Search Results for author:
Found 48 papers, 21 papers with code
Demonstration of DB-GPT: Next Generation Data Interaction System Empowered by Large Language Models
The recent breakthroughs in large language models (LLMs) are positioned to transition many areas of software.
AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls
We also revisit the evaluation protocol introduced by previous works and identify a limitation in this protocol that leads to an artificially high pass rate.
EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
In this paper, we reconsider speculative sampling and derive two key observations.
DiPmark: A Stealthy, Efficient and Resilient Watermark for Large Language Models
Watermarking techniques offer a promising way to secure data via embedding covert information into the data.
RAIN: Your Language Models Can Align Themselves without Finetuning
We discover that by integrating self-evaluation and rewind mechanisms, unaligned LLMs can directly produce responses consistent with human preferences via self-boosting.
zkDL: Efficient Zero-Knowledge Proofs of Deep Learning Training
In response to this challenge, we present zero-knowledge deep learning (zkDL), an efficient zero-knowledge proof for deep learning training.
Gradient-Based Word Substitution for Obstinate Adversarial Examples Generation in Language Models
Furthermore, to show the transferability of obstinate word substitutions found by GradObstinate, we replace the words in four representative NLP benchmarks with their obstinate substitutions.
Cooperation or Competition: Avoiding Player Domination for Multi-Target Robustness via Adaptive Budgets
We identify a phenomenon named player domination in the bargaining game, namely that the existing max-based approaches, such as MAX and MSD, do not converge.
Understanding the Impact of Adversarial Robustness on Accuracy Disparity
More specifically, we demonstrate that while the constraint of adversarial robustness consistently degrades the standard accuracy in the balanced class setting, the class imbalance ratio plays a fundamentally different role in accuracy disparity compared to the Gaussian case, due to the heavy tail of the stable distribution.
Direct-Effect Risk Minimization for Domain Generalization
In this work, we introduce the concepts of direct and indirect effects from causal inference to the domain generalization problem.
Towards Robust Dataset Learning
In this paper, we study the problem of learning a robust dataset such that any classifier naturally trained on the dataset is adversarially robust.
Nash Equilibria and Pitfalls of Adversarial Training in Adversarial Robustness Games
Adversarial training is a standard technique for training adversarially robust models.
A Closer Look at Robustness to L-infinity and Spatial Perturbations and their Composition
In adversarial machine learning, the popular $\ell_\infty$ threat model has been the focus of much previous work.
RetrievalGuard: Provably Robust 1-Nearest Neighbor Image Retrieval
The challenge is to design a provably robust algorithm that takes into consideration the 1-NN search and the high-dimensional nature of the embedding space.
Causal Balancing for Domain Generalization
While machine learning models rapidly advance the state-of-the-art on various real-world tasks, out-of-domain (OOD) generalization remains a challenging problem given the vulnerability of these models to spurious correlations.
Building Robust Ensembles via Margin Boosting
Consequently, an emerging line of work has focused on learning an ensemble of neural networks to defend against adversarial attacks.
Certified Error Control of Candidate Set Pruning for Two-Stage Relevance Ranking
For example, on MS MARCO Passage v1, our method yields an average candidate set size of 27 out of 1, 000 which increases the reranking speed by about 37 times, while the MRR@10 is greater than a pre-specified value of 0. 38 with about 90% empirical coverage and the empirical baselines fail to provide such guarantee.
A Law of Robustness beyond Isoperimetry
We prove a Lipschitzness lower bound $\Omega(\sqrt{n/p})$ of the interpolating neural network with $p$ parameters on arbitrary data distributions.
Boosting Barely Robust Learners: A New Perspective on Adversarial Robustness
We present an oracle-efficient algorithm for boosting the adversarial robustness of barely robust learners.
Towards Transferable Unrestricted Adversarial Examples with Minimum Changes
Extensive experiments verify the effectiveness of our framework on balancing imperceptibility and transferability of the crafted adversarial examples.
Unrestricted Adversarial Attacks on ImageNet Competition
Many works have investigated the adversarial attacks or defenses under the settings where a bounded and imperceptible perturbation can be added to the input.
Towards Transferable Adversarial Perturbations with Minimum Norm
In this work, we propose a \emph{geometry-aware framework} to generate transferable adversarial perturbation with minimum norm for each input.
Self-Adaptive Training: Bridging Supervised and Self-Supervised Learning
We propose self-adaptive training -- a unified training algorithm that dynamically calibrates and enhances training processes by model predictions without incurring an extra computational cost -- to advance both supervised and self-supervised learning of deep neural networks.
An Analysis of Robustness of Non-Lipschitz Networks
Despite significant advances, deep networks remain highly susceptible to adversarial attack.
Adversarial Robustness of Stabilized NeuralODEs Might be from Obfuscated Gradients
Even replacing only the first layer of a ResNet by such a ODE block can exhibit further improvement in robustness, e. g., under PGD-20 ($\ell_\infty=0. 031$) attack on CIFAR-10 dataset, it achieves 91. 57\% and natural accuracy and 62. 35\% robust accuracy, while a counterpart architecture of ResNet trained with TRADES achieves natural and robust accuracy 76. 29\% and 45. 24\%, respectively.
A Closer Look at Accuracy vs. Robustness
Current methods for training robust networks lead to a drop in test accuracy, which has led prior works to posit that a robustness-accuracy tradeoff may be inevitable in deep learning.
Self-Adaptive Training: beyond Empirical Risk Minimization
We propose self-adaptive training---a new training algorithm that dynamically corrects problematic training labels by model predictions without incurring extra computational cost---to improve generalization of deep learning for potentially corrupted training data.
Random Smoothing Might be Unable to Certify $\ell_\infty$ Robustness for High-Dimensional Images
We show a hardness result for random smoothing to achieve certified adversarial robustness against attacks in the $\ell_p$ ball of radius $\epsilon$ when $p>2$.
Optimal Analysis of Subset-Selection Based L_p Low-Rank Approximation
We show that this algorithm has an approximation ratio of $O((k+1)^{1/p})$ for $1\le p\le 2$ and $O((k+1)^{1-1/p})$ for $p\ge 2$.
Design and Interpretation of Universal Adversarial Patches in Face Detection
We consider universal adversarial patches for faces -- small visual elements whose addition to a face image reliably destroys the performance of face detectors.
Optimal Analysis of Subset-Selection Based L_p Low Rank Approximation
We show that this algorithm has an approximation ratio of $O((k+1)^{1/p})$ for $1\le p\le 2$ and $O((k+1)^{1-1/p})$ for $p\ge 2$.
Efficient Symmetric Norm Regression via Linear Sketching
When the loss function is a general symmetric norm, our algorithm produces a $\sqrt{d} \cdot \mathrm{polylog} n \cdot \mathrm{mmc}(\ell)$-approximate solution in input-sparsity time, where $\mathrm{mmc}(\ell)$ is a quantity related to the symmetric norm under consideration.
Theoretically Principled Trade-off between Robustness and Accuracy
We identify a trade-off between robustness and accuracy that serves as a guiding principle in the design of defenses against adversarial examples.
Ranked #3 on
Adversarial Attack
on CIFAR-10
Stackelberg GAN: Towards Provable Minimax Equilibrium via Multi-Generator Architectures
In this work, we give new results on the benefits of multi-generator architecture of GANs.
Testing Matrix Rank, Optimally
This improves upon the previous $O(d^2/\epsilon^2)$ bound (SODA'03), and bypasses an $\Omega(d^2/\epsilon^2)$ lower bound of (KDD'14) which holds if the algorithm is required to read a submatrix.
Deep Neural Networks with Multi-Branch Architectures Are Less Non-Convex
We show that one cause for such success is due to the fact that the multi-branch architecture is less non-convex in terms of duality gap.
Algorithmic Regularization in Over-parameterized Matrix Sensing and Neural Networks with Quadratic Activations
We show that the gradient descent algorithm provides an implicit regularization effect in the learning of over-parameterized matrix factorization models and one-hidden-layer neural networks with quadratic activations.
Noise-Tolerant Interactive Learning Using Pairwise Comparisons
We study the problem of interactively learning a binary classifier using noisy labeling and pairwise comparison oracles, where the comparison oracle answers which one in the given two instances is more likely to be positive.
Differentially Private Clustering in High-Dimensional Euclidean Spaces
We study the problem of clustering sensitive data while preserving the privacy of individuals represented in the dataset, which has broad applications in practical machine learning and data analysis tasks.
Regression Phalanxes
Tomal et al. (2015) introduced the notion of "phalanxes" in the context of rare-class detection in two-class classification problems.
Matrix Completion and Related Problems via Strong Duality
This work studies the strong duality of non-convex matrix factorization problems: we show that under certain dual conditions, these problems and its dual have the same optimum.
Noise-Tolerant Interactive Learning from Pairwise Comparisons
We study the problem of interactively learning a binary classifier using noisy labeling and pairwise comparison oracles, where the comparison oracle answers which one in the given two instances is more likely to be positive.
Sample and Computationally Efficient Learning Algorithms under S-Concave Distributions
In this work, we introduce new convex geometry tools to study the properties of $s$-concave distributions and use these properties to provide bounds on quantities of interest to learning including the probability of disagreement between two halfspaces, disagreement outside a band, and the disagreement coefficient.
Noise-Tolerant Life-Long Matrix Completion via Adaptive Sampling
For this problem, we present an algorithm that returns a matrix of a small error, with sample complexity almost as small as the best prior results in the noiseless case.
Completing Low-Rank Matrices with Corrupted Samples from Few Coefficients in General Basis
As an application, we also find that the solutions to extended robust Low-Rank Representation and to our extended robust MC are mutually expressible, so both our theory and algorithm can be applied to the subspace clustering problem with missing values under certain conditions.
Relations among Some Low Rank Subspace Recovery Models
More specifically, we discover that once a solution to one of the models is obtained, we can obtain the solutions to other models in closed-form formulations.
Multi-rank Sparse Hierarchical Clustering
There has been a surge in the number of large and flat data sets - data sets containing a large number of features and a relatively small number of observations - due to the growing ability to collect and store information in medical research and other fields.
A Counterexample for the Validity of Using Nuclear Norm as a Convex Surrogate of Rank
For several rank minimization problems, such a replacement has been theoretically proven to be valid, i. e., the solution to nuclear norm minimization problem is also the solution to rank minimization problem.
