paper, we propose the RANUM approach including novel techniques for three reliability assurance tasks: detection of potential numerical defects, confirmation of potential-defect feasibility, and suggestion of defect fixes.
Fairness in Federated Learning via Core-Stability
Nonetheless, the heterogeneity nature of distributed data makes it challenging to define and ensure fairness among local agents.
LOT: Layer-wise Orthogonal Training on Improving $\ell_2$ Certified Robustness
On the other hand, as existing works show that semi-supervised training helps improve empirical robustness, we aim to bridge the gap and prove that semi-supervised learning also improves the certified robustness of Lipschitz-bounded models.
Robustness Certification of Visual Perception Models via Camera Motion Smoothing
To this end, we study the robustness of the visual perception model under camera motion perturbations to investigate the influence of camera motion on robotic perception.
CARE: Certifiably Robust Learning with Reasoning via Variational Inference
In particular, we propose a certifiably robust learning with reasoning pipeline (CARE), which consists of a learning component and a reasoning component.
General Cutting Planes for Bound-Propagation-Based Neural Network Verification
Our generalized bound propagation method, GCP-CROWN, opens up the opportunity to apply general cutting plane methods for neural network verification while benefiting from the efficiency and GPU acceleration of bound propagation methods.
FOCUS: Fairness via Agent-Awareness for Federated Learning on Heterogeneous Data
However, due to the heterogeneous nature of local data, it is challenging to optimize or even define fairness of the trained global model for the agents.
Double Sampling Randomized Smoothing
To overcome this hurdle, we propose a Double Sampling Randomized Smoothing (DSRS) framework, which exploits the sampled probability from an additional smoothing distribution to tighten the robustness certification of the previous smoothed classifier.
Can pruning improve certified robustness of neural networks?
Given the fact that neural networks are often over-parameterized, one effective way to reduce such computational overhead is neural network pruning, by removing redundant parameters from trained neural networks.
Certifying Some Distributional Fairness with Subpopulation Decomposition
In this paper, we first formulate the certified fairness of an ML model trained on a given data distribution as an optimization problem based on the model performance loss bound on a fairness constrained distribution, which is within bounded distributional distance with the training distribution.
COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks
We leverage COPA to certify three RL environments trained with different algorithms and conclude: (1) The proposed robust aggregation protocols such as temporal aggregation can significantly improve the certifications; (2) Our certification for both per-state action stability and cumulative reward bound are efficient and tight; (3) The certification for different training algorithms and environments are different, implying their intrinsic robustness properties.
SapientML: Synthesizing Machine Learning Pipelines by Learning from Human-Written Solutions
In this work we propose an AutoML technique SapientML, that can learn from a corpus of existing datasets and their human-written pipelines, and efficiently generate a high-quality pipeline for a predictive task on a new dataset.
Certifying Out-of-Domain Generalization for Blackbox Functions
As a result, the wider application of these techniques is currently limited by its scalability and flexibility -- these techniques often do not scale to large-scale datasets with modern deep neural networks or cannot handle loss functions which may be non-smooth such as the 0-1 loss.
TPC: Transformation-Specific Smoothing for Point Cloud Models
In this paper, we propose a transformation-specific smoothing framework TPC, which provides tight and scalable robustness guarantees for point cloud models against semantic transformation attacks.
CARD: Certifiably Robust Machine Learning Pipeline via Domain Knowledge Integration
In particular, we express the domain knowledge as first-order logic rules and embed these logic rules in a probabilistic graphical model.
On the Certified Robustness for Ensemble Models and Beyond
Thus, to explore the conditions that guarantee to provide certifiably robust ensemble ML models, we first prove that diversified gradient and large confidence margin are sufficient and necessary conditions for certifiably robust ensemble models under the model-smoothness assumption.
CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing
We then develop a local smoothing algorithm for policies derived from Q-functions to guarantee the robustness of actions taken along the trajectory; we also develop a global smoothing algorithm for certifying the lower bound of a finite-horizon cumulative reward, as well as a novel local smoothing algorithm to perform adaptive search in order to obtain tighter reward certification.
Progressive-Scale Boundary Blackbox Attack via Projective Gradient Estimation
In this paper, we show that such efficiency highly depends on the scale at which the attack is applied, and attacking at the optimal scale significantly improves the efficiency.
TRS: Transferability Reduced Ensemble via Promoting Gradient Diversity and Model Smoothness
To answer these questions, in this work we first theoretically analyze and outline sufficient conditions for adversarial transferability between models; then propose a practical algorithm to reduce the transferability between base models within an ensemble to improve its robustness.
TRS: Transferability Reduced Ensemble via Encouraging Gradient Diversity and Model Smoothness
To answer these questions, in this work we first theoretically analyze and outline sufficient conditions for adversarial transferability between models; then propose a practical algorithm to reduce the transferability between base models within an ensemble to improve its robustness.
Nonlinear Projection Based Gradient Estimation for Query Efficient Blackbox Attacks
We aim to bridge the gap between the two by investigating how to efficiently estimate gradient based on a projected low-dimensional space.
On the Limitations of Denoising Strategies as Adversarial Defenses
Surprisingly, our experimental results show that even if most of the perturbations in each dimension is eliminated, it is still difficult to obtain satisfactory robustness.
SoK: Certified Robustness for Deep Neural Networks
Great advances in deep neural networks (DNNs) have led to state-of-the-art performance on a wide range of tasks.
Improving Certified Robustness via Statistical Learning with Logical Reasoning
Intensive algorithmic efforts have been made to enable the rapid improvements of certificated robustness for complex ML models recently.
TSS: Transformation-Specific Smoothing for Robustness Certification
Moreover, to the best of our knowledge, TSS is the first approach that achieves nontrivial certified robustness on the large-scale ImageNet dataset.
Influence-Directed Explanations for Deep Convolutional Networks
We study the problem of explaining a rich class of behavioral properties of deep neural networks.
Case Study: Explaining Diabetic Retinopathy Detection Deep CNNs via Integrated Gradients
In this report, we applied integrated gradients to explaining a neural network for diabetic retinopathy detection.
