Search Results for author:
Found 35 papers, 13 papers with code
Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks
Recently, increasing attention has been drawn to the internal mechanisms of convolutional neural networks, and the reason why the network makes specific decisions.
Interpreting Interpretations: Organizing Attribution Methods by Criteria
In this work we expand the foundationsof human-understandable concepts with which attributionscan be interpreted beyond "importance" and its visualization; we incorporate the logical concepts of necessity andsufficiency, and the concept of proportionality.
Towards Frequency-Based Explanation for Robust CNN
We show that the vulnerability of the model against tiny distortions is a result of the model is relying on the high-frequency features, the target features of the adversarial (black and white-box) attackers, to make the prediction.
Smoothed Geometry for Robust Attribution
Feature attributions are a popular tool for explaining the behavior of Deep Neural Networks (DNNs), but have recently been shown to be vulnerable to attacks that produce divergent explanations for nearby inputs.
Reconstructing Actions To Explain Deep Reinforcement Learning
Feature attribution has been a foundational building block for explaining the input feature importance in supervised learning with Deep Neural Network (DNNs), but face new challenges when applied to deep Reinforcement Learning (RL). We propose a new approach to explaining deep RL actions by defining a class of \emph{action reconstruction} functions that mimic the behavior of a network in deep RL.
ABSTRACTING INFLUENCE PATHS FOR EXPLAINING (CONTEXTUALIZATION OF) BERT MODELS
While “attention is all you need” may be proving true, we do not yet know why: attention-based transformer models such as BERT are superior but how they contextualize information even for simple grammatical rules such as subject-verb number agreement(SVA) is uncertain.
Influence Patterns for Explaining Information Flow in BERT
While attention is all you need may be proving true, we do not know why: attention-based transformer models such as BERT are superior but how information flows from input tokens to output predictions are unclear.
Globally-Robust Neural Networks
We show that widely-used architectures can be easily adapted to this objective by incorporating efficient global Lipschitz bounds into the network, yielding certifiably-robust models by construction that achieve state-of-the-art verifiable accuracy.
Robust Models Are More Interpretable Because Attributions Look Normal
Recent work has found that adversarially-robust deep networks used for image classification are more interpretable: their feature attributions tend to be sharper, and are more concentrated on the objects associated with the image's ground-truth class.
Consistent Counterfactuals for Deep Models
Counterfactual examples are one of the most commonly-cited methods for explaining the predictions of machine learning models in key areas such as finance and medical diagnosis.
Context-Aware Compilation of DNN Training Pipelines across Edge and Cloud
Experimental results show that our system not only adapts well to, but also draws on the varying contexts, delivering a practical and efficient solution to edge-cloud model training.
Ranked #2 on
Recommendation Systems
on MovieLens 1M
(Precision metric)
On Optimizing Shared-ride Mobility Services with Walking Legs
Shared-ride mobility services that incorporate traveler walking legs aim to reduce vehicle-kilometers-travelled (VKT), vehicle-hours-travelled (VHT), request rejections, fleet size, or some combination of these factors, compared to door-to-door (D2D) shared-ride services.
Risk-Averse No-Regret Learning in Online Convex Games
To address this challenge, we propose a new online risk-averse learning algorithm that relies on one-point zeroth-order estimation of the CVaR gradients computed using CVaR values that are estimated by appropriately sampling the cost functions.
Faithful Explanations for Deep Graph Models
Second, our analytical and empirical results demonstrate that feature attribution methods cannot capture the nonlinear effect of edge features, while existing subgraph explanation methods are not faithful.
On the Perils of Cascading Robust Classifiers
We present \emph{cascade attack} (CasA), an adversarial attack against cascading ensembles, and show that: (1) there exists an adversarial input for up to 88\% of the samples where the ensemble claims to be certifiably robust and accurate; and (2) the accuracy of a cascading ensemble under our attack is as low as 11\% when it claims to be certifiably robust and accurate on 97\% of the test set.
A Zeroth-Order Momentum Method for Risk-Averse Online Convex Games
Specifically, the agents use the conditional value at risk (CVaR) as a risk measure and rely on bandit feedback in the form of the cost values of the selected actions at every episode to estimate their CVaR values and update their actions.
Improving Robust Generalization by Direct PAC-Bayesian Bound Minimization
Recent research in robust optimization has shown an overfitting-like phenomenon in which models trained against adversarial attacks exhibit higher robustness on the training set compared to the test set.
Learning Modulo Theories
Recent techniques that integrate \emph{solver layers} into Deep Neural Networks (DNNs) have shown promise in bridging a long-standing gap between inductive learning and symbolic reasoning techniques.
Unlocking Deterministic Robustness Certification on ImageNet
We show that fast ways of bounding the Lipschitz constant for conventional ResNets are loose, and show how to address this by designing a new residual block, leading to the \emph{Linear ResNet} (LiResNet) architecture.
Streaming Kernel PCA Algorithm With Small Space
The kernel method, which is commonly used in learning algorithms such as Support Vector Machines (SVMs), has also been applied in PCA algorithms.
Policy Evaluation in Distributional LQR
Distributional reinforcement learning (DRL) enhances the understanding of the effects of the randomness in the environment by letting agents learn the distribution of a random return, rather than its expected value as in standard RL.
Universal and Transferable Adversarial Attacks on Aligned Language Models
Specifically, our approach finds a suffix that, when attached to a wide range of queries for an LLM to produce objectionable content, aims to maximize the probability that the model produces an affirmative response (rather than refusing to answer).
Automatic Answerability Evaluation for Question Generation
This work proposes PMAN (Prompting-based Metric on ANswerability), a novel automatic evaluation metric to assess whether the generated questions are answerable by the reference answers for the QG tasks.
Representation Engineering: A Top-Down Approach to AI Transparency
In this paper, we identify and characterize the emerging area of representation engineering (RepE), an approach to enhancing the transparency of AI systems that draws on insights from cognitive neuroscience.
Ranked #3 on
Question Answering
on TruthfulQA
A Recipe for Improved Certifiable Robustness: Capacity and Data
A key challenge, supported both theoretically and empirically, is that robustness demands greater network capacity and more data than standard training.
Is Certifying $\ell_p$ Robustness Still Worthwhile?
There are three layers to this inquiry, which we address in this paper: (1) why do we care about robustness research?
Can LLMs Follow Simple Rules?
As Large Language Models (LLMs) are deployed with increasing real-world responsibilities, it is important to be able to specify and constrain the behavior of these systems in a reliable manner.
Transfer Attacks and Defenses for Large Language Models on Coding Tasks
They improve upon previous neural network models of code, such as code2seq or seq2seq, that already demonstrated competitive results when performing tasks such as code summarization and identifying code vulnerabilities.
Local Convergence of Approximate Newton Method for Two Layer Nonlinear Regression
Our main results involve analyzing the convergence properties of an approximate Newton method used to minimize the regularized training loss.
Semantic Complete Scene Forecasting from a 4D Dynamic Point Cloud Sequence
To tackle this challenging problem, we properly model the synergetic relationship between future forecasting and semantic scene completion through a novel network named SCSFNet.
GenH2R: Learning Generalizable Human-to-Robot Handover via Scalable Simulation, Demonstration, and Imitation
We further introduce a distillation-friendly demonstration generation method that automatically generates a million high-quality demonstrations suitable for learning.
CrossVideo: Self-supervised Cross-modal Contrastive Learning for Point Cloud Video Understanding
This paper introduces a novel approach named CrossVideo, which aims to enhance self-supervised cross-modal contrastive learning in the field of point cloud video understanding.
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
Automated red teaming holds substantial promise for uncovering and mitigating the risks associated with the malicious use of large language models (LLMs), yet the field lacks a standardized evaluation framework to rigorously assess new methods.
The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
To measure these risks of malicious use, government institutions and major AI labs are developing evaluations for hazardous capabilities in LLMs.
Risk-averse Learning with Non-Stationary Distributions
Considering non-stationary environments in online optimization enables decision-maker to effectively adapt to changes and improve its performance over time.
