Search Results for author:
Found 41 papers, 20 papers with code
Neural Network Control Policy Verification With Persistent Adversarial Perturbation
In this paper, we show how to combine recent works on static neural network certification tools with robust control theory to certify a neural network policy in a control loop.
Crafting Large Language Models for Enhanced Interpretability
We introduce the Concept Bottleneck Large Language Model (CB-LLM), a pioneering approach to creating inherently interpretable Large Language Models (LLMs).
Breaking the Barrier: Enhanced Utility and Robustness in Smoothed DRL Agents
However, a notable gap exists in the performance of current smoothed DRL agents, often characterized by significantly low clean rewards and weak robustness.
AND: Audio Network Dissection for Interpreting Deep Acoustic Models
Neuron-level interpretations aim to explain network behaviors and properties by investigating neurons responsive to specific perceptual or structural input patterns.
Linear Explanations for Individual Neurons
In recent years many methods have been developed to understand the internal workings of neural networks, often by describing the function of individual neurons in the model.
Provably Robust Conformal Prediction with Improved Efficiency
To address these limitations, we first propose a novel framework called RSCP+ to provide provable robustness guarantee in evaluation, which fixes the issues in the original RSCP method.
Describe-and-Dissect: Interpreting Neurons in Vision Networks with Language Models
In this paper, we propose Describe-and-Dissect (DnD), a novel method to describe the roles of hidden neurons in vision networks.
One step closer to unbiased aleatoric uncertainty estimation
Neural networks are powerful tools in various applications, and quantifying their uncertainty is crucial for reliable decision-making.
Corrupting Neuron Explanations of Deep Visual Features
The inability of DNNs to explain their black-box behavior has led to a recent surge of explainability methods.
Promoting Robustness of Randomized Smoothing: Two Cost-Effective Approaches
The second approach introduces a post-processing method EsbRS which greatly improves the robustness certificate based on building model ensembles.
The Importance of Prompt Tuning for Automated Neuron Explanations
Recent advances have greatly increased the capabilities of large language models (LLMs), but our understanding of the models and their safety has not progressed as fast.
Prediction without Preclusion: Recourse Verification with Reachable Sets
As a result, they can assign predictions that are fixed $-$ meaning that individuals who are denied loans and interviews are, in fact, precluded from access to credit and employment.
Concept-Monitor: Understanding DNN training through individual neurons
In this work, we propose a general framework called Concept-Monitor to help demystify the black-box DNN training processes automatically using a novel unified embedding space and concept diversity metric.
Label-Free Concept Bottleneck Models
Motivated by these challenges, we propose Label-free CBM which is a novel framework to transform any neural network into an interpretable CBM without labeled concept data, while retaining a high accuracy.
Constructive Assimilation: Boosting Contrastive Learning Performance through View Generation Strategies
Recently, several attempts have been made to replace such domain-specific, human-designed transformations with generated views that are learned.
ConCerNet: A Contrastive Learning Based Framework for Automated Conservation Law Discovery and Trustworthy Dynamical System Prediction
Deep neural networks (DNN) have shown great capacity of modeling a dynamical system; nevertheless, they usually do not obey physics constraints such as conservation laws.
Certified Interpretability Robustness for Class Activation Mapping
Interpreting machine learning models is challenging but crucial for ensuring the safety of deep networks in autonomous driving systems.
Learning Sample Reweighting for Accuracy and Adversarial Robustness
There has been great interest in enhancing the robustness of neural network classifiers to defend against adversarial perturbations through adversarial training, while balancing the trade-off between robust accuracy and standard accuracy.
CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks
Finally CLIP-Dissect is computationally efficient and can label all neurons from five layers of ResNet-50 in just 4 minutes, which is more than 10 times faster than existing methods.
Attacking c-MARL More Effectively: A Data Driven Approach
In recent years, a proliferation of methods were developed for cooperative multi-agent reinforcement learning (c-MARL).
On the Equivalence between Neural Network and Support Vector Machine
Therefore, in this work, we propose to establish the equivalence between NN and SVM, and specifically, the infinitely wide NN trained by soft margin loss and the standard soft margin SVM with NTK trained by subgradient descent.
Efficient Certification for Probabilistic Robustness
Recent developments on the robustness of neural networks have primarily emphasized the notion of worst-case adversarial robustness in both verification and robust training.
Learning Sample Reweighting for Adversarial Robustness
There has been great interest in enhancing the robustness of neural network classifiers to defend against adversarial perturbations through adversarial training, while balancing the trade-off between robust accuracy and standard accuracy.
Tactics on Refining Decision Boundary for Improving Certification-based Robust Training
In verification-based robust training, existing methods utilize relaxation based methods to bound the worst case performance of neural networks given certain perturbation.
Adversarially Robust Conformal Prediction
By combining conformal prediction with randomized smoothing, our proposed method forms a prediction set with finite-sample coverage guarantee that holds for any data distribution with $\ell_2$-norm bounded adversarial noise, generated by any adversarial attack algorithm.
Evaluating Robustness of Cooperative MARL
In recent years, a proliferation of methods were developed for multi-agent reinforcement learning (MARL).
On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning
Despite the generalization power of the meta-model, it remains elusive that how adversarial robustness can be maintained by MAML in few-shot learning.
Fast Training of Provably Robust Neural Networks by SingleProp
Recent works have developed several methods of defending neural networks against adversarial attacks with certified guarantees.
Higher-Order Certification for Randomized Smoothing
We also provide a framework that generalizes the calculation for certification using higher-order information.
Robust Deep Reinforcement Learning through Adversarial Loss
To address this issue, we propose RADIAL-RL, a principled framework to train reinforcement learning agents with improved robustness against $l_p$-norm bounded adversarial attacks.
Toward Evaluating Robustness of Deep Reinforcement Learning with Continuous Control
Deep reinforcement learning has achieved great success in many previously difficult reinforcement learning tasks, yet recent studies show that deep RL agents are also unavoidably susceptible to adversarial perturbations, similar to deep neural networks in classification tasks.
Verification of Neural Network Control Policy Under Persistent Adversarial Perturbation
In this paper, we show how to combine recent works on neural network certification tools (which are mainly used in static settings such as image classification) with robust control theory to certify a neural network policy in a control loop.
Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective
Graph neural networks (GNNs) which apply the deep neural networks to graph data have achieved significant performance for the task of semi-supervised node classification.
POPQORN: Quantifying Robustness of Recurrent Neural Networks
The vulnerability to adversarial attacks has been a critical issue for deep neural networks.
Finite-Sum Smooth Optimization with SARAH
The total complexity (measured as the total number of gradient computations) of a stochastic first-order optimization algorithm that finds a first-order stationary point of a finite-sum smooth nonconvex objective function $F(w)=\frac{1}{n} \sum_{i=1}^n f_i(w)$ has been proven to be at least $\Omega(\sqrt{n}/\epsilon)$ for $n \leq \mathcal{O}(\epsilon^{-2})$ where $\epsilon$ denotes the attained accuracy $\mathbb{E}[ \|\nabla F(\tilde{w})\|^2] \leq \epsilon$ for the outputted approximation $\tilde{w}$ (Fang et al., 2018).
PROVEN: Certifying Robustness of Neural Networks with a Probabilistic Approach
With deep neural networks providing state-of-the-art machine learning models for numerous machine learning tasks, quantifying the robustness of these models has become an important area of research.
CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks
This motivates us to propose a general and efficient framework, CNN-Cert, that is capable of certifying robustness on general convolutional neural networks.
Efficient Neural Network Robustness Certification with General Activation Functions
Finding minimum distortion of adversarial examples and thus certifying robustness in neural network classifiers for given data points is known to be a challenging problem.
On Extensions of CLEVER: A Neural Network Robustness Evaluation Algorithm
We apply extreme value theory on the new formal robustness guarantee and the estimated robustness is called second-order CLEVER score.
Towards Fast Computation of Certified Robustness for ReLU Networks
Verifying the robustness property of a general Rectified Linear Unit (ReLU) network is an NP-complete problem [Katz, Barrett, Dill, Julian and Kochenderfer CAV17].
Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach
Our analysis yields a novel robustness metric called CLEVER, which is short for Cross Lipschitz Extreme Value for nEtwork Robustness.
